Motion trajectory planning method and apparatus, and intelligent driving device

Abstract

This application provides a motion trajectory planning method and apparatus, and an intelligent driving device. The method includes the steps of: acquiring a planned driving path and first motion parameters for a first intelligent driving device; acquiring a predicted motion trajectory and second motion parameters for a first object; when the planned driving path partially overlaps with the predicted motion trajectory, determining a planned motion trajectory for the first intelligent driving device based on the first motion parameter and the second motion parameter, where the planned motion trajectory includes a motion trajectory in which the first intelligent driving device intercepts or yields to the first object at a first preset speed; and controlling the first intelligent driving device to drive based on the planned motion trajectory.

Description

[Technical Field]

[0001] The present application relates to the field of intelligent driving, and more particularly to a motion trajectory planning method and apparatus, and an intelligent driving device. [Background technology]

[0002] In the field of autonomous vehicle driving, to ensure that an autonomous vehicle responds appropriately to surrounding obstacles, the vehicle's decision-making module labels the obstacles and provides appropriate inputs to the motion planning module. Traditional decision-making and planning based on finite state machines (FSMs) is typically affected by target trajectory prediction accuracy. For example, when the target is a pedestrian or non-vehicle, the direction of movement is unknown due to the large degrees of freedom of the target's movement, resulting in large fluctuations in trajectory prediction results. The target's predicted motion trajectory usually encroaches on the autonomous vehicle's path. In some scenarios, such as on roads with both vehicles and non-vehicles or at unmarked intersections, improper target trajectory prediction can cause problems such as unexpected, frequent, and sudden braking, false stops, and continuous yielding by the autonomous vehicle. This reduces the autonomous vehicle's passing efficiency and degrades the user's riding experience. Summary of the Invention [Means for solving the problem]

[0003] The present application provides a motion trajectory planning method and apparatus, and an intelligent driving device, to reduce problems such as unexpected frequent slow and fast braking, unexpected stopping, continuous yielding, and simultaneous starting and stopping of the intelligent driving device, thereby improving the passing efficiency of the intelligent driving device and improving the user's riding experience.

[0004] The intelligent driving device in this application may include land transportation means, water transportation means, air transportation means, industrial devices, agricultural devices, entertainment devices, etc. For example, the intelligent driving device may be a vehicle. The vehicle is a vehicle in a broad sense and may be a transportation means (such as a commercial vehicle, a passenger car, a motorcycle, an aircraft, or a train), an industrial vehicle (such as a forklift, a trailer, or a tractor), a construction vehicle (such as a hydraulic excavator, a bulldozer, or a crane), an agricultural device (such as a lawn mower or a harvester), a recreational device, a toy vehicle, etc. The type of vehicle is not particularly limited in the embodiments of this application. As another example, the intelligent driving device may be a transportation means such as an airplane or a ship.

[0005] According to a first aspect, there is provided a motion trajectory planning method for a first intelligent driving device capable of autonomous movement. The method includes the steps of: acquiring a planned driving path and first motion parameters for the first intelligent driving device, the first motion parameters including a speed and / or acceleration of the first intelligent driving device; acquiring a predicted motion trajectory and second motion parameters for a first object, the second motion parameters including a speed and / or acceleration of the first object; determining a planned motion trajectory for the first intelligent driving device based on the first motion parameter and the second motion parameter when the planned driving path partially overlaps with the predicted motion trajectory, the planned motion trajectory including a motion trajectory in which the first intelligent driving device intercepts or yields to the first object at a first preset speed; and controlling the first intelligent driving device to drive based on the planned motion trajectory.

[0006] In some possible implementations, the first preset speed may be a relatively low speed that the driver and passengers of the first intelligent driving device feel is safe, and may be adjusted based on the aggression of the driver and passengers.

[0007] In some possible implementations, the first preset speed is greater than or equal to 3 kilometers per hour and less than or equal to 15 kilometers per hour. For example, the first preset speed may be 5 km / h, 10 km / h, or another speed.

[0008] It should be noted that in this application, whether the first intelligent driving device intercepts or yields to the first object is determined based on the particular object that passes through the conflict area earlier. If the first intelligent driving device passes through the conflict area earlier than the first object, the first intelligent driving device is considered to intercept the first object, or if the first intelligent driving device passes through the conflict area later than the first object, the first intelligent driving device is considered to yield to the first object. A conflict area is an area where the predicted planned path of the first intelligent driving device overlaps with the estimated trajectory of the first object.

[0009] In the above technical solution, while ensuring safety and complying with traffic regulations, the first intelligent driving device can actively maintain a relatively low speed to closely monitor the behavior of the first object. As a result, the planned movement trajectory of the first intelligent driving device is less affected by the accuracy of the first object's trajectory prediction. When the first intelligent driving device yields to the first object, the first intelligent driving device can travel at a first preset speed without needing to stop. This helps improve the driving stability of the first intelligent driving device. When the first intelligent driving device is transporting passengers, passenger comfort can be improved, improving the passenger riding experience. In addition, because the first intelligent driving device does not need to stop while yielding to the first object, the passing efficiency of the first intelligent driving device can be further improved. When the first intelligent driving device intercepts the first object at a first preset speed, because the first intelligent driving device travels at a relatively slow speed, the first object can adjust its movement trajectory based on the movement trajectory of the first intelligent driving device, thereby preventing the first intelligent driving device from repeatedly yielding to the first object. This helps improve the passing efficiency of the first intelligent driving device. In particular, in scenarios such as narrow roads where both automobiles and non-automobiles may travel or unmarked intersections, the first intelligent driving device will not encounter problems such as frequent, unexpected, and incorrect braking, incorrect stopping, continuous yielding, and simultaneous starting and stopping. This helps improve the driving stability and passing efficiency of the first intelligent driving device.

[0010] For example, the first intelligent driving device may be a vehicle capable of moving autonomously, or may be another object capable of moving autonomously, such as an intelligent robot.

[0011] For example, the first object may be another intelligent driving device, including an intelligent driving device capable of autonomous movement and / or a manually controlled intelligent driving device. The intelligent driving device may be a motor vehicle or a non-motor vehicle. Alternatively, the first object may be a person or another object capable of autonomous movement in addition to the intelligent driving device.

[0012] For example, the planned driving route of the first intelligent driving device may be a route generated by the planning and control module of the first intelligent driving device and expected to be driven by the first intelligent driving device in a future period of time. It should be understood that the route may include only spatial location information.

[0013] For example, the predicted motion trajectory of the first object may be a motion trajectory of the first object in a future time period and a motion trajectory predicted by a trajectory prediction module of the first intelligent driving device based on the obtained position, velocity, and / or acceleration of the first object. In some possible implementations, the predicted motion trajectory of the first object may alternatively be transmitted to the first intelligent driving device by a cloud or another facility.

[0014] It should be understood that the "future period" may be 10 seconds, 20 seconds, or some other duration.

[0015] It should be understood that when the planned driving path partially overlaps with the predicted motion trajectory, the driving trajectory of the first intelligent driving device needs to be planned to ensure the safety of the interaction between the first intelligent driving device and the first object and the user's riding experience in the first intelligent driving device. In this case, the first game strategy can be determined based on the first motion parameters of the first intelligent driving device and the motion parameters of the first object to further determine the planned motion trajectory of the first intelligent driving device.

[0016] In some possible implementations, when the first motion parameters include only the velocity of the first intelligent driving device, the acceleration of the first intelligent driving device may be estimated based on the velocity of the first intelligent driving device. When the second motion parameters include only the velocity of the first object, the acceleration of the first object may be estimated based on the velocity of the first object. When the first motion parameters include only the acceleration of the first intelligent driving device, the velocity of the first intelligent driving device may be estimated with reference to the acceleration based on position information of the first intelligent driving device within the planned driving path. When the second motion parameters include only the acceleration of the first object, the velocity of the first object may be estimated with reference to the acceleration based on position information of the first object within the predicted motion trajectory.

[0017] Referring to the first aspect, in some implementation forms of the first aspect, the step of determining a planned motion trajectory based on the first motion parameter and the second motion parameter includes the steps of: determining a first estimated trajectory of the first intelligent driving device based on a first sampled acceleration and the first motion parameter, where the first sampled acceleration is determined within the sampling space and is an acceleration that can be reached by the first intelligent driving device; determining a second estimated trajectory of the first object based on a second sampled acceleration and the second motion parameter, where the second sampled acceleration is determined within the sampling space and is an acceleration that can be reached by the first object; and determining a planned motion trajectory based on the first estimated trajectory and the second estimated trajectory when the first estimated trajectory and the second estimated trajectory indicate that the first intelligent driving device will not collide with the first object or indicate that the first object will collide with a side housing or rear of the first intelligent driving device in the driving direction of the first object at the first time point, where the first time point is a time point after the current time point.

[0018] It should be understood that multiple groups of pairs of the first sampled acceleration and the second sampled acceleration can be acquired in the sampling space, and multiple groups of pairs of the first estimated trajectory and the second estimated trajectory can be determined. Furthermore, the planned motion trajectory of the first intelligent driving device can be determined based on the pair with the smallest strategic cost for autonomous driving in the multiple groups of pairs of the first estimated trajectory and the second estimated trajectory.

[0019] For example, in the sampling space, the minimum value of the first sampling acceleration and the second sampling acceleration is -4 m / s 2 The maximum value is 3 m / s 2In the plurality of groups of pairs of first sampling acceleration and second sampling acceleration obtained in the sampling space, the sampling interval between two groups of the first sampling acceleration may be 1 m / s 2 The sampling interval between two groups of the second sampling acceleration may be 1 m / s or another value. 2 It should be understood that the second estimated trajectory is an estimable motion trajectory of the first object.

[0020] In some possible implementations, both the first intelligent driving device and the first object are vehicles. When both the first intelligent driving device and the first object are in a driving state, "the first object collides with the side housing or rear of the first intelligent driving device in the driving direction of the first object" can be understood as the front of the first object colliding with a part of the body of the first intelligent driving device other than the front. Alternatively, when the first object is in an inverted state, the rear of the first object collides with a part of the body of the first intelligent driving device other than the front.

[0021] In some possible implementations, it may be determined that the first intelligent driving device will collide with the first object (the colliding portion of the first intelligent driving device is not limited) based on the first estimated trajectory and the second estimated trajectory, and the first intelligent driving device is stationary when the collision occurs. In this case, the planned motion trajectory may alternatively be determined based on the first estimated trajectory and the second estimated trajectory.

[0022] In some possible implementation forms, it may be determined that the first intelligent driving device will collide with the first object based on the first estimated trajectory and the second estimated trajectory, and when the collision type is such that the first intelligent driving device collides with the side housing or rear of the first object in the driving direction of the first intelligent driving device, the first estimated trajectory and the second estimated trajectory are ignored, i.e., the planned movement trajectory is no longer determined based on the first estimated trajectory and the second estimated trajectory.

[0023] In the above technical solution, the game strategy of the first intelligent driving device can be determined based on whether the first intelligent driving device will collide with the first object and the collision type, which helps to improve the driving safety of the first intelligent driving device.

[0024] Referring to the first aspect, in some implementation forms of the first aspect, the first motion parameter includes a speed and / or acceleration of the first intelligent driving device, and the step of determining a first estimated trajectory of the first intelligent driving device based on the first sampled acceleration and the first motion parameter includes the steps of determining a first estimated sub-trajectory based on the first sampled acceleration and the speed and / or acceleration of the first intelligent driving device, wherein the speed of the first intelligent driving device at an end point of the first estimated sub-trajectory is a first preset speed; determining a second estimated sub-trajectory based on the first preset speed, wherein the end point of the first estimated sub-trajectory is a start point of the second estimated sub-trajectory; and determining the first estimated trajectory based on the first estimated sub-trajectory and the second estimated sub-trajectory.

[0025] It should be noted that the "end point of the first estimated sub-trajectory" is not the point at which the first intelligent driving device stops moving, but rather the "end point of the first estimated sub-trajectory" is only used as a feature to distinguish two estimated sub-trajectory segments with different characteristics within the first estimated trajectory, and the "end point of the first estimated sub-trajectory" may also be referred to as the "start point of the second estimated sub-trajectory."

[0026] In some possible implementations, when the first sampled acceleration is a negative value and the current acceleration of the first intelligent driving device is not equal to the first sampled acceleration, the first estimated sub-trajectory may include a trajectory along which the acceleration of the first intelligent driving device changes from the current acceleration to the first sampled acceleration. When the acceleration of the first intelligent driving device is changed to the first sampled acceleration, the velocity of the first intelligent driving device does not decrease to the first preset velocity. In this case, the first estimated sub-trajectory may further include a trajectory along which the first intelligent driving device moves at the first sampled acceleration to decrease the velocity of the first intelligent driving device to the first preset velocity.

[0027] In some possible implementations, when the first sampled acceleration is a positive value and the current acceleration of the first intelligent driving device is not equal to the first sampled acceleration, the first estimated sub-trajectory may include a trajectory along which the acceleration of the first intelligent driving device changes from the current acceleration to the first sampled acceleration. When the acceleration of the first intelligent driving device is changed to the first sampled acceleration, the speed of the first intelligent driving device does not increase to the first preset speed. In this case, the first estimated sub-trajectory may further include a trajectory along which the first intelligent driving device moves at the first sampled acceleration to increase the speed of the first intelligent driving device to the first preset speed.

[0028] In some possible implementations, if the first sampled acceleration is equal to the current acceleration of the first intelligent driving device and the current speed of the first intelligent driving device is not equal to the first preset speed, the first estimated sub-trajectory may include a trajectory along which the first intelligent driving device moves at the current acceleration (i.e., the first sampled acceleration) and changes its current speed to the first preset speed.

[0029] In some possible implementations, if the first sampled acceleration is not equal to the current acceleration of the first intelligent driving device and the current speed of the first intelligent driving device is equal to the first preset speed, the first estimated sub-trajectory may be null, i.e., the second estimated sub-trajectory is determined directly based on the current speed (i.e., the first preset speed).

[0030] In some possible implementations, the first estimated sub-trajectory may be further determined based on the first sampled acceleration and the speed and / or acceleration of the first intelligent driving device, where the speed of the first intelligent driving device at the end point of the first estimated sub-trajectory is a second speed, the second speed being the maximum speed at which the first intelligent driving device can travel or the maximum speed limit of the road section along which the first intelligent driving device travels, and the second estimated sub-trajectory is determined based on the second speed. The first estimated trajectory includes a first estimated sub-trajectory and a second estimated sub-trajectory.

[0031] For example, when the first sampled acceleration is a positive value and the current acceleration of the first intelligent driving device is not equal to the first sampled acceleration, the first estimated sub-trajectory may include a trajectory along which the acceleration of the first intelligent driving device changes from the current acceleration to the first sampled acceleration. When the acceleration of the first intelligent driving device is changed to the first sampled acceleration, the speed of the first intelligent driving device does not increase to the second preset speed. In this case, the first estimated sub-trajectory may further include a trajectory along which the first intelligent driving device moves at the first sampled acceleration to increase the speed of the first intelligent driving device to the second preset speed.

[0032] In some possible implementations, the first estimated trajectory of the first intelligent driving device may alternatively be determined based on the second sampled acceleration, and the first motion parameter specifically includes: determining a third estimated sub-trajectory based on the second sampled acceleration and the speed and / or acceleration of the first intelligent driving device, wherein the speed of the first intelligent driving device at the end point of the third estimated sub-trajectory is a third speed or 0, and the third speed is the maximum speed at which the first intelligent driving device can travel or the maximum speed limit of the road section on which the first intelligent driving device travels; and determining a fourth estimated sub-trajectory based on the third speed when the speed of the first intelligent driving device at the end point of the third estimated sub-trajectory is the third speed, wherein the first estimated trajectory includes the third estimated sub-trajectory or the first estimated trajectory includes the third estimated sub-trajectory and the fourth estimated sub-trajectory, and the end point of the third estimated sub-trajectory is the start point of the fourth estimated sub-trajectory.

[0033] It should be understood that the "estimated sub-trajectory" in the above technical solution can be understood as a set of points along which the position of the first intelligent driving device changes over time in the forward direction of the first intelligent driving device, and each point does not include a position perpendicular to the forward direction of the first intelligent driving device. For example, if the first intelligent driving device is an intelligent driving device, the "forward direction of the first intelligent driving device" may be in a plane parallel to the ground and parallel to the longitudinal symmetry plane of the intelligent driving device.

[0034] In the above technical solution, when the trajectory planning of the first intelligent driving device in the forward direction of the first intelligent driving device is performed, the speed of the first intelligent driving device is reduced to a maximum first preset speed, thereby preventing the speed of the first intelligent driving device from decreasing to 0 and effectively avoiding frequent stops of the first intelligent driving device. This helps improve the passing efficiency of the first intelligent driving device. When the first intelligent driving device is transporting passengers, the passenger's riding experience can be further improved.

[0035] In relation to the first aspect, in some implementation forms of the first aspect, the step of determining a second estimated trajectory of the first object based on the third sampled acceleration and the second motion parameter includes the steps of: determining a fifth estimated sub-trajectory based on the third sampled acceleration and the velocity and / or acceleration of the first object, wherein the velocity of the first object at an end point of the fifth estimated sub-trajectory is a fourth speed or 0, and the fourth speed is the maximum speed at which the first object can travel or the maximum speed limit of the road section on which the first object travels; and, when the velocity of the first intelligent driving device at the end point of the fifth estimated sub-trajectory is the fourth speed, determining a sixth estimated sub-trajectory based on the fourth speed, wherein the second estimated trajectory includes the fifth estimated sub-trajectory, or the second estimated trajectory includes the fifth estimated sub-trajectory and the sixth estimated sub-trajectory.

[0036] Referring to the first aspect, in some implementation forms of the first aspect, the step of determining a planned motion trajectory based on the first estimated trajectory and the second estimated trajectory includes the steps of determining a first game strategy based on the first estimated trajectory and the second estimated trajectory, the first game strategy instructing the first intelligent driving device to intercept the path of the first object at a first preset speed or yield to the first object, and when the first duration is greater than a first time threshold, determining the planned motion trajectory based on the first game strategy, the planned driving path, and the second estimated trajectory.

[0037] For example, the first time threshold may be 0.1 seconds, or 0.3 seconds, or the first time threshold may be another value.

[0038] It should be understood that in the process of moving the first intelligent driving device and the first object, multiple groups of estimated trajectory pairs may be estimated in real time based on the first motion parameters of the first intelligent driving device and the second motion parameters of the first object, and different game strategies may be determined based on the different estimated trajectory pairs. In this application, the game strategies include: the first intelligent driving device intercepting the path of the first object at a first preset speed; the first intelligent driving device yielding to the first object at the first preset speed; and the first intelligent driving device intercepting the path of the first object or yielding to the first object in a non-creeping manner.

[0039] In some possible implementations, the control device of the first intelligent driving device determines the game strategy once every fixed time period, for example, 20 milliseconds or 50 milliseconds.

[0040] When a game strategy is determined based on an estimated trajectory pair, the game strategy determined for the current frame (or current period) may differ from the game strategy determined for the previous frame (or previous period). To prevent instability of the planned motion trajectory and instability caused by frequent changes in the game strategy, the present application proposes that the planned motion trajectory be determined based on a first game strategy when it is determined that the duration of the first game strategy is greater than a first time threshold. Assume that the first game strategy is for the first intelligent driving device to intercept the path of the first object at a first preset speed, the second game strategy is for the first intelligent driving device to intercept the path of the first object or yield to the first object in a non-creeping manner, and the third game strategy is for the first intelligent driving device to yield to the first object at a first preset speed. For example, the fixed time is 20 milliseconds, and the first time threshold is 0.1 seconds. If the determined game strategy is the second game strategy before the game strategy is determined as the first game strategy, the game strategy needs to be determined as the first game strategy five consecutive times, and then the planned movement trajectory is further determined based on the first game strategy, the planned driving path, and the second estimated trajectory.

[0041] In some possible implementations, the value of the first time threshold may be determined based on the game strategy before the game strategy is determined as the first game strategy. In some possible implementations, if the game strategy determined before the first game strategy is determined is the second game strategy, the first time threshold is the first threshold, or if the game strategy determined before the first game strategy is determined is the third game strategy, the first time threshold is the second threshold. The first threshold may be smaller than the second threshold. For example, the first threshold may be 0.1 seconds, and the second threshold may be 0.3 seconds.

[0042] In some possible implementations, if a second game strategy is determined after the first game strategy is determined, and the duration of the second game strategy is greater than a third threshold, the planned movement trajectory is determined based on the second game strategy. The third threshold is greater than the second threshold. For example, the first time threshold is the second threshold. The first threshold is less than the second threshold. For example, the third threshold may be 0.5 seconds.

[0043] In the above technical solution, when the game strategy is changed, whether to re-plan the trajectory based on the game strategy can be determined based on the duration of the changed game strategy. If the duration of the changed game strategy does not satisfy the condition, the movement trajectory will not be re-planned, thereby avoiding frequent changes of the game strategy and improving the stability of the movement trajectory planning.

[0044] Referring to the first aspect, in some implementation forms of the first aspect, the step of determining a planned motion trajectory based on a first game strategy, a planned driving path, and a second estimated trajectory includes the steps of determining a period during which a first position space of the first object occupies a second position space of the first intelligent driving device based on the planned driving path and the second estimated trajectory, and determining a planned motion trajectory based on the first game strategy, the second position space, and the period, wherein the planned motion trajectory includes a trajectory during which the first intelligent driving device moves at a first preset speed in the second position space, or the planned motion trajectory includes a trajectory during which the first intelligent driving device moves at a first preset speed during the period.

[0045] In some possible implementations, determining a planned movement trajectory based on the first game strategy, the second position space, and the period includes determining a third position space based on the first game strategy, the second position space, and a distance threshold safedis; determining a first period based on the period and a time threshold TimeGap; and determining a planned movement trajectory based on the first period, a first preset speed, and the third position space.

[0046] Referring to the first aspect, in some implementation forms of the first aspect, before the step of determining a first game strategy based on the first estimated trajectory and the second estimated trajectory, the method further includes a step of determining that a strategy cost of an estimated trajectory pair including the first estimated trajectory and the second estimated trajectory is smallest.

[0047] For example, the strategy cost may include a security strategy cost and may further include at least one of a comfort strategy cost, a traversability strategy cost, and a right-of-way strategy cost. Specifically, the security strategy cost represents the driving safety of the moving object, with lower security indicating a higher strategy cost. The comfort strategy cost represents the user's comfort with the moving object, with a higher acceleration change rate of the moving object generally indicating lower comfort and a higher strategy cost. The traversability strategy cost represents the traversability of the moving object passing through a conflict point. For example, the greater the difference between the calibration time and the time at which the first estimated trajectory of the first intelligent driving device passes through the conflict point, the lower the traversability and the higher the strategy cost. The calibration time is the time at which the estimated trajectory of the first intelligent driving device passes through the conflict point when the lateral offset of the first intelligent driving device is 0 and the sampling acceleration is 0. The right-of-way strategy cost represents whether the motion status of the object with a strong right-of-way changes. If the pair of the first estimated trajectory and the second estimated trajectory changes the motion status of the object with a strong right-of-way, the strategy cost is high.

[0048] It should be understood that the "moving object" may be the first intelligent driving device or the first object.

[0049] In some possible implementations, the strategy costs may include only the security strategy costs. Alternatively, in addition to the security strategy costs, the strategy costs may further include a comfort strategy cost, a traversability strategy cost, and a right-of-way strategy cost of the first intelligent driving device and the first object, and the weights of the strategy costs may be different. In some possible implementations, the weights of each strategy cost may alternatively vary depending on the driving scenario.

[0050] In some possible implementations, the minimum value of the strategy cost may be 0.

[0051] For example, the first object is an intelligent driving device. When it is determined based on the first estimated trajectory and the second estimated trajectory that a first object in the driving direction of the first object will collide with the first intelligent driving device in a direction deviating from the driving direction of the first intelligent driving device, the overall strategy cost can be determined by referring to the speed of the first object at the collision location. It should be understood that when the strategy cost includes only a security strategy cost, when multiple groups of first estimated trajectory and second estimated trajectory pairs are estimated, the first estimated trajectory and second estimated trajectory pair with the lowest security strategy cost is used to determine the first game strategy.

[0052] In the above technical solution, the strategic cost of the first estimated trajectory and the second estimated trajectory pair can be evaluated, and the specific first estimated trajectory / second estimated trajectory pair used for trajectory planning of the first intelligent driving device can be determined based on the strategic cost. This helps improve the validity of the planned motion trajectory of the first intelligent driving device. Furthermore, the planned motion trajectory can be more accurately evaluated by referring to the driving scenario and multiple strategic cost evaluation dimensions.

[0053] Referring to the first aspect, in some implementation forms of the first aspect, determining a first estimated trajectory of the first intelligent driving device based on the first sampled acceleration and the first motion parameter includes determining the first estimated trajectory based on a lateral offset of the first intelligent driving device, the first sampled acceleration, and the first motion parameter, wherein the lateral offset is an offset perpendicular to the driving direction of the first intelligent driving device.

[0054] In some possible implementations, an estimated sub-trajectory (or sometimes referred to as a longitudinal trajectory) of the first intelligent driving device is determined based on the first sampled acceleration and the first motion parameter, i.e., the estimated sub-trajectory is a trajectory of the first intelligent driving device in a driving direction parallel to the first intelligent driving device.

[0055] Furthermore, a first estimated trajectory of the first intelligent driving device can be determined based on the estimated sub-trajectory and with reference to the lateral offset of the first intelligent driving device. The first estimated trajectory is a set including points whose coordinates of the first intelligent driving device change over time, i.e., is a result obtained by combining the longitudinal trajectory of the first intelligent driving device and the lateral offset of the first intelligent driving device.

[0056] It should be appreciated that for the first object, a second estimated trajectory may also be determined based on the lateral offset, the second sampled acceleration, and the second motion parameter of the first object.

[0057] Referring to the first aspect, in some implementation forms of the first aspect, before the step of obtaining the predicted motion trajectory and second motion parameters of the first object, the method further includes a step of determining that the distance between the first object and the first intelligent driving device is less than or equal to a first distance threshold and greater than or equal to a second distance threshold.

[0058] For example, the first distance threshold may be 100 meters, or 200 meters, or another value.

[0059] For example, the second distance threshold may be determined based on a classification of a closest in-path vehicle (CIPV). When the second distance threshold is determined by a classification of a CIPV, it should be understood that the second distance threshold may be different when the first object is located in different directions around the first intelligent driving device. In some possible implementations, the second distance threshold may also be another time distance and / or another spatial distance. For example, if the second distance is a time distance, the second distance threshold may be 2 seconds, 3 seconds, or another value; or if the second distance is a spatial distance, the second distance threshold may be 1.5 meters, 2 meters, or another value.

[0060] In some possible implementations, if there are two or more first objects whose distances to the first intelligent driving device are equal to or less than a first distance threshold, the distances between the two or more first objects and the first intelligent driving device must all be determined to be equal to or greater than a second distance threshold. In other words, if the distance between any first object around the first intelligent driving device and the first intelligent driving device is less than the second distance threshold, the autonomous driving decision-making and trajectory planning of the first intelligent driving device will not be performed.

[0061] In the above technical solution, the maximum distance between the first object and the first intelligent driving device is limited, thereby eliminating first objects that are too far from the first intelligent driving vehicle and reducing the amount of calculation in the trajectory planning process. The minimum distance between the first object and the first intelligent driving device is limited, thereby preventing the first object from being too close to the first intelligent driving device and not having enough space to slow down and drive away. This helps to improve the safety of the autonomous driving process.

[0062] According to a second aspect, a motion trajectory planning method is provided, the method including the steps of: acquiring a planned driving path and first motion parameters of a first intelligent driving device; acquiring a predicted motion trajectory and second motion parameters of a first object; determining a planned motion trajectory of the first intelligent driving device based on the first motion parameters and the second motion parameters when the planned driving path partially overlaps with the predicted motion trajectory, wherein the planned motion trajectory indicates that the first intelligent driving device will pass through a conflict area at a first preset speed, or indicates that the first intelligent driving device will travel at a first preset speed when the first object passes through the conflict area, the conflict area being an area where the planned driving path of the first intelligent driving device partially overlaps with the estimated trajectory of the first object; and controlling the first intelligent driving device to travel based on the planned motion trajectory.

[0063] According to a third aspect, a motion trajectory planning method is provided, the method including the steps of: acquiring a planned driving path and first motion parameters of a first intelligent driving device; acquiring a predicted motion trajectory and second motion parameters of a first object; when the planned driving path partially overlaps with the predicted motion trajectory, determining a first game strategy based on the first motion parameters and the second motion parameters, wherein the first game strategy instructs the first intelligent driving device to intercept the path of the first object at a first preset speed or to yield to the first object; and determining a planned motion trajectory of the first intelligent driving device based on the first game strategy.

[0064] It should be noted that the first game strategy is used to determine whether the first intelligent driving device will intercept the first object's path or yield to the first object at a first preset speed, so that the first intelligent driving device is predicted to pass through the conflict area at the first preset speed, or the first intelligent driving device is predicted to move at the first preset speed when the first object passes through the conflict area. However, in a specific implementation process, the speed of the first intelligent driving device when passing through the conflict area does not necessarily have to reach the first preset speed, or may be faster than the first preset speed. Below, two examples are used to specifically describe scenarios that may occur in the actual driving process of the first intelligent driving device.

[0065] If the first intelligent driving device passes through the conflict area faster than the first object, this can be further detailed as follows:

[0066] 1. The first intelligent driving device passes through a conflict area in the process of accelerating from a driving speed slower than a first preset speed to the first preset speed. Furthermore, after the first intelligent driving device passes through the conflict area, the interaction between the first intelligent driving device and the first object ends. Therefore, after the first intelligent driving device passes through the conflict area, it can be determined and planned that the first intelligent driving device will continue to drive at a driving speed faster than the first preset speed.

[0067] 2. If the speed of the first intelligent driving device reaches a first preset speed before it reaches the conflict area (the first preset speed may decrease from a driving speed faster than the first preset speed, or increase from a driving speed slower than the first preset speed), the first intelligent driving device passes through the conflict area at the first preset speed. Furthermore, after the first intelligent driving device passes through the conflict area, the interaction between the first intelligent driving device and the first object ends. Therefore, it may be determined and planned that the first intelligent driving device will continue driving at a driving speed faster than the first preset speed after passing through the conflict area.

[0068] 3. The first intelligent driving device passes through a conflict area in the process of decelerating from a driving speed faster than the first preset speed to the first preset speed. Furthermore, after the first intelligent driving device passes through the conflict area, the interaction between the first intelligent driving device and the first object ends. Therefore, it can be determined and planned that after the first intelligent driving device passes through the conflict area, the first intelligent driving device will end the deceleration state and continue to drive at a driving speed faster than the first preset speed.

[0069] It will be understood that in the first two cases above, the first intelligent driving device intercepts the path of the first object at a driving speed equal to or less than the first preset speed, and in the third case, the first intelligent driving device intercepts the path of the first object at a driving speed greater than the first preset speed.

[0070] If the first intelligent driving device passes through the conflict area slower than the first object, this can be further detailed as follows:

[0071] 1. In the process of the first intelligent driving device driving toward the conflict area, the first intelligent driving device is in a state of accelerating from a driving speed slower than the first preset speed to the first preset speed. In this case, the first object passes through the conflict area. Furthermore, after the first object passes through the conflict area, the interaction between the first intelligent driving device and the first object ends. Therefore, after it is determined that the first object passes through the conflict area, it may be determined and planned that the first intelligent driving device will continue driving at a driving speed faster than the first preset speed.

[0072] 2. In the process of the first intelligent driving device driving toward the conflict area at a first preset speed, the first object passes through the conflict area. Furthermore, after the first object passes through the conflict area, the interaction between the first intelligent driving device and the first object ends. Therefore, after it is determined that the first object passes through the conflict area, it may be determined and planned that the first intelligent driving device will continue driving at a driving speed faster than the first preset speed.

[0073] 3. In the process of the first intelligent driving device driving toward the conflict area, the first intelligent driving device is decelerating from a driving speed faster than the first preset speed to the first preset speed. In this case, the first object passes through the conflict area. Furthermore, after the first object passes through the conflict area, the interaction between the first intelligent driving device and the first object ends. Therefore, after it is determined that the first object passes through the conflict area, it may be determined and planned that the first intelligent driving device will continue driving at a driving speed faster than the first preset speed.

[0074] It will be understood that in the first two cases above, the first intelligent driving device yields to the first object at a driving speed equal to or less than the first preset speed, and in the third case, the first intelligent driving device yields to the first object at a driving speed higher than the first preset speed.

[0075] In other words, whether the first intelligent driving device intercepts the first object's path at a first preset speed or concedes to the first object through decision-making based on a first game strategy, when the first intelligent driving device passes through the conflict area, the speed of the first intelligent driving device may be the first preset speed, or may be faster or slower than the first preset speed.

[0076] It should be noted that after the aforementioned "interaction between the first intelligent driving device and the first object ends," the motion behavior of the first object no longer affects the decision-making and planning of the motion trajectory of the first intelligent driving device. It should be understood that after the interaction between the first intelligent driving device and the first object ends, another object may appear that is too close to the first intelligent driving device. In this case, after passing through the conflict area, the first intelligent driving device can stop in a timely manner instead of continuing to drive at a driving speed faster than the first preset speed.

[0077] According to a fourth aspect, there is provided a motion trajectory planning apparatus including: an acquisition unit configured to acquire a planned driving path and first motion parameters of a first intelligent driving device and acquire a predicted motion trajectory and second motion parameters of a first object; and a processing unit configured, when the planned driving path partially overlaps with the predicted motion trajectory, to determine a planned motion trajectory of the first intelligent driving device based on the first motion parameter and the second motion parameter and control the first intelligent driving device to drive based on the planned motion trajectory, where the planned motion trajectory includes a motion trajectory in which the first intelligent driving device intercepts or yields to the first object at a first preset speed.

[0078] Referring to the fourth aspect, in some implementation forms of the fourth aspect, the processing unit determines a first estimated trajectory of the first intelligent driving device based on a first sampled acceleration and a first motion parameter, where the first sampled acceleration is determined within the sampling space and is an acceleration that the first intelligent driving device may reach; the processing unit is configured to determine a second estimated trajectory of the first object based on a second sampled acceleration and a second motion parameter, where the second sampled acceleration is determined within the sampling space and is an acceleration that the first object may reach; and the processing unit is configured to determine a planned motion trajectory based on the first estimated trajectory and the second estimated trajectory when the first estimated trajectory and the second estimated trajectory indicate that the first intelligent driving device will not collide with the first object, or when the first object in the driving direction of the first object indicates that the first object will collide with the first intelligent driving device in a direction away from the driving direction of the first intelligent driving device, where the first time point is a time point after the current time point.

[0079] Referring to the fourth aspect, in some implementation forms of the fourth aspect, the first motion parameter includes a speed and / or acceleration of the first intelligent driving device, and the processing unit is specifically configured to determine a first estimated sub-trajectory based on the first sampled acceleration and the speed and / or acceleration of the first intelligent driving device, wherein the speed of the first intelligent driving device at an end point of the first estimated sub-trajectory is a first preset speed, and determine a second estimated sub-trajectory based on the first preset speed, and the first estimated trajectory includes the first estimated sub-trajectory and the second estimated sub-trajectory.

[0080] Referring to the fourth aspect, in some implementation forms of the fourth aspect, the processing unit is configured to specifically determine a first game strategy based on the first estimated trajectory and the second estimated trajectory, the first game strategy instructing the first intelligent driving device to intercept the path of the first object at a first preset speed or yield to the first object, and when the first duration is longer than a first time threshold, determine a planned movement trajectory based on the first game strategy, the planned driving path, and the second estimated trajectory.

[0081] Referring to the fourth aspect, in some implementation forms of the fourth aspect, the processing unit is specifically configured to determine a period during which the first position space of the first object occupies the second position space of the first intelligent driving device based on the planned driving path and the second estimated trajectory, and to determine a planned motion trajectory based on the first game strategy, the second position space, and the period, wherein the planned motion trajectory includes a trajectory during which the first intelligent driving device moves at a first preset speed in the second position space, or the planned motion trajectory includes a trajectory during which the first intelligent driving device moves at a first preset speed during the period.

[0082] Referring to the fourth aspect, in some implementation forms of the fourth aspect, the processing unit is specifically configured to determine that a strategy cost of an estimated trajectory pair including a first estimated trajectory and a second estimated trajectory is smallest.

[0083] Referring to the fourth aspect, in some implementation forms of the fourth aspect, the processing unit is specifically configured to determine a first estimated trajectory based on a lateral offset of the first intelligent driving device, a first sampled acceleration, and a first motion parameter, wherein the lateral offset is an offset perpendicular to the driving direction of the first intelligent driving device.

[0084] Referring to the fourth aspect, in some implementation forms of the fourth aspect, the processing unit is further configured to determine that the distance between the first object and the first intelligent driving device is less than or equal to a first distance threshold and greater than or equal to a second distance threshold.

[0085] According to a fifth aspect, a motion trajectory planning apparatus is provided. The apparatus includes: an acquisition unit configured to acquire a planned driving path and first motion parameters of a first intelligent driving device and acquire a predicted motion trajectory and second motion parameters of a first object; and a processing unit configured to determine a planned motion trajectory of the first intelligent driving device based on the first motion parameters and the second motion parameters when the planned driving path overlaps with the predicted motion trajectory, where the planned motion trajectory indicates that the first intelligent driving device will pass through a conflict area at a first preset speed or indicates that the first intelligent driving device will travel at the first preset speed when the first object passes through the conflict area, the conflict area being an area where the planned driving path of the first intelligent driving device overlaps with the estimated trajectory of the first object, and the processing unit is configured to control the first intelligent driving device to travel based on the planned motion trajectory.

[0086] According to a sixth aspect, there is provided a motion trajectory planning apparatus including: an acquisition module configured to acquire a planned driving path and first motion parameters of a first intelligent driving device and acquire a predicted motion trajectory and second motion parameters of a first object; and a processing module configured to determine a first game strategy based on the first motion parameter and the second motion parameter when the planned driving path overlaps with the predicted motion trajectory, the first game strategy instructing the first intelligent driving device to intercept the path of the first object or yield to the first object at a first preset speed, the processing module configured to determine the planned motion trajectory of the first intelligent driving device based on the first game strategy.

[0087] According to a seventh aspect, there is provided a motion trajectory planning device, the device including: a memory configured to store a program; and a processor configured to execute the program stored in the memory. When the program stored in the memory is executed, the processor is configured to execute a method according to any one of the possible implementation forms of the first to third aspects.

[0088] According to an eighth aspect, there is provided an intelligent driving device, the intelligent driving device including an apparatus according to any one of the possible implementation forms of the fourth to seventh aspects.

[0089] Referring to the eighth aspect, in some implementations of the eighth aspect, the intelligent driving device is a vehicle.

[0090] According to a ninth aspect, there is provided a computer program product, the computer program product comprising computer program code which, when executed on a computer, enables the computer to perform a method according to any one of the possible implementations of the first to third aspects.

[0091] It should be noted that all or part of the computer program code may be stored in a first storage medium, which may be encapsulated together with the processor or separately from the processor, which is not specifically limited in the embodiments of the present application.

[0092] According to a tenth aspect, there is provided a computer-readable medium storing program code that, when executed on a computer, enables the computer to perform a method according to any one of the possible implementations of the first to third aspects.

[0093] According to an eleventh aspect, there is provided a chip, the chip including a processor configured to invoke a computer program or computer instructions stored in a memory, such that the processor performs a method according to any one of the possible implementations of the first to third aspects.

[0094] In relation to the eleventh aspect, in one possible implementation form, the processor is coupled to the memory via an interface.

[0095] Referring to the eleventh aspect, in a possible implementation, the chip system further includes a memory, which stores computer programs or computer instructions. [Brief explanation of the drawings]

[0096] [Figure 1] FIG. 1 is a schematic functional block diagram of an intelligent driving device according to an embodiment of the present application. [Figure 2] FIG. 2 is a schematic diagram of the sensing ranges of various sensors according to an embodiment of the present application. [Figure 3] FIG. 1 is a schematic diagram of the system architecture required to implement a motion trajectory planning method according to an embodiment of the present application. [Figure 4]FIG. 1 is a schematic diagram of the system architecture required to implement a motion trajectory planning method according to an embodiment of the present application. [Figure 5] 1 is a schematic flowchart of a motion trajectory planning method according to an embodiment of the present application; [Figure 6(a)] 1 is a schematic diagram of an application scenario of a motion trajectory planning method according to an embodiment of the present application; [Figure 6(b)] 1 is a schematic diagram of an application scenario of a motion trajectory planning method according to an embodiment of the present application; [Figure 6(c)] 1 is a schematic diagram of an application scenario of a motion trajectory planning method according to an embodiment of the present application; [Figure 7] 1 is a schematic diagram of a CIPV, according to an embodiment of the present application. [Figure 8] 1 is a schematic flowchart of a motion trajectory planning method according to an embodiment of the present application; [Figure 9] FIG. 2 is a schematic diagram of a sampling space according to an embodiment of the present application. [Figure 10] FIG. 1 is a schematic diagram of lateral path estimation according to an embodiment of the present application; [Figure 11] FIG. 2 is a schematic diagram of longitudinal trajectory estimation according to an embodiment of the present application; [Figure 12] 1 is a schematic diagram of a vehicle side according to an embodiment of the present application; [Figure 13] 1 is a schematic diagram of an application scenario of a game strategy according to an embodiment of the present application; [Figure 14(a)] 1 is a schematic flowchart of a game strategy stabilization process according to an embodiment of the present application. [Figure 14(b)] 1 is a schematic flowchart of a game strategy stabilization process according to an embodiment of the present application. [Figure 14(c)] 1 is a schematic flowchart of a game strategy stabilization process according to an embodiment of the present application. [Figure 14(d)] 1 is a schematic flowchart of a game strategy stabilization process according to an embodiment of the present application. [Figure 15] 2 is a schematic diagram of the movement trajectories of an ego-vehicle and a game object according to an embodiment of the present application; [Figure 16] FIG. 10 is a schematic diagram of an object's constraints yielding in creep advance, according to an embodiment of the present application; [Figure 17] FIG. 10 is a schematic diagram of a constraint for a path-stealing object in a creep advance, according to an embodiment of the present application; [Figure 18] 1 is a schematic flowchart of a motion trajectory planning method according to an embodiment of the present application; [Figure 19] 1 is a schematic block diagram of a motion trajectory planning device according to an embodiment of the present application; [Figure 20] 1 is a schematic block diagram of a motion trajectory planning device according to an embodiment of the present application; DETAILED DESCRIPTION OF THE INVENTION

[0097] The following describes the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. In the description in the embodiments of the present application, " / " means "or" unless otherwise specified. For example, A / B can represent A or B. In this specification, "and / or" only describes an association relationship for describing related objects and indicates that three relationships may exist. For example, A and / or B can represent the following three cases: a case where only A exists, a case where both A and B exist, and a case where only B exists.

[0098] In the embodiments of the present application, prefix terms such as "first" and "second" are used only to distinguish between different described objects and do not limit the position, order, priority, quantity, content, etc. of the described objects. In the embodiments of the present application, the use of prefix terms such as ordinal numbers to distinguish between described objects does not constitute a limitation on the described objects. For an explanation of the described objects, please refer to the contextual explanation in the claims or embodiments. The use of such prefix terms should not constitute unnecessary limitations. Also, in the description of the present embodiment, unless otherwise specified, "at least one" means one or more, and "multiple" means two or more. The character " / " typically indicates an "or" relationship between related objects. At least one of the following items (moieties) or similar expressions refers to any combination of these items, including any combination of a singular item (moiety) or multiple items (moieties). For example, at least one item (portion) of a, b, or c may refer to a, b, c, a and b, a and c, b and c, or a, b, and c, where a, b, and c may be singular or plural.

[0099] 1 is a schematic functional block diagram of an intelligent driving device 100 according to one embodiment of the present application. The intelligent driving device 100 may include a sensing system 120, a display device 130, and a computing platform 150. The sensing system 120 may include several sensors that sense information about the environment surrounding the intelligent driving device 100. For example, the sensing system 120 may include a positioning system. The positioning system may be a global positioning system (GPS), or may be one or more of a BeiDou system or another positioning system, an inertial measurement unit (IMU), a lidar, a millimeter-wave radar, an ultrasonic radar, or a camera device.

[0100] Some or all of the functions of the intelligent driving device 100 may be controlled by a computing platform 150. The computing platform 150 may include processors 151 to 15n (n is a positive integer). A processor is a circuit having signal processing capabilities. In one implementation, the processor may be a circuit having the ability to read and execute instructions, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which may be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor may implement a specific function by using logical relationships of hardware circuits. The logical relationships of the hardware circuits may be fixed or reconfigurable. For example, the processor may be a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field programmable gate array (FPGA). In a reconfigurable hardware circuit, the process of a processor loading a configuration document to implement the hardware circuit may be understood as the process of the processor loading instructions to implement some or all of the functions of the aforementioned units. In addition, the processor may alternatively be a hardware circuit designed for artificial intelligence and may be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), or a deep learning processing unit (DPU).Additionally, the computing platform 150 may further include a memory configured to store instructions, and some or all of the processors 151 to 15n may access and execute the instructions in the memory to implement corresponding functions.

[0101] The intelligent driving device 100 may include an advanced driving assistance system (ADAS). The ADAS uses multiple sensors in the sensing system 120 (including, but not limited to, lidar, millimeter-wave radar, camera devices, ultrasonic sensors, a global positioning system, and an inertial measurement unit) to acquire information about the surroundings of the intelligent driving device, and analyzes and processes the acquired information to implement functions such as obstacle detection, target recognition, positioning of the intelligent driving device, path planning, and driver monitoring / attention alerting. In this way, the driving safety, automation, and comfort of the intelligent driving device are improved.

[0102] FIG. 2 is a schematic diagram of the detection ranges of various sensors. The sensors may include, for example, the lidar, millimeter-wave radar, camera devices, and ultrasonic sensors of the detection system 120 shown in FIG. 1. Millimeter-wave radar may be classified as long-range radar and medium-range / short-range radar. Currently, the detection range of lidar is approximately 80 to 150 meters, the detection range of long-range millimeter-wave radar is approximately 1 to 250 meters, the detection range of medium-range / short-range millimeter-wave radar is approximately 30 to 120 meters, the detection range of cameras is approximately 50 to 200 meters, and the detection range of ultrasonic radar is approximately 0 to 5 meters.

[0103] At different levels of automation (L0 to L5), ADAS can implement different levels of autonomous driving assistance based on information obtained by using artificial intelligence algorithms and multiple sensors. The aforementioned levels of automation (L0 to L5) are based on the Society of Automotive Engineers (SAE) rating scale. L0 indicates no automation, L1 indicates driver assistance, L2 indicates partial automation, L3 indicates conditional automation, L4 indicates high automation, and L5 indicates full automation. At levels L1 to L3, the task of monitoring and responding to road conditions is performed by the driver and the system, and the driver must take over the dynamic driving task. At levels L4 and L5, it may be possible to completely transform the driver into a passenger. Currently, functions that can be implemented by ADAS mainly include, but are not limited to, adaptive cruise, automatic emergency braking, automatic parking, blind spot monitoring, forward intersection traffic warning / braking, rear intersection traffic warning / braking, forward vehicle collision warning, lane estimation warning, lane keeping assist, rear vehicle collision prevention warning, traffic sign recognition, traffic jam assist, highway assist, etc. It should be understood that the aforementioned functions may have specific modes at different autonomous driving levels (L0 to L5). A higher autonomous driving level indicates a more intelligent mode.

[0104] As described above, in the current technical background, methods for planning autonomous driving trajectories are typically based on FSM and game-based object decision-making and planning. Decision-making and planning are significantly affected by the accuracy of the game object's trajectory prediction. For example, when the game object is a pedestrian or non-vehicle, the direction of movement is unknown due to the large degrees of freedom of the target's movement, resulting in large fluctuations in trajectory prediction results. In this case, the game object's predicted motion trajectory often intrudes into the autonomous vehicle's driving path. Incorrect game object trajectory prediction may cause problems such as unexpected and frequent sudden braking, false stopping, and continuous yielding of the autonomous vehicle, or may cause the game object and the autonomous vehicle to stop and / or start simultaneously. A typical scenario is a road or intersection where both automobiles and non-automobiles are traveling without signs. This leads to low autonomous vehicle passage efficiency and a poor user experience. In consideration of this, embodiments of the present application provide a motion trajectory planning method and apparatus, as well as an intelligent driving device, that can perform vehicle trajectory planning based on semantic-level decision-making tags of game strategies and the estimated trajectory of the game object. The vehicle actively maintains low-speed creep during the autonomous driving process and closely monitors the behavior of game objects, while ensuring safety and complying with traffic laws. When the vehicle maintains low-speed creep, it is in a slow state and is less affected by the accuracy of game object trajectory prediction, which helps avoid problems such as frequent stalls, loose braking, sudden braking, and false stops. This helps improve the user's riding experience.

[0105] It should be noted that non-motor vehicles in this application are means of transport that are driven by human or animal power and run on roads, and means of transport that are driven by a power unit but are designed with a maximum speed, vehicle weight, and dimensions that meet relevant national standards, such as an electric wheelchair or electric bicycle for the disabled. A motor vehicle is a means of transport that is driven or towed by its power unit.

[0106] It should be understood that "creep" in the embodiments of the present application refers to a state in which the vehicle travels at a speed equal to or lower than a specific speed. For example, the "speed" may be 10 km / h, 5 km / h, or another value. It should be understood that when the host vehicle is in a creep state, the planned motion trajectory of the host vehicle is less affected by the trajectory prediction accuracy of the game object.

[0107] FIG. 3 is an architecture diagram of a trajectory planning system according to an embodiment of the present application. As shown in FIG. 3, the trajectory planning system includes a sensing module, a decision-making and planning module, a control module, a parameter identification module, and an execution unit. The sensing module may include one or more camera devices or one or more radar sensors in the sensing system 120 shown in FIG. 1 and is configured to collect ambient environment information of the intelligent driving device, real-time motion parameters of the intelligent driving device, etc. The sensing module may further process the collected ambient environment information and establish a world model including roads, obstacles, etc. for downstream modules (i.e., the decision-making and planning module and the control module). The decision-making and planning module and the control module may be one or more processors in the computing platform 150 shown in FIG. 1. Specifically, the decision-making and planning module is configured to determine a game strategy for the intelligent driving device based on the ambient environment information, generate an estimated trajectory of a game object, and determine a planned motion trajectory based on the game strategy and the estimated trajectory of the game object. The control module is configured to calculate a corresponding control amount based on the planned motion trajectory and output the control amount to the execution unit. When the executive unit executes control based on the control amount, the intelligent driving device is controlled to travel based on the planned motion trajectory. In some possible implementations, the executive unit can also include steering and braking control systems in the intelligent driving device 100.

[0108] As shown in FIG. 4, the decision-making and planning module may include a game object sorting module, an interactive game decision-making module, and a motion planning module. The game object sorting module is configured to perform game object sorting. The interactive game decision-making module is configured to estimate estimated trajectories of the game objects and an estimated trajectory of the ego-vehicle based on the sorted game objects, and generate a game strategy (also called a semantic-level decision tag) based on the estimated trajectories of the game objects and the estimated trajectory of the ego-vehicle. The motion planning module is configured to plan a motion trajectory of the ego-vehicle based on the game strategy and the estimated trajectories of the game objects to generate a planned motion trajectory.

[0109] Hereinafter, the detailed operation processes of the above three modules will be described with reference to FIGS.

[0110] FIG. 5 is a schematic flowchart of a motion trajectory planning method 500 according to an embodiment of the present application. The method 500 may be applied to the intelligent driving device shown in FIG. 1 or may be performed by the system shown in FIG. 3 or FIG. 4. For example, the method 500 may be performed by the game object sorting module of FIG. 4. In the following, the method 500 is described using an example in which the intelligent driving device is a vehicle. It should be understood that the steps or operations of the motion trajectory planning method shown in FIG. 5 are merely examples for explanation. In this embodiment of the present application, other operations or variations of the operations in FIG. 5 may also be performed. The method 500 includes the following steps:

[0111] S501: Obtain motion status information and road information of interaction objects whose distance to the own vehicle is less than or equal to a preset distance.

[0112] For example, an interaction object may include, but is not limited to, an intelligent driving device, a pedestrian, an electric vehicle, a bicycle, and another object.

[0113] For example, the preset distance may be 100 meters (m), or 200 m, or another distance.

[0114] For example, the motion status information of the interaction object may include, but is not limited to, a predicted motion trajectory and second motion parameters, such as position information, speed, and acceleration, of the interaction object. For example, the motion status information of the interaction object may be calculated by the ego-vehicle based on position information and / or speed information of the interaction object, the position information and / or speed information being measured using a radar sensor or the like. Alternatively, the motion status information of the interaction object may be received using vehicle-to-infrastructure (V2I) communication, or vehicle-to-everything (V2X) information exchange, or vehicle-to-vehicle (V2V) communication, or may be received in another manner.

[0115] For example, the host vehicle may directly receive the predicted motion trajectory of the interaction object using V2I, V2V, or V2X. As another example, the predicted motion trajectory of the interaction object may be calculated by the host vehicle based on the received position information, navigation angle information, etc. of the interaction object. The position information, navigation angle information, etc. may be included in basic vehicle safety message (BSM) information or other information.

[0116] It should be understood that the predicted motion trajectory of the interaction object may be understood as the predicted motion trajectory of the interaction object in a future time period, for example, 10 seconds or 20 seconds.

[0117] For example, the road information includes, but is not limited to, lane information of the current road, guidance rules for one or more lanes of the current road, etc. The road information may be received by the host vehicle by using V2I, V2V, or V2X, or may be obtained by the host vehicle by collecting and calculating using a radar sensor and / or a camera device.

[0118] S502: Interaction objects whose predicted motion trajectories partially overlap with the planned driving route of the host vehicle are determined as pre-selected game objects.

[0119] For example, the planned driving route may be obtained by using a planning and control module of the ego vehicle.

[0120] In some possible implementations, the motion status of the interaction object may be determined based on the predicted motion trajectory of the interaction object, and the pre-selected game object is determined with reference to the motion status of the interaction object. For example, when the interaction object moves along the predicted motion trajectory, the motion status of the interaction object is considered to be definite. In this case, when the predicted motion trajectory of the interaction object overlaps partially with the planned driving path of the host vehicle, the interaction object is considered to be a pre-selected game object.

[0121] For example, as shown in FIG. 6(a), the host vehicle travels straight, and the interaction object is blocked by an obstacle and needs to occupy the host vehicle's driving lane, or the interaction object enters from the right side of the host vehicle. In this case, if it is determined that the predicted motion trajectory of the interaction object partially overlaps with the host vehicle's planned driving path, the interaction object is determined to be a pre-screened game object. Alternatively, as shown in FIG. 6(b), the host vehicle travels straight through an unmarked intersection, and the interaction object turns left into the opposite lane of the intersection, or the host vehicle turns left through an unmarked intersection, and the interaction object travels straight into the opposite lane of the intersection. In this case, if it is determined that the predicted motion trajectory of the interaction object partially overlaps with the host vehicle's planned driving path, the interaction object can be determined to be a pre-screened game object.

[0122] In another example, the actual motion trajectory of the interaction object is different from the predicted motion trajectory. In this case, the motion status of the interaction object is considered to be uncertain. Furthermore, a new predicted motion trajectory of the interaction object may be determined based on the driving intention of the interaction object to determine whether the new predicted motion trajectory overlaps with the planned driving path of the ego-vehicle.

[0123] For example, the driving intention of the interaction object may be determined based on a semantic intention-based behavior prediction method, and when it is determined that the driving intention of the interaction object overlaps with the movement trajectory of the ego-vehicle, the interaction object is determined to be a pre-screened game object.

[0124] For example, as shown in FIG. 6(c), when the host vehicle goes straight through an unmarked intersection, the interaction object may go straight or may turn left or right on the left side of the host vehicle. In this case, the driving intention of the interaction object may be determined based on the state of the turn light of the interaction object. Furthermore, when the interaction object goes straight or turns left, the driving intention of the interaction object partially overlaps with the planned driving path of the host vehicle. In this case, the interaction object may be determined to be a pre-screened game object.

[0125] S503: Determine whether the prescreened game object is a dangerous object.

[0126] Specifically, if the pre-selected game object is not a dangerous object, S504 is executed to determine a game strategy of the ego-vehicle based on the pre-selected game object, that is, the autonomous driving game decision-making and trajectory planning are executed for the pre-selected game object. If the pre-selected game object is a dangerous object, S505 is executed to terminate the autonomous driving decision-making and trajectory planning process.

[0127] It should be noted that the above phrase "terminate the autonomous driving decision-making and trajectory planning process" means that the trajectory planning process provided in this embodiment of the present application is not executed. It should be understood that in a specific implementation process, the ego-vehicle may execute other driving decision-making and trajectory planning.

[0128] It should be further noted that a "dangerous object" in the present embodiment is an interaction object that is too close to the ego-vehicle in space and / or time, and for which trajectory planning including a creep strategy in the present embodiment is not suitable. It should be understood that other autonomous driving decision-making and / or trajectory planning may be performed for the dangerous object, for example, automatic emergency braking.

[0129] For example, CIPV screening can be performed on pre-screened game objects to determine whether the pre-screened game objects are dangerous objects. A schematic diagram of CIPV screening is shown in Figure 7. For safety considerations, a region (e.g., an equilateral trapezoidal region or a vase-shaped region) that changes with speed and is symmetrical with respect to the longitudinal symmetry plane of the ego-vehicle is provided ahead of the ego-vehicle in its traveling direction to screen out dangerous objects. As shown in Figure 7, the longitudinal length of the CIPV screening area, i.e., the length in the direction parallel to the direction of travel of the host vehicle (direction S in Figure 7), includes three parts: ef, fg, and gd. ef is a constant threshold, indicating that a certain longitudinal range from the front of the host vehicle to the rear of the host vehicle is also a dangerous object screening area. fg is the host vehicle's constant speed threshold, representing the distance the host vehicle travels at its current vehicle speed within the reaction time from when the driver receives an emergency stop signal to when the driver causes the intelligent driving device to brake. gd is the host vehicle's braking distance threshold, representing the distance the host vehicle needs to brake at the maximum deceleration in its current operating state. The formula for the longitudinal length of the CIPV screening area is expressed as follows:

number

[0130] where L ef L represents the length of the ef segment, and longitude_const_thresh represents the longitude constant threshold. fg represents the length of the fg segment,

number

[0131] The lateral extent of the CIPV screening region, i.e., the direction perpendicular to the longitudinal symmetry plane of the host vehicle (direction L in FIG. 7), is determined by the lengths of ab and dc. Both ab and dc are lateral constant thresholds, and the length of ab may be longer than the length of dc. The lateral extent of the CIPV screening region is from ab to dc in the longitudinal direction, and the lateral extent may decrease linearly or nonlinearly in the longitudinal direction. FIG. 7 shows a schematic diagram of the CIPV screening region, in which the lateral extent decreases linearly.

[0132] In some possible implementations, the shape of the CIPV screening region may be dynamically changed to fit the vehicle model and aggression tendency of the pre-screened game object by adjusting the longitudinal constant threshold (e.g., ef), the lateral constant threshold (e.g., ab and dc), the lateral length contraction change rate, the ego vehicle speed, the ego vehicle acceleration, the driver's reaction time, etc. For example, a larger vehicle model of the pre-screened game object may indicate a longer e and / or longer ab and / or cd, or a higher aggression of the ego vehicle may indicate a shorter length of e and / or shorter lengths of ab and / or cd.

[0133] Furthermore, the duration ttl of the trajectory conflict or intention conflict between the pre-selected game object and the ego-vehicle in the horizontal direction, i.e., the direction perpendicular to the vertical symmetry plane of the intelligent driving device, is calculated based on the CIPV selection area. The calculation formula is as follows:

number

[0134] where L obj_l represents the distance between the pre-selected game object and the ego-vehicle in the lateral direction, and V obj_l represents the lateral velocity of the pre-selected game object.

[0135] In addition, the speed difference ΔV between the pre-selected game object and the ego-vehicle in the longitudinal direction, i.e., the direction parallel to the driving direction of the intelligent driving device, is calculated. The calculation formula is as follows: ΔV=V obj_s -V ego_s

[0136] where V obj_s represents the longitudinal velocity of the pre-selected game object, and V ego_s represents the longitudinal velocity of the ego-vehicle. For a pre-screened game object to be determined as a dangerous object, the following conditions must be met: (a) the pre-screened game object is within the CIPV screening area; (b) the ttl of the pre-screened game object is less than or equal to a first preset threshold ttl_thresh; and (c) the ΔV of the game object is less than or equal to a second preset threshold ΔV_thresh. The first preset threshold ttl_thresh is determined based on the longitudinal position and vehicle model of the pre-screened game object and the aggression of the ego-vehicle, and may be dynamically adjusted based on one or more of the aforementioned information. The second preset threshold ΔV_threshold is determined based on the vehicle model of the pre-screened game object and the aggression of the ego-vehicle, and may be dynamically adjusted based on the vehicle model of the pre-screened game object and / or the aggression of the ego-vehicle.

[0137] It should be understood that if a pre-screened game object is determined to be a "hazardous object," then the creep strategy-based trajectory planning in the present application is not performed on the "hazardous object," and an action such as autonomous emergency braking (AEB) is performed. If a pre-screened game object is determined not to be a "hazardous object," then the creep strategy-based trajectory planning in the present application continues on the pre-screened game object.

[0138] S504: Determine a game strategy for the host vehicle based on the pre-selected game objects.

[0139] Note that the pre-selected game objects in this step are the "game objects" that need to be taken into account when trajectory planning is performed for the ego-vehicle based on a creep strategy in subsequent embodiments (e.g., method 800).

[0140] S505: End the autonomous driving decision-making and trajectory planning process.

[0141] According to the motion trajectory planning method provided in this embodiment of the present application, game objects that need to be considered when trajectory planning is performed for the ego-vehicle based on the creep strategy can be pre-selected based on trajectory conflict, intention conflict, and CIPV methods, so that the game strategy determination and trajectory planning can be performed in a relatively safe environment, thereby improving driving safety.

[0142] FIG. 8 is a schematic flowchart of a motion trajectory planning method 800 according to an embodiment of the present application. The method 800 may be applied to the intelligent driving device shown in FIG. 1 or may be performed by the system shown in FIG. 3 or FIG. 4. For example, the method 800 may be performed by the interactive game decision-making module of FIG. 4. In some possible implementations, the method 800 may be performed after the method 500. For example, the method 800 may be considered as an extension of S504. It should be understood that the steps or operations of the motion trajectory planning method shown in FIG. 8 are merely examples for explanation. In this embodiment of the present application, other operations or variations of the operations in FIG. 8 may also be performed. The method 800 includes the following steps:

[0143] S801: Generate a sampling space.

[0144] In this embodiment of the present application, the sampling space is a space used to describe the possible status of the ego-vehicle and / or game object. The possible status includes, but is not limited to, kinematic status such as speed, acceleration, or jerk. The possible status may also include another kinematic status of the ego-vehicle and / or game object. It should be understood that the possible status space has an upper limit of the status value and a lower limit of the status value. The upper limit of the status value is the maximum value of the status that can be reached by the vehicle, for example, the maximum acceleration, maximum speed, and maximum jerk that can be reached by the ego-vehicle and / or game object. The lower limit of the status value is the minimum value of the status that can be reached by the ego-vehicle and / or game object, for example, the minimum acceleration, minimum speed, and minimum jerk that can be reached by the vehicle. When trajectory estimation is performed for the ego-vehicle and game object, the trajectories of the ego-vehicle and game object are estimated based on the possible status of the ego-vehicle and game object collected in the sampling space. In this application, an example in which the possible status in the sampling space is acceleration is used for explanation.

[0145] For example, the longitudinal acceleration sampling space is generated based on the motion status information of the ego-vehicle and the game object by considering longitudinal feature information such as road speed limit, acceleration jerk value, and type of game object, etc. The lateral offset sampling space is generated based on feature information such as road boundary, static obstacles, and the kinematics of the intelligent driving device.

[0146] It should be noted that in the embodiments of the present application, the "longitudinal direction" can be understood as a direction parallel to the longitudinal symmetry plane of the intelligent driving device in a plane parallel to the ground, i.e., the driving direction of the intelligent driving device. In the embodiments of the present application, the "lateral direction" can be understood as a direction perpendicular to the longitudinal symmetry plane of the intelligent driving device, i.e., the direction perpendicular to the driving direction of the intelligent driving device in a plane parallel to the ground.

[0147] For example, the game objects may be understood as pre-screened game objects that are not dangerous objects in the above embodiments, or may be game objects that are screened in another way.

[0148] In some possible implementations, a minimum lateral offset, a current lateral offset, and a maximum lateral offset are selected for the game object and the ego-vehicle, respectively, to obtain 3 × 3 = 9 lateral offset sampling spaces. Sampling in the lateral offset sampling space indicates the offset of the trajectory of the ego-vehicle or game object in a direction perpendicular to the longitudinal symmetry plane of the intelligent driving device. Sampling in multiple longitudinal sampling spaces may be performed for each lateral offset sampling space. For example, the longitudinal sampling space of the ego-vehicle may be divided into a longitudinal creep acceleration sampling space and a longitudinal non-creep acceleration sampling space of the ego-vehicle. The two sampling regions and sampling intervals may be the same. The difference is that during trajectory estimation, the ego-vehicle's longitudinal non-creep acceleration and the longitudinal creep acceleration-based trajectory estimation have different upper and lower limit speeds. In a specific implementation process, sampling in the longitudinal creep acceleration sampling space and sampling in the longitudinal non-creep acceleration sampling space may be distinguished using a "tag" or the like. The longitudinal acceleration sampling space of the game object includes the longitudinal non-creep acceleration sampling space. The ego-vehicle's lateral and longitudinal sampling spaces and the game object's lateral and longitudinal sampling spaces are cross-connected to form the final sampling space, as shown in Figure 9. Specifically, the lateral offset sampling regions of the ego-vehicle and game object shown in Figure 9 are [minEgoLateraloffset, maxEgoLateraloffset] and [minObjLateraloffset, maxObjLateraloffset], respectively. In Figure 9, the ego-vehicle's longitudinal non-creep acceleration sampling space and longitudinal creep acceleration sampling space both have regions of [-4, 3] m / s 2 and the region of the game object's vertical acceleration sampling space is [-4, 3] m / s 2 and the sampling interval in the vertical acceleration sampling space is 1 m / s 2, resulting in 16×8=128 vertical sampling spaces. The sampling space formed by the ego-vehicle and game objects may include 9×128=1152 sampling spaces. It should be understood that the specific sampling intervals of the horizontal and vertical sampling spaces may be other intervals and may be determined based on hardware computation performance and accuracy requirements. For example, the vertical sampling interval may be set to 2 m / s 2 or 0.5m / s 2 As another example, the horizontal sampling interval may be further divided into 5×5=25 horizontal offset sampling spaces.

[0149] S802: Based on sampling in the sampling space, perform a lateral path estimation of the host vehicle based on the current position of the host vehicle, and perform a longitudinal trajectory estimation of the host vehicle based on the current acceleration of the host vehicle.

[0150] In some possible implementations, the lateral path and longitudinal trajectory of the ego-vehicle are estimated separately based on sampling in the sampling space. The lateral path includes an offset path curve shape, as shown in Figure 10. The longitudinal trajectory includes a relationship between longitudinal distances (s) at corresponding time points (t). Finally, multiple groups of estimated trajectories with time information are generated based on the lateral path and longitudinal trajectory.

[0151] For example, based on the SL coordinates shown in FIG. 7, the lateral path of the ego-vehicle is estimated by using the following equation:

number

[0152] where s e is the longitudinal position of the vehicle (unit: m) at the time when the lateral path of the vehicle is estimated, and the position changes with the estimation time. e ) is the longitudinal position s of the vehicle e is the horizontal offset (unit: m) corresponding to se StartThresh is the longitudinal starting position of the ego vehicle (unit: m), which can be understood as the position of the ego vehicle in the direction parallel to the longitudinal symmetry plane of the intelligent driving device when trajectory estimation starts; curEgoLateralOffset is the offset (unit: m) corresponding to the current direction of the ego vehicle; s e CubicCurveThresh is the longitudinal position (unit: m) at which the cubic curve connection ends, egolateralOffset is the lateral offset (unit: m) at which the cubic curve connection of the ego vehicle ends, and corresponds to minEgoLateralOffset or maxEgoLateralOffset of the ego vehicle, and s e StartThresh and s e CubicCurveThresh can be dynamically adjusted based on the vehicle model and the steepness of the ego vehicle. For example, if the vehicle model of the ego vehicle is a large vehicle, s e StartThresh and / or s e When the value of CubicCurveThresh is large and / or the steepness of the ego-vehicle is high, s e StartThresh and / or s e The value of CubicCurveThresh is small. The path is smoothed by using a cubic curve (s e StartThresh, curEgoLateralOffset) to (s e CubicCurveThresh, egolateralOffset) and (s e StartThresh, curEgoLateralOffset) and (s e The tangent direction of the cubic curve in CubicCurveThresh, egolateralOffset) is parallel to the driving direction of the intelligent driving device, and a, b, c, and d are coefficients of a cubic polynomial, and the specific values of a, b, c, and d can be determined based on the vehicle model and the steepness of the egocentric vehicle. The specific values of a, b, c, and d are not limited in this application.

[0153] In the process of estimating the longitudinal trajectory of the host vehicle, the longitudinal acceleration of the host vehicle changes with estimation time, as shown in Figure 11, where the horizontal axis represents the estimation time point t and the vertical axis represents the acceleration of the host vehicle. For example, the longitudinal position of the host vehicle at a certain time point in the trajectory estimation process may be determined based on the estimated longitudinal acceleration of the host vehicle and the speed of the host vehicle, and the longitudinal positions of the host vehicle at multiple time points in the trajectory estimation process form the longitudinal trajectory of the host vehicle. As shown in Figure 11, the longitudinal acceleration estimation of the host vehicle can include the following four phases: (1) delay phase (t ∈ [0, delayTime)): longitudinal trajectory estimation is performed based on the host vehicle's current acceleration (currentAcc); (2) constant jerk phase (t ∈ [delayTime, jerkChangeTime) (hereinafter referred to as the constant jerk phase): the jerk is determined based on the acceleration at which the constant jerk phase starts and the longitudinal sampling acceleration (targetAcc), and longitudinal trajectory estimation is performed based on the constant jerk; (3) constant acceleration phase (t ∈ [jerkChangeTime, speedLimitTime)): the longitudinal sampling acceleration (targetAcc) is maintained for trajectory estimation; and (4) constant velocity phase (t ≥ speedLimitTime): when the estimated velocity reaches an upper or lower bound speed, the upper or lower bound speed is maintained for trajectory estimation. Note that the constant jerk phase may be a process of linearly increasing or decreasing acceleration. It is further noted that when the longitudinal sampling acceleration is the longitudinal non-creep acceleration, the upper limit speed for longitudinal trajectory estimation may be the upper limit speed set by the host vehicle or the maximum speed limit of the road section on which the host vehicle is traveling, and the lower limit speed for longitudinal trajectory estimation may be 0.If the longitudinal sampling acceleration is the longitudinal creep acceleration and the current speed of the host vehicle is lower than the creep speed, the upper bound speed for longitudinal trajectory estimation may be the creep speed, and the lower bound speed for longitudinal trajectory estimation may be 0; or if the current speed of the host vehicle is equal to or greater than the creep speed, the upper bound speed for longitudinal trajectory estimation may be the upper bound speed set by the host vehicle or the maximum speed limit of the road, and the lower bound speed for longitudinal trajectory estimation may be the creep speed. For example, the creep speed may be preset by the system or set by the user, and may be, for example, 5 km / h or 10 km / h, or may be another value. This is not specifically limited in the embodiments of the present application.

[0154] It should be understood that the above-mentioned four phases of the longitudinal trajectory estimation of the ego-vehicle are merely illustrative examples. In a specific implementation process, the longitudinal trajectory estimation of the ego-vehicle may include only one, two, or three of the above-mentioned phases. In one example, when the current acceleration currentAcc of the ego-vehicle is equal to the longitudinal sampling acceleration targetAcc, the longitudinal trajectory estimation may be performed starting from the constant acceleration phase (3). In another example, when the current acceleration currentAcc of the ego-vehicle is equal to or less than the longitudinal sampling acceleration targetAcc and the current speed of the ego-vehicle reaches an upper bound speed or a lower bound speed, the trajectory estimation may be performed from the constant speed phase (4).

[0155] S803: Based on sampling in the sampling space, perform lateral path estimation for the game object based on the current position of the game object, and perform longitudinal trajectory estimation for the game object based on the current acceleration of the game object.

[0156] In some possible implementations, the game object trajectory estimation method may be the same as the ego-vehicle trajectory estimation method. For example, based on the SL coordinates shown in Figure 7, the lateral path of the game object is estimated using the following formula:

number

[0157] where s o is the vertical position of the game object (unit: m), and its position changes depending on the estimation time, and l(s o ) is the horizontal offset (in meters) corresponding to the vertical position of the game object, and s o StartThresh is the starting vertical position of the game object, curObjLateralOffset is the offset (in meters) corresponding to the current orientation of the game object, and s o CubicCurveThresh is the vertical position (in meters) where the cubic curve connection ends, objlateralOffset is the horizontal offset (in meters) where the cubic curve connection ends for the game object, corresponding to the game object's minObjLateralOffset or maxObjLateralOffset, and s o StartThresh and s o CubicCurveThresh can be dynamically adjusted based on the vehicle model and the abruptness of the game object. For example, if the vehicle model of the game object is a large vehicle, then s o StartThresh and / or s o If the CubicCurveThresh value is large and / or the game object has high abruptness, o StartThresh and / or s o The value of CubicCurveThresh is small. The path is constructed using a cubic curve (s o StartThresh, curObjLateralOffset) to (s o CubicCurveThresh, objlateralOffset) and (s o StartThresh, objcurLateralOffset) and (s oThe tangent direction of the cubic curve in CubicCurveThresh, objlateralOffset) is parallel to the direction of the intelligent driving device, and a, b, c, and d are coefficients of a cubic polynomial, and the values of the coefficients may be the same as or different from the values of a, b, c, and d in the equation for lateral path estimation of the host vehicle.

[0158] In some possible implementations, for a method of estimating the longitudinal trajectory of a game object, please refer to the description of the longitudinal trajectory estimation of the ego-vehicle. For example, as shown in Fig. 11, the longitudinal acceleration estimation of a game object can include the following four phases: (1) Delay Phase (t ∈ [0, delayTime): The longitudinal trajectory estimation is performed based on the current acceleration (currentAcc) of the game object; (2) Constant Jerk Phase (t ∈ [delayTime, jerkChangeTime): The acceleration change rate is determined based on the acceleration at which the Constant Jerk phase begins and the longitudinal sampling acceleration (targetAcc), and the longitudinal trajectory estimation is performed based on the Constant Jerk; (3) Constant Acceleration Phase (t ∈ [jerkChangeTime, speedLimitTime)): The longitudinal sampling acceleration (targetAcc) is maintained for trajectory estimation; and (4) Constant Velocity Phase (t ≥ speedLimitTime): When the estimated velocity reaches an upper or lower bound velocity, the upper or lower bound velocity is maintained for trajectory estimation. For example, the upward velocity for estimating the longitudinal trajectory of the game object may be the maximum speed limit of the road section on which the game object is traveling, and the downward velocity for estimating the longitudinal trajectory may be 0. Note that the constant jerk phase may be a process of linearly increasing acceleration or a process of linearly decreasing acceleration.

[0159] It should be understood that the above-mentioned four phases of game object longitudinal trajectory estimation are merely illustrative examples, and in a particular implementation, game object longitudinal trajectory estimation may include only one, two, or three of the above-mentioned phases.

[0160] It should be understood that the estimated trajectory of the ego-vehicle (or game object) can be determined based on the estimated lateral path and the estimated longitudinal trajectory of the ego-vehicle (or game object). The estimated trajectory is the result of combining a set of points whose coordinates of the ego-vehicle (or game object) change over time, i.e., the longitudinal trajectory and the lateral offset of the ego-vehicle (or game object).

[0161] S804: A strategy cost evaluation is performed on the estimated trajectory pair of the ego-vehicle and the game object.

[0162] It should be understood that, based on the sampling space shown in Figure 9, a longitudinal sampled acceleration and a lateral offset of the ego-vehicle, and a longitudinal sampled acceleration and a lateral offset of the game object may be determined each time sampling is performed in the sampling space. It should be understood that an estimated trajectory determined based on the estimated trajectory of the ego-vehicle and the aforementioned sampling, and an estimated trajectory determined based on the estimated trajectory of the game object and the aforementioned sampling form an estimated trajectory pair.

[0163] For example, a strategy cost (hereinafter referred to as cost) evaluation is performed for all estimated trajectory pairs of the ego-vehicle and the game object. A lower strategy cost indicates a higher strategic benefit. In this case, the strategy is most likely to be used as the optimal strategy. In some possible implementations, the strategy benefit evaluation may be performed from one or more of five dimensions: security, comfort, traversability, right-of-way, and offset.

[0164] In some possible implementations, the orientation and velocity of the front of the ego-vehicle and the game object are considered to determine the security cost based on the minimum distance between the estimated trajectory of the ego-vehicle and the estimated trajectory of the game object in the estimated trajectory pair. A smaller minimum distance based on velocity and orientation indicates a higher security cost. When the minimum distance based on velocity and orientation is smaller than a certain threshold, it is determined that the ego-vehicle will collide with the game object at the minimum distance between the estimated trajectories. The collision is classified as a first type collision or a second type collision based on the motion status and position and attitude of the ego-vehicle and the game object during the collision. For ease of explanation, in this embodiment of the present application, the first type collision is simply referred to as "E2O" and the second type collision is simply referred to as "O2E."

[0165] For example, when both the host vehicle and the game object are moving, if the host vehicle collides with the side housing or rear of the game object in the direction of travel of the host vehicle, the collision is considered to be a first type of collision. Alternatively, if the game object collides with the side housing or rear of the host vehicle in the direction of travel of the game object, the collision is considered to be a second type of collision. Alternatively, if the game object is stationary, the host vehicle collides with the game object, and the collision is considered to be a first type of collision regardless of the collision position of the game object. Alternatively, if the host vehicle is stationary, the game object collides with the host vehicle, and the collision is considered to be a second type of collision regardless of the collision position of the host vehicle.

[0166] It should be understood that the side housing of a vehicle includes the left body side housing and the right body side housing. For example, the left and right sides including the left and right body sides (pillars A, B, and C) and exterior covers are referred to as the left and right body side housings. For example, the area indicated by the dashed line in FIG. 12 is the left body side housing of the vehicle. Pillar A is located at the front of the side housing and is connected to the front housing plate for mounting the front door hinges and windshield, and is a pillar for rotating the front side door switch. Pillar B is located at the center of the side housing and is a pillar for mounting the front safety belt, front door lock, and rear door hinge, and is a pillar for rotating the rear door switch (in some light commercial vehicles, only the left and right front doors are available, and pillar B is located at the rear of the side housing). Pillar C is located at the rear of the side housing and is a pillar for mounting the rear seat belt and rear side door lock, and is a pillar for mounting the rear windshield and rear door. The support pillar D is a support pillar that constitutes the rear door frame together with the rear beam of the upper cover, etc., to support the rear triangular window and the rear door frame. In some possible implementations, the body side housing is included in a side housing assembly, and the side housing assembly may further include an inner plate and a reinforcing part.

[0167] In some possible implementations, the vehicle side housing further includes left and right body side housings and wheels. For example, the left vehicle housing includes the left vehicle body side housing and left wheels (e.g., including the left front wheel and the left rear wheel). The right vehicle housing includes the right vehicle body side housing and right wheels (e.g., including the right front wheel and the right rear wheel).

[0168] It will be appreciated that the rear of the vehicle may also be the side of the vehicle on which the rear bumper and rear license plate are located.

[0169] Note that when it is determined that no collision will occur based on the estimated trajectory of the ego-vehicle and the estimated trajectory of the game object, the security cost is 0. If the collision is a first type collision, the security cost is approximately infinite. If the collision is a second type collision, the security cost may be determined based on the velocity of the game object at the collision location.

[0170] For example, the formula for calculating the security cost can be shown as follows:

number

[0171] Here, Cost safety represents a security cost, v represents the velocity of the game object at the collision location when a collision is determined to have occurred based on the estimated trajectory of the ego-vehicle and the estimated trajectory of the game object, vThresMin represents a lower speed threshold for executing a security cost penalty on the velocity of the game object when the estimated trajectory of the ego-vehicle collides with the estimated trajectory of the game object, vThresMax represents an upper speed threshold for executing a security cost penalty on the velocity of the game object when the estimated trajectory of the ego-vehicle collides with the estimated trajectory of the game object, and m is a weight value. In some possible implementations, the weight value is associated with the type of game object.

[0172] In another example, the comfort cost of an estimated trajectory pair of the ego-vehicle and the game object may be determined based on the jerk value of the ego-vehicle (or game object) in the estimated trajectory of the ego-vehicle (or game object). The formula for calculating the comfort cost of the ego-vehicle (or game object) may be as follows:

number

[0173] Here, Cost comfortable represents the comfort cost, jerk represents the jerk of the ego vehicle (or game object), jerkThresMin represents the lower jerk threshold of the ego vehicle (or game object), and jerkThresMax represents the upper jerk threshold of the ego vehicle (or game object). In some possible implementations, if jerk is less than jerkThresMin, then Cost comfortable is 0. Or, if jerk is greater than jerkThresMax, Cost comfortable is 1. It should be understood that better comfort means a smaller comfort cost. The comfort cost includes the ego vehicle comfort cost and the game object comfort cost, and the weights of the game object comfort cost in the ego vehicle comfort cost and the comfort cost may be different.

[0174] In yet another example, a method for calculating the passability cost of an estimated trajectory pair of an ego-vehicle and a game object may be shown as follows, i.e., the formula for calculating the passability cost of the ego-vehicle (or game object) may be as follows:

number

[0175] Here, Cost passability represents the traversability cost, deltaT represents the difference between the time when the current estimated trajectory of the ego-vehicle (or game object) passes through the conflict point and the time when the estimated trajectory of the ego-vehicle (or game object) passes through the conflict point, where in the estimated trajectory, the lateral sampling offset is the offset corresponding to the current direction and the longitudinal sampling acceleration is 0, tThresMin represents the lower threshold of the time difference, and tThresMax represents the upper threshold of the time difference. In some possible implementations, if deltaT is less than tThresMin, then Cost passabilityis 0 or if deltaT exceeds tThresMax, Cost passability is 1. It should be understood that better traversability indicates a smaller traversability cost. The traversability cost includes the traversability cost of the ego-vehicle and the traversability cost of the game object. The traversability cost of the ego-vehicle and the traversability cost of the game object may have different weights in the traversability cost.

[0176] In yet another example, the right-of-way relationship between the ego-vehicle and the game object is determined based on the estimated trajectory pair of the ego-vehicle and the game object. If the interactive game allows an intelligent driving device with a strong right-of-way to change its motion status, a strong right-of-way cost penalty should be imposed on the change of the motion status, that is, the intelligent driving device with a strong right-of-way tends not to change its current motion status. The right-of-way cost of the estimated trajectory pair of the ego-vehicle and the game object may be expressed as follows: The formula for calculating the right-of-way cost of the ego-vehicle (or game object) may be as follows:

number

[0177] Here, Cost roadRight represents the right-of-way cost, acc represents the current longitudinal sampled acceleration of the intelligent driving device with a strong right-of-way, accThresMin represents the lower longitudinal acceleration threshold, and accThresMax represents the upper longitudinal acceleration threshold. In some possible implementations, if acc is greater than accThresMax, then Cost roadRight is 0. Or if acc is greater than accThresMin, Cost roadRightis 1. The right of way cost includes the right of way cost of the own vehicle and the right of way cost of the game object, and the right of way cost of the own vehicle and the right of way cost of the game object may have different weights in the right of way cost.

[0178] It should be noted that when the strategy cost evaluation is performed based on the estimated trajectory pair of the ego-vehicle and the game object, the aforementioned costs may be weighted and summed to obtain the current final cost of the estimated trajectory pair of the ego-vehicle and the game object. The cost weight distribution may be security weight > road weight = traversability weight > comfort weight, or may be another distribution scheme. This is not specifically limited in this application.

[0179] It is further noted that when strategy cost evaluation is performed based on an estimated trajectory pair of the ego-vehicle and the game object, one or more of the aforementioned costs may be used, or modifications and / or extensions may be performed based on the aforementioned costs.

[0180] S805: Determine an initial game strategy based on the estimated trajectory pair with the smallest strategy cost.

[0181] In some possible implementations, the initial game strategy is determined based on the estimated trajectory pair with the smallest strategy cost among all estimated trajectory pairs of the ego-vehicle and the game object. In the case of a longitudinal game strategy in the initial game strategy, if the ego-vehicle passes through the conflict area faster than the game object based on the trajectory estimation, the longitudinal game strategy of the initial game strategy is to intercept the path of the game object. If the ego-vehicle passes through the conflict area slower than the game object, the longitudinal game strategy is to yield to the game object. In some possible implementations, whether the longitudinal game strategy is a creep strategy or a non-creep strategy is determined based on the longitudinal sampled acceleration. For example, if the longitudinal sampled acceleration of the ego-vehicle belongs to the creep acceleration sampling space of the ego-vehicle, the longitudinal game strategy is a creep strategy, or if the longitudinal sampled acceleration of the ego-vehicle belongs to the non-creep acceleration sampling space of the ego-vehicle, the longitudinal game strategy is a non-creep strategy. For the lateral game strategy in the initial game strategy, if the ego vehicle's lateral sampling offset is not the offset corresponding to the current direction (curEgoLateralOffset), the optimal lateral game strategy is to avoid the game object. If the ego vehicle's lateral sampling offset is the offset corresponding to the current direction (curEgoLateralOffset), the game object is ignored. For the non-creep strategy in the longitudinal game strategy, the decision tag of the steal game object is GRABWAY (abbreviated as GW), and the decision tag of the yield game object is YIELD (abbreviated as YD). For the creep strategy, if the ego vehicle passes through the conflict region faster than the game object based on the trajectory estimation, the game object is the steal game object by creeping forward, and if the ego vehicle passes through the conflict region slower than the game object, the game object is the yield game object by creeping forward.The decision tag of a creep forward grab game object is CREEP-FORWARD-GRABWAY (abbreviated as CFG), and the decision tag of a creep forward yield game object is CREEP-FORWARD-YIELD (abbreviated as CFY). For sideways game strategies, the decision tag of an avoidance game object is BYPASS (abbreviated as BP), and the decision tag of an ignore game object is IGNORE (abbreviated as IG). For example, as shown in Figure 13(a), the initial game strategy is the avoidance and grab strategy BP-GW, and as shown in Figure 13(b), the initial game strategy is the ignore and creep forward yield strategy IG-CFY.

[0182] It should be further noted that the difference between the creep strategy and the non-creep strategy is that when the motion planning module executes a trajectory plan for intercepting a path based on the creep strategy, the ego-vehicle passes through the conflict area at as fast a creeping speed as possible, and when the motion planning module executes a trajectory plan for yielding a path based on the creep strategy, the ego-vehicle travels at as fast a creeping speed as possible during the period in which the game object passes through the conflict area. That is, it can be understood that by using the creep strategy, the motion planning module is instructed to plan the ego-vehicle's trajectory within the conflict area or the ego-vehicle's trajectory during the period in which the game object passes through the conflict area based on the creeping trajectory. However, when the motion planning module executes a trajectory plan for intercepting or yielding a path based on the non-creep strategy, there is no reference value for the running speed of the ego-vehicle when passing through the conflict area or the running speed of the ego-vehicle when the game object passes through the conflict area. The ego-vehicle can intercept the path of the game object at a very high speed or can stop to yield to the game object.

[0183] S806: Perform a stabilization process on the initial game strategy to generate a final game strategy.

[0184] In some possible implementations, timers with different thresholds are set based on a hierarchical state machine, making it more difficult to change a non-creeping tag to a creeping tag (YD / GW → CFY / CFG), to change between a creeping advance stealing tag and a creeping advance yielding tag (CFY←→CFG), and to change a creeping tag to a non-creeping tag (CFY / CFG → YD / GW). 14(a), 14(b), 14(c), and 14(d) are schematic diagrams of the stabilization process of the game strategy when the time interval between the previous frame and the current frame is intervalTime, where minTimerThres, midTimerThres, and maxTimerThres are timer time thresholds that increase sequentially, ydToCfyTimer is a timer that indicates that the decision tag has changed from YD to CFY, ydToCfgTimer is a timer that indicates that the decision tag has changed from YD to CFG, cfyToYdTimer is a timer that indicates that the decision tag has changed from CFY to YD, and cfyToGwTimer is a timer that indicates that the decision tag has changed from YD to CFG. is a timer indicating that the decision tag has changed from CFY to GW, cfyToCfgTimer is a timer indicating that the decision tag has changed from CFY to CFG, cfgToYdTimer is a timer indicating that the decision tag has changed from CFG to YD, cfgToGwTimer is a timer indicating that the decision tag has changed from CFG to GW, cfgToCfyTimer is a timer indicating that the decision tag has changed from CFG to CFY, gwToCfyTimer is a timer indicating that the decision tag has changed from GW to CFY, and gwToCfgTimer is a timer indicating that the decision tag has changed from GW to CFG.

[0185] For example, minTimerThres, midTimerThres, and maxTimerThres may be 0.1 seconds, 0.3 seconds, and 0.5 seconds, respectively, or minTimerThres, midTimerThres, and maxTimerThres may be other values.

[0186] As shown in Figures 14(a) and 14(b), if the vertical decision tag of the previous frame is YD or GW and the vertical decision tag of the current frame is CFY or CFG, intervalTime is added to the duration currently recorded by the corresponding timer. The vertical decision tag of the current frame is changed to CFY or CFG only if the duration recorded by the corresponding timer is greater than the timer time threshold minTimerThres. When the duration recorded by the corresponding timer is less than the timer time threshold minTimerThres, the vertical decision tag of the current frame is changed to the vertical decision tag of the previous frame.

[0187] As shown in Figures 14(c) and 14(d), when the vertical decision tag of the previous frame is CFY or CFG and the vertical decision tag of the current frame is YD or GW, intervalTime is added to the duration currently recorded by the corresponding timer. The vertical decision tag of the current frame is changed to YD or GW only when the time of the corresponding timer is greater than the timer time threshold maxTimerThres. When the time of the corresponding timer is less than the timer time threshold maxTimerThres, the vertical decision tag of the current frame is changed to the vertical decision tag of the previous frame. When the vertical decision tag of the previous frame is CFY (or CFG) and the vertical decision tag of the current frame is CFG (or CFY), intervalTime is added to the duration currently recorded by the corresponding timer. The vertical decision tag of the current frame is changed to CFG (or CFY) only when the time of the corresponding timer is greater than the timer time threshold midTimerThres. When the time of the corresponding timer is less than the timer time threshold midTimerThres, the vertical decision tag of the current frame is changed to the vertical decision tag of the previous frame.

[0188] According to the motion trajectory planning method provided in this embodiment of the present application, based on the refined lateral and longitudinal sampling trajectories, path validity is considered laterally, and sampling is performed separately based on the longitudinal creep acceleration sampling space and non-creep acceleration sampling space. Upper and lower bounds on speed for trajectory estimation can be used to reduce the difference between the estimated trajectory and the actual motion trajectory. To ensure safety and comply with traffic regulations, the ego-vehicle actively maintains low-speed creep to closely monitor the behavior of the game object. If the behavior of the game object is abrupt, the time or space distance between the ego-vehicle and the game object is smaller than the safety distance. In this case, the ego-vehicle may be guaranteed to yield to the game object from a creeping state (i.e., non-creep yielding). If the behavior of the game object is conservative, the ego-vehicle may have space to intercept the game object. In this case, the ego-vehicle may find an appropriate opportunity to intercept the game object from a creeping state (i.e., not a non-creep intercepting).

[0189] In this embodiment of the present application, after the interactive game decision-making module shown in Figure 4 generates a final game strategy, the motion planning module generates a speed curve that meets the kinematics requirements of the intelligent driving device based on the final game strategy. The following uses an example in which the final game strategy is a creep strategy to describe the method for the motion planning module to plan a motion trajectory.

[0190] For example, the motion planning module determines a time period during which a first position space of the game object occupies a second position space of the ego-vehicle based on the planned driving path of the ego-vehicle and the estimated trajectory of the game object, and generates a time-based spatial constraint using a collision detection algorithm. As an example, the game scenario shown in FIG. 15 is used. The space occupied by the game object from s1 to s2 of the planned driving path of the ego-vehicle between times t1 and t2 (i.e., the "time period") (i.e., the "second position space") is the ego-vehicle's unpassable space, i.e., the unpassable space indicated by the shaded area in each of FIGS. 16(a) and 17(a), where t1 is the collision start time and t2 is the collision end time.

[0191] Furthermore, the position where the creep starts and the creep duration are determined based on the final game strategy to plan the longitudinal trajectory of the host vehicle. If the final game strategy is a creep forward and yield strategy, the position where the creep forward and yield strategy ends may be s1, and the creep duration may be the duration between t1 and t2. Then, the position where the creep forward and yield strategy starts is determined based on the position where the creep forward and yield strategy ends. For example, the creep distance is determined based on the creep speed and the creep duration, and the position where the creep forward and yield strategy starts is determined based on the creep distance and the position where the creep forward and yield strategy ends. In this way, the speed of the host vehicle from the current position to the position where the creep forward and yield strategy starts is determined based on the position where the creep forward and yield strategy starts and the current position of the host vehicle. If the final game strategy is a creep forward to take over the path strategy, the position where the creep forward to take over the path strategy starts is s1, and the host vehicle ends the creep forward to take over the path strategy at time t1, at time s2. In this way, the creep duration is determined based on the creep speed and the creep travel distance, and the time when the creep forward to take over the path strategy starts is determined based on the creep duration and time t1. In addition, the speed of the host vehicle from the current position to the position where the creep forward to take over the path strategy starts is planned based on the current position of the host vehicle and the position and time when the creep forward to take over the path strategy starts.

[0192] In some possible implementations, a safe distance in time and space is introduced because the behavior of the game object is uncertain. In a creep forward yielding scenario, as shown in FIG. 16(a), TimeGap1 and TimeGap2 are introduced in terms of time. As a result, the ego-vehicle is expected to enter the creep state in advance within TimeGap1 before the conflict start time t1 and exit the creep state within TimeGap2 after the conflict end time t2, i.e., the creep duration CFTime = TimeGap1 + TimeGap2 + (t2 - t1). In terms of space, a safe distance safeDis is introduced to maintain an extra safeDis distance in the space where the ego-vehicle is expected to yield based on the original conflict. This design can increase the spatial distance between the ego-vehicle and the game object, thereby improving creep safety to a certain extent. Furthermore, as shown in FIG. 16(b), within the creep duration CFTime, the intelligent driving device maintains driving at a creep velocity Cf_Velocity. In the scenario of creeping forward to steal a path, as shown in Figure 17(a), a TimeGap is introduced, and the ego vehicle is expected to exit the creep state within the TimeGap before the collision start time t1. Spatial safety distances safeDis1 and safeDis2 are introduced, and in the space where the stealing is expected, the extra safeDis1 and safeDis2 distances are maintained based on the original conflict, i.e., creep distance CFdis = safeDis1 + safeDis2 + (s2 - s1) and creep duration CFTime = CFTime / Cf_Velocity. Furthermore, as shown in Figure 17(b), within the creep duration CFTime, the intelligent driving device maintains creep velocity Cf_Velocity. This design can guarantee the stability of the game strategy to a certain extent and reduce changes in game strategy caused by uncertainty.

[0193] For example, TimeGap1, TimeGap2, and TimeGap may each be 0.5 seconds, or may each be a different value, and the three values may be the same or different. safeDis, safeDis1, and safeDis2 may each be 0.5 meters, or may each be 1 meter, or may each be a different value, and the three values may be the same or different.

[0194] 18 is a schematic flowchart of a motion trajectory planning method 1800 according to one embodiment of the present application. The method shown in the flowchart may be applied to the intelligent driving device shown in FIG. 1, or may be performed by the system shown in FIG. 3 or FIG. 4. The method 1800 includes the following steps:

[0195] S1810: Obtain a planned driving path and first motion parameters of a first intelligent driving device, where the first motion parameters include a speed and / or an acceleration of the first intelligent driving device.

[0196] For example, the first intelligent driving device may be the self-vehicle in the above-mentioned embodiments, or may be another object that can move autonomously, such as an intelligent robot.

[0197] For example, the planned driving path of the first intelligent driving device may be obtained from the planning and control module. The first motion parameters may be obtained from the sensing system. The first motion parameters may include, but are not limited to, speed, acceleration, a correspondence between the position of the first intelligent driving device and time, etc.

[0198] S1820: Obtain a predicted motion trajectory and second motion parameters of the first object, where the second motion parameters include a velocity and / or an acceleration of the first object.

[0199] It should be understood that, in this specification, the entity for obtaining the predicted motion trajectory and the second motion parameter of the first object and the entity for obtaining the planned driving path and the first motion parameter of the first intelligent driving device may be the same entity, e.g., the same entity may be the first intelligent driving device.

[0200] For example, the first object may be the game object in the above-described embodiment, or another object that can influence the first intelligent driving device when planning a motion trajectory. The second motion parameters may include, but are not limited to, velocity, acceleration, correspondence between the position and time of the first object, etc.

[0201] For example, for a method of obtaining the predicted motion trajectory and the second motion parameters of the first object, please refer to the description of the above embodiment, for example, the description of S501 of the method 500. Details will not be repeated here.

[0202] S1830: When the planned driving path partially overlaps with the predicted motion trajectory, determine a planned motion trajectory of the first intelligent driving device based on the first motion parameter and the second motion parameter, and the planned motion trajectory includes a motion trajectory in which the first intelligent driving device intercepts the path of the first object or yields to the first object at a first preset speed.

[0203] For example, for a method for determining whether the planned driving path overlaps with the predicted motion trajectory, please refer to the description of the above embodiment, for example, the description of S502 of the method 500. Details will not be repeated here.

[0204] For example, the first game strategy may be the final game strategy in the aforementioned embodiment, and more specifically, may be the creep strategy, CFY, or CFG in the vertical game strategy in the aforementioned embodiment.

[0205] In some possible implementations, the first preset speed is equal to or greater than 3 km / h and equal to or less than 15 km / h.

[0206] For example, the first preset speed may be the "creep speed" in the above-mentioned embodiment, or may be another speed at which the planned motion trajectory of the first intelligent driving device is not easily affected by the trajectory prediction accuracy of the first object.

[0207] For example, for a method for determining a planned motion trajectory based on the first motion parameter and the second motion parameter, please refer to the description of the above embodiment, for example, the description of the method 800. Details will not be repeated here.

[0208] S1840: Control the first intelligent driving device to drive based on the planned motion trajectory.

[0209] Optionally, the step of determining a planned motion trajectory based on the first motion parameters and the second motion parameters includes the steps of: determining a first estimated trajectory of the first intelligent driving device based on a first sampled acceleration and the first motion parameters, where the first sampled acceleration is determined within the sampling space and is an acceleration that can be reached by the first intelligent driving device; determining a second estimated trajectory of the first object based on a second sampled acceleration and the second motion parameters, where the second sampled acceleration is determined within the sampling space and is an acceleration that can be reached by the first object; and determining a first game strategy based on the first estimated trajectory and the second estimated trajectory when the first estimated trajectory and the second estimated trajectory indicate that the first intelligent driving device will not collide with the first object or indicate that the first object in the driving direction of the first object will collide with the first intelligent driving device in a direction away from the driving direction of the first intelligent driving device at the first time point, where the first time point is a time point after the current time point.

[0210] For example, the first sampling acceleration and the second sampling acceleration may be the vertical sampling acceleration in the above-described embodiment. More specifically, the first sampling acceleration may be the vertical sampling acceleration in the above-described creep vertical sampling space.

[0211] For example, the first estimated orbit and the second estimated orbit may be the estimated orbits in the method 800 of the above-described embodiment. For specific methods for determining the first estimated orbit and the second estimated orbit, please refer to the description of S802 to S804 of the method 800. Details will not be repeated here.

[0212] For example, for a method for determining whether the first intelligent driving device will collide with the first object and the collision type based on the first estimated trajectory and the second estimated trajectory, please refer to the description of method 1100 above. Details will not be repeated here.

[0213] It will be understood that the step of determining the "estimated trajectory" in this embodiment of the present application may be performed by the interactive game decision-making module in the aforementioned embodiment, and the step of determining the "planned motion trajectory" in this embodiment of the present application may be performed by the motion planning module in the aforementioned embodiment.

[0214] Optionally, the first motion parameter includes a speed and / or acceleration of the first intelligent driving device, and the step of determining a first estimated trajectory of the first intelligent driving device based on the first sampled acceleration and the first motion parameter includes the steps of determining a first estimated sub-trajectory based on the first sampled acceleration and the speed and / or acceleration of the first intelligent driving device, wherein the speed of the first intelligent driving device at an end point of the first estimated sub-trajectory is a first preset speed; determining a second estimated sub-trajectory based on the first preset speed, wherein the end point of the first estimated sub-trajectory is a start point of the second estimated sub-trajectory; and determining the first estimated trajectory based on the first estimated sub-trajectory and the second estimated sub-trajectory.

[0215] For example, the first estimated sub-trajectory may include at least one of a delay phase (t∈[0, delayTime)), a constant jerk phase (t∈[delayTime, jerkChangeTime)), and a constant acceleration phase (t∈[jerkChangeTime, speedLimitTime)) in the aforementioned embodiment, and the second estimated sub-trajectory may be a trajectory of the constant acceleration phase in the aforementioned embodiment.

[0216] For example, to determine the first estimated sub-trajectory and the second estimated sub-trajectory, see the description of S802 and S803 of method 800. Details will not be repeated here.

[0217] In some possible implementations, the first estimated trajectory may further include a third estimated sub-trajectory, and the third estimated sub-trajectory may include a trajectory in which the traveling speed decreases from the first preset speed to 0 (i.e., stop).

[0218] Optionally, the step of determining a planned motion trajectory based on the first estimated trajectory and the second estimated trajectory includes the steps of determining a first game strategy based on the first estimated trajectory and the second estimated trajectory, the first game strategy instructing the first intelligent driving device to intercept the path of the first object at a first preset speed or yield to the first object, and when the first duration is greater than a first time threshold, determining a planned motion trajectory based on the first game strategy, the planned driving path, and the second estimated trajectory.

[0219] For example, the duration of the first game strategy may be the duration of any timer within ydToCfgTimer, ydToCfyTimer, gwToCfgTimer, and gwToCfyTimer in the aforementioned embodiments, or the duration of the first game strategy may be the duration of any timer within cfgToCfyTimer or cfyToCfgTimer in the aforementioned embodiments.

[0220] Optionally, the step of determining a planned motion trajectory based on the first game strategy, the planned driving path, and the second estimated trajectory includes the steps of determining a period during which the first position space of the first object occupies the second position space of the first intelligent driving device based on the planned driving path and the second estimated trajectory, and determining a planned motion trajectory based on the first game strategy, the second position space, and the period, wherein the planned motion trajectory includes a trajectory along which the first intelligent driving device moves at a first preset speed in the second position space, or the planned motion trajectory includes a trajectory along which the first intelligent driving device moves at a first preset speed during the period.

[0221] For example, the planned motion trajectory may be the trajectory of the intelligent driving device that continues to move at the creep velocity Cf_Velocity within the creep duration CFTime in the above-described embodiment, as shown in FIG. 16 or FIG.

[0222] For example, for a more specific method for determining a planned motion trajectory based on the first game strategy, the planned driving path, and the second estimated trajectory, please refer to the description of the above embodiment, and the details will not be repeated here.

[0223] Optionally, before the step of determining a first game strategy based on the first estimated trajectory and the second estimated trajectory, the method further includes a step of determining that a strategy cost of an estimated trajectory pair including the first estimated trajectory and the second estimated trajectory is minimum.

[0224] For example, the strategic cost may be the strategic cost in the above-described embodiment.

[0225] For a method for determining the strategy cost of the first game strategy based on the type of the first object, the first estimated trajectory, and the second estimated trajectory, please refer to the description of S804 of method 800. Details will not be repeated here.

[0226] Optionally, before the step of obtaining the predicted motion trajectory and the second motion parameters of the first object, the method further includes a step of determining that the distance between the first object and the first intelligent driving device is less than or equal to a first distance threshold and greater than or equal to a second distance threshold.

[0227] For example, the first distance threshold may be the preset distance in S501 of the method 500 described above.

[0228] For example, the second distance threshold may be determined based on the CIPV screening in the above-described embodiment, or may be determined using another method.

[0229] According to the motion trajectory planning method provided in this embodiment of the present application, under the premise of ensuring safety and complying with traffic regulations, the host vehicle can actively maintain a creep speed and closely monitor the behavior of game objects, so that the planned motion trajectory of the host vehicle is less affected by game objects. In particular, in narrow lanes where both automobiles and non-automobiles may be traveling, or in unmarked intersections, the host vehicle will not have problems such as unexpected and frequent incorrect braking, incorrect stopping, continuous yielding, and simultaneous starting and stopping. This helps improve the passing efficiency of the host vehicle and improve the user's riding experience.

[0230] In the embodiments of the present application, unless otherwise specified or there is no logical contradiction, the terms and / or descriptions between the embodiments are consistent and can be cross-referenced, and the technical features of different embodiments can be combined based on their internal logical relationships to form new embodiments.

[0231] Above, the method provided in the embodiment of the present application has been described in detail with reference to FIGS. 5 to 18. Hereinafter, the device provided in one embodiment of the present application will be described in detail with reference to FIGS. 19 and 20. It should be understood that the description of the device embodiment corresponds to the description of the method embodiment. Therefore, for the contents that have not been explained in detail, please refer to the above-mentioned method embodiment. For the sake of brevity, the details will not be explained again here.

[0232] 19 is a schematic block diagram of a motion trajectory planning apparatus 1900 according to an embodiment of the present application. The apparatus 1900 includes an acquisition unit 1910 and a processing unit 1920. The acquisition unit 1910 can implement corresponding communication functions, and the processing unit 1920 is configured to perform data processing.

[0233] Optionally, the apparatus 1900 may further include a storage unit. The storage unit may be configured to store instructions and / or data. The processing unit 1920 may read the instructions and / or data in the storage unit to enable the apparatus to implement the above-described method embodiments.

[0234] Apparatus 1900 may include units configured to perform the method of Figure 5, Figure 8, or Figure 18. In addition, the units in apparatus 1900 and other operations and / or functions described above are used to realize corresponding procedures in the method embodiments of Figure 5, Figure 8, or Figure 18, respectively.

[0235] When the apparatus 1900 is configured to perform the method 1800 of FIG. 18, the acquisition unit 1910 may be configured to perform S1810 and S1820 of the method 1800, and the processing unit 1920 may be configured to perform S1830 and S1840 of the method 1800.

[0236] In particular, the acquisition unit 1910 of the apparatus 1900 is configured to acquire a planned driving path and first motion parameters of the first intelligent driving device, the first motion parameters including a speed and / or acceleration of the first intelligent driving device, and acquire a predicted motion trajectory and second motion parameters of the first object, the second motion parameters including the speed and / or acceleration of the first object. The processing unit 1920 is further configured to determine a planned motion trajectory of the first intelligent driving device based on the first motion parameter and the second motion parameter when the planned driving path overlaps with the predicted motion trajectory, the planned motion trajectory including a motion trajectory in which the first intelligent driving device intercepts or yields to the path of the first object at a first preset speed, and to control the first intelligent driving device to drive based on the planned motion trajectory.

[0237] In some possible implementations, the processing unit 1920 is specifically configured to: determine a first estimated trajectory of the first intelligent driving device based on a first sampled acceleration and a first motion parameter, where the first sampled acceleration is determined within the sampling space and is an acceleration that can be reached by the first intelligent driving device; determine a second estimated trajectory of the first object based on a second sampled acceleration and a second motion parameter, where the second sampled acceleration is determined within the sampling space and is an acceleration that can be reached by the first object; and determine a planned motion trajectory based on the first estimated trajectory and the second estimated trajectory when the first estimated trajectory and the second estimated trajectory indicate that the first intelligent driving device will not collide with the first object or indicate that the first object will collide with a side housing or rear of the first intelligent driving device in the driving direction of the first object, where the first time point is a time point after the current time point.

[0238] In some possible implementations, the processing unit 1920 is specifically configured to determine a first estimated sub-trajectory based on the first sampled acceleration and the speed and / or acceleration of the first intelligent driving device, the speed of the first intelligent driving device at the end of the first estimated sub-trajectory is a first preset speed, determine a second estimated sub-trajectory based on the first preset speed, the end of the first estimated sub-trajectory is the start point of the second estimated sub-trajectory, and the first estimated trajectory includes the first estimated sub-trajectory and the second estimated sub-trajectory.

[0239] In some possible implementations, the processing unit 1920 is specifically configured to determine a first game strategy based on the first estimated trajectory and the second estimated trajectory, the first game strategy instructing the first intelligent driving device to intercept the path of the first object at a first preset speed or yield to the first object, and when the first duration is greater than a first time threshold, determine a planned movement trajectory based on the first game strategy, the planned driving path, and the second estimated trajectory.

[0240] In some possible implementation forms, the processing unit 1920 is specifically configured to determine a period of time during which the first position space of the first object occupies the second position space of the first intelligent driving device based on the planned driving path and the second estimated trajectory, and determine a planned movement trajectory based on the first game strategy, the second position space, and the period of time, wherein the planned movement trajectory includes a trajectory during which the first intelligent driving device moves at a first preset speed in the second position space, or the planned movement trajectory includes a trajectory during which the first intelligent driving device moves at a first preset speed.

[0241] In some possible implementations, the processing unit 1920 is specifically configured to determine that the strategy cost of an estimated orbit pair including a first estimated orbit and a second estimated orbit is the smallest.

[0242] In some possible implementations, the processing unit 1920 is specifically configured to determine a first estimated trajectory based on a lateral offset of the first intelligent driving device, a first sampled acceleration, and a first motion parameter, where the lateral offset is an offset perpendicular to the driving direction of the first intelligent driving device.

[0243] In some possible implementations, the processing unit 1920 is further configured to determine that the distance between the first object and the first intelligent driving device is less than or equal to a first distance threshold and greater than or equal to a second distance threshold.

[0244] In some possible implementations, the first preset speed is equal to or greater than 3 km / h and equal to or less than 15 km / h.

[0245] It should be understood that the division into units within the device is merely a logical division of function. In actual implementation, all or some of the units may be integrated into one physical entity or may be physically separated. In addition, the units within the device may be implemented in the form of a processor that invokes software. For example, the device may include a processor connected to a memory, which stores instructions, and the processor invokes the instructions stored in the memory to implement any one of the methods or functions of the units within the device. The processor may be a general-purpose processor such as a CPU or microprocessor, and the memory may be memory within the device or memory external to the device. Alternatively, the units within the device may be implemented in the form of a hardware circuit, and the functions of some or all of the units may be implemented by designing a hardware circuit. A hardware circuit may be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the units are implemented by designing a logical relationship between elements within the circuit. As another example, in another implementation, the hardware circuit may be implemented using a PLD. Using an FPGA as an example, the FPGA can include a large number of logic gate circuits, and the connections between the logic gate circuits are configured using a configuration file to implement some or all of the functions of the aforementioned units. All of the units of the aforementioned device can be implemented in the form of software called by a processor, or in the form of hardware circuits, or some of the units can be implemented in the form of software called by a processor, and the remaining units can be implemented in the form of hardware circuits.

[0246] In an embodiment of the present application, a processor is a circuit having signal processing capabilities. In one implementation, the processor may be a circuit capable of reading and executing instructions, such as a CPU, a microprocessor, a GPU, or a DSP. In another implementation, the processor can implement a specific function by using the logical relationships of a hardware circuit, which may be fixed or reconfigurable. For example, the processor may be a hardware circuit implemented by an ASIC or a PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the hardware circuit may be understood as the process of the processor loading instructions to implement some or all of the functions of the aforementioned units. In addition, the processor may be a hardware circuit designed for artificial intelligence, such as an ASIC, an NPU, a TPU, or a DPU.

[0247] It will be appreciated that the units within the aforementioned apparatus may be configured to implement one or more processors (or processing circuits) of the aforementioned methods, such as a CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0248] Furthermore, all or some of the units in the aforementioned devices may be integrated or implemented independently. In one implementation, these units are integrated and implemented in the form of a system-on-a-chip (SOC). The SOC may include at least one processor configured to implement any one of the aforementioned methods or to implement the functions of the units of the device. The type of the at least one processor may vary, and may include, for example, a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0249] For example, the acquisition unit 1910 may include the game object selection module shown in FIG. 4, and the processing unit 1920 may include the interactive game decision-making module and / or the motion planning module shown in FIG.

[0250] In a particular implementation, the operations performed by the acquisition unit 1910 and the processing unit 1920 may be performed by the same processor or different processors, e.g., multiple processors. In one example, one or more processors may be connected to one or more sensors in the sensing system 120 of FIG. 1 to acquire first motion parameters of the intelligent driving device from the one or more sensors and process the first motion parameters to acquire an estimated trajectory of the intelligent driving device. Alternatively, one or more processors may be further connected to a power system of the intelligent driving device to control the intelligent driving device to travel based on the planned motion trajectory. For example, in a particular implementation, the one or more processors may be disposed in an in-vehicle infotainment system or another in-vehicle terminal. For example, in a particular implementation, the apparatus 1900 may be a chip disposed in the in-vehicle infotainment system or another in-vehicle terminal. For example, in a particular implementation, the apparatus 1900 may be the computing platform 150 shown in FIG. 1 disposed in the intelligent driving device.

[0251] FIG. 20 is a schematic block diagram of a motion trajectory planning device according to an embodiment of the present application. The motion trajectory planning device 2000 shown in FIG. 20 may include a processor 2010, a transceiver 2020, and a memory 2030. The processor 2010, the transceiver 2020, and the memory 2030 are connected using an internal connection path. The memory 2030 is configured to store instructions. The processor 2010 is configured to execute the instructions stored in the memory 2030 so that the transceiver 2020 receives / transmits some parameters. Optionally, the memory 2030 may be coupled to the processor 2010 using an interface or may be integrated into the processor 2010.

[0252] It should be noted that the transceiver 2020 may include, but is not limited to, an input / output interface transceiver device to facilitate communication between the apparatus 2000 and another device or communication network.

[0253] In the implementation process, the steps of the aforementioned method can be performed by using integrated logic circuits of hardware in the processor 2010 or by using instructions in the form of software. The methods disclosed with reference to the embodiments of the present application may be directly executed by a hardware processor, or may be executed by using a combination of hardware and software modules in the processor. The software modules may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, or a register. The storage medium is located in the memory 2030, and the processor 2010 reads information from the memory 2030 and performs the steps of the aforementioned method in cooperation with the processor hardware. To avoid repetition, details will not be described again here.

[0254] The processor 2010 may be a general-purpose CPU, a microprocessor, an ASIC, a GPU, or one or more integrated circuits configured to execute associated programs to implement the motion trajectory planning method in the method embodiments of the present application. The processor 2010 may be an integrated circuit chip and have signal processing capabilities. In a specific implementation process, the steps of the motion trajectory planning method of the present application may be performed using instructions in the form of integrated logic circuits of hardware or software within the processor 2010. Alternatively, the processor 2010 may be a general-purpose processor, a DSP, an ASIC, an FPGA or another programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The processor may implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor, or the processor may be any conventional processor, etc. The steps of the methods disclosed with reference to the embodiments of the present application may be directly executed and achieved by a hardware decoding processor, or may be executed and achieved by using a combination of hardware and software modules within the decoding processor. The software modules may be located in a storage medium that is mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, or a register. The storage medium is located in memory 2030. The processor 2010 reads the information in memory 2030 and, in cooperation with the processor hardware, executes the motion trajectory planning method in the method embodiment of the present application.

[0255] The memory 2030 may be a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM).

[0256] The transceiver 2020 uses a transceiver device, such as, but not limited to, a transceiver, to facilitate communication between the device 2000 and another device or a communication network.

[0257] For example, the transceiver 2010 may include a game object sorting module as shown in FIG. 4, and the processor 2020 may include an interactive game decision-making module and / or a motion planning module as shown in FIG.

[0258] An embodiment of the present application further provides an intelligent driving device, which can include the aforementioned device 1900 or the aforementioned device 2000.

[0259] An embodiment of the present application further provides a computer-readable medium, which stores program code or instructions, which, when executed by a processor of a computer, enable the processor to implement the method of FIG.

[0260] An embodiment of the present application further provides a chip including at least one processor and a memory, wherein the at least one processor is coupled to the memory and configured to read and execute instructions in the memory to perform the method of Figure 5, Figure 8, or Figure 18.

[0261] All aspects, embodiments, or features are presented in this application in terms of systems that include multiple devices, components, modules, etc. It is to be appreciated and understood that each system may include other devices, components, modules, etc. and / or may not include all of the devices, components, modules, etc. discussed with reference to the accompanying drawings. Additionally, combinations of these solutions may also be used.

[0262] It should be understood that the sequence numbers of the above processes do not refer to the execution order in various embodiments of the present application, and the execution order of the processes should be determined based on the functions and internal logic of the processes, and should not be construed as any limitation on the implementation process of the embodiments of the present application.

[0263] Additionally, in the embodiments of this application, terms such as "for example," "e.g.," and the like are used to denote providing an example, illustration, or description. Any embodiment or design scheme described in this application as an "example" is not described as being preferred over other embodiments or design schemes, or as having any particular advantages. Rather, the term "example" is used to present concepts in a particular way.

[0264] In the embodiments of the present application, "corresponding" and "corresponding" may be used interchangeably. It should be noted that the meanings represented by the terms are consistent when no differences are highlighted.

[0265] References herein to "one embodiment," "some embodiments," etc., indicate that one or more embodiments of the present application include the particular feature, structure, or characteristic described with reference to the embodiment. Thus, statements such as "in one embodiment," "in some embodiments," "in some other embodiments," and "in other embodiments" appearing in various places herein are not necessarily meant to refer to the same embodiment. Instead, unless specifically emphasized otherwise, these statements mean "one or more, but not all, embodiments." The terms "including," "having," and variations thereof all mean "including, but not limited to," unless specifically emphasized otherwise.

[0266] Those skilled in the art will recognize that, in combination with the examples described in the embodiments disclosed herein, the units and algorithm steps can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed by hardware or software depends on the specific application and the design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but the implementation should not be considered to go beyond the scope of this application.

[0267] For the sake of convenience, those skilled in the art will clearly understand that the detailed operation processes of the above-mentioned systems, devices and units may refer to the corresponding processes in the above-mentioned method embodiments, and the details will not be repeated here.

[0268] In some embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other ways. For example, the described device embodiments are merely examples. For example, the division into units is merely a logical division of function, and may be otherwise implemented in actual practice. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not implemented. Furthermore, the shown or described mutual couplings or direct couplings or communication connections may be implemented using some interfaces. Indirect couplings or communication connections between devices or units may be implemented in electronic, mechanical, or other forms.

[0269] The units described as separate parts may or may not be physically separate, and the parts shown as units may or may not be physical units, or may be located in one place or distributed over multiple network units. Some or all of the units may be selected based on actual requirements to achieve the objectives of the solutions of the embodiments.

[0270] In addition, the functional units of the embodiments of the present application may be integrated into one processing unit, each of the units may exist physically alone, or two or more units may be integrated into one unit.

[0271] When functions are implemented in the form of software functional units and sold or used as independent products, the functions may be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application may essentially be implemented in the form of a software product, or a portion of the technical solutions may be implemented in the form of a software product. The computer software product is stored in a storage medium and includes instructions for instructing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the methods described in the embodiments of the present application. The aforementioned storage medium includes any medium capable of storing program code, such as a USB flash drive, a removable hard disk, a ROM, a RAM, a magnetic disk, an optical disk, etc.

[0272] The above description is merely a specific implementation of the present application and is not intended to limit the scope of protection of the present application. Any variations or replacements that can be easily conceived by those skilled in the art within the technical scope disclosed in the present application shall fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the scope of protection of the claims. [Explanation of symbols]

[0273] 100 Intelligent Driving Devices 120 Detection System 130 Display device 150 Computing Platforms 151 processors 152 processors 15n processor 500 Motion trajectory planning method 800 Motion trajectory planning method 1800 Motion trajectory planning method 1900 Motion trajectory planning device 1910 Acquisition Units 1920 processing units 2000 Motion Trajectory Planning Device 2010 Processor, Transceiver 2020 processor, transceiver 2030 Memory

Claims

1. A motion trajectory planning method, comprising: acquiring a planned driving path and first motion parameters of a first intelligent driving device, the first motion parameters including a speed and / or an acceleration of the first intelligent driving device; obtaining a predicted motion trajectory and second motion parameters of a first object, the second motion parameters including a velocity and / or an acceleration of the first object; When the planned driving path overlaps with the predicted motion trajectory, determining a planned motion trajectory of the first intelligent driving device based on the first motion parameter and the second motion parameter, wherein the planned motion trajectory includes a motion trajectory in which the first intelligent driving device intercepts or yields to the first object at a first preset speed; controlling the first intelligent driving device to drive based on the planned motion trajectory; A method comprising:

2. determining a planned motion trajectory of the first intelligent driving device based on the first motion parameter and the second motion parameter; determining a first estimated trajectory of the first intelligent driving device based on a first sampled acceleration and the first motion parameter, wherein the first sampled acceleration is determined within a sampling space and is an acceleration that can be reached by the first intelligent driving device; determining a second estimated trajectory of the first object based on a second sampled acceleration and the second motion parameter, the second sampled acceleration being an acceleration determined within the sampling space that may be reached by the first object; determining the planned motion trajectory based on the first estimated trajectory and the second estimated trajectory when the first estimated trajectory and the second estimated trajectory indicate that the first intelligent driving device will not collide with the first object or that the first object will collide with a side housing or a rear part of the first intelligent driving device in the traveling direction of the first object at a first time point, wherein the first time point is a time point after a current time point; 2. The method of claim 1, comprising:

3. determining a first estimated trajectory of the first intelligent driving device based on a first sampled acceleration and the first motion parameter; determining a first estimated sub-trajectory based on the first sampled acceleration and the velocity and / or acceleration of the first intelligent driving device, wherein the velocity of the first intelligent driving device at an end point of the first estimated sub-trajectory is the first preset velocity; determining a second estimated sub-trajectory based on the first preset velocity, wherein the end point of the first estimated sub-trajectory is a start point of the second estimated sub-trajectory; determining the first estimated trajectory based on the first estimated sub-trajectory and the second estimated sub-trajectory; 3. The method of claim 2, comprising:

4. determining the planned motion trajectory based on the first estimated trajectory and the second estimated trajectory, determining a first game strategy based on the first estimated trajectory and the second estimated trajectory, the first game strategy instructing the first intelligent driving device to either intercept the path of the first object at the first preset speed or yield to the first object; determining the planned motion trajectory based on the first game strategy, the planned travel path, and the second estimated trajectory when a duration of the first game strategy is greater than a first time threshold; 4. The method of claim 2 or 3, comprising:

5. determining the planned motion trajectory based on the first game strategy, the planned travel path, and the second estimated trajectory, Determining a period during which a first position space of the first object occupies a second position space of the first intelligent driving device based on the planned driving path and the second estimated trajectory; determining the planned motion trajectory based on the first game strategy, the second position space, and the time period, wherein the planned motion trajectory includes a trajectory along which the first intelligent driving device travels in the second position space at the first preset speed, or the planned motion trajectory includes a trajectory along which the first intelligent driving device travels at the first preset speed during the time period; 5. The method of claim 4, comprising:

6. Before the step of determining a first game strategy based on the first estimated trajectory and the second estimated trajectory, the method further comprises: The method of claim 4 , further comprising determining that a strategy cost of an estimated trajectory pair including the first estimated trajectory and the second estimated trajectory is the smallest.

7. determining a first estimated trajectory of the first intelligent driving device based on a first sampled acceleration and the first motion parameter; determining the first estimated trajectory based on a lateral offset of the first intelligent driving device, the first sampled acceleration, and the first motion parameter, wherein the lateral offset is an offset perpendicular to a driving direction of the first intelligent driving device; 7. The method of any one of claims 2 to 6, comprising:

8. Before the step of obtaining a predicted motion trajectory and a second motion parameter of a first object, the method further comprises:

8. The method of claim 1, further comprising determining that a distance between the first object and the first intelligent driving device is less than or equal to a first distance threshold and greater than or equal to a second distance threshold.

9. 9. The method of claim 1, wherein the first preset speed is greater than or equal to 3 kilometers per hour and less than or equal to 15 kilometers per hour.

10. A motion trajectory planning device comprising an acquisition unit and a processing unit, The acquisition unit: configured to obtain a planned driving path and first motion parameters of a first intelligent driving device, and obtain a predicted motion trajectory and second motion parameters of a first object, wherein the first motion parameters include a speed and / or acceleration of the first intelligent driving device, and the second motion parameters include a speed and / or acceleration of the first object; The processing unit When the planned driving path partially overlaps with the predicted motion trajectory, determine a planned motion trajectory of the first intelligent driving device based on the first motion parameters and the second motion parameters; An apparatus configured to control the first intelligent driving device to travel based on the planned motion trajectory, wherein the planned motion trajectory includes a motion trajectory in which the first intelligent driving device intercepts the path of the first object or yields to the first object at a first preset speed.

11. The processing unit is configured to determine a first estimated trajectory of the first intelligent driving device based on a first sampled acceleration and the first motion parameter, the first sampled acceleration being determined within a sampling space and being an acceleration that can be reached by the first intelligent driving device; The processing unit determining a second estimated trajectory of the first object based on a second sampled acceleration and the second motion parameter, the second sampled acceleration being an acceleration determined within the sampling space that may be reached by the first object; The processing unit The device of claim 10, wherein the device is configured to determine the planned motion trajectory based on the first estimated trajectory and the second estimated trajectory when the first estimated trajectory and the second estimated trajectory indicate that the first intelligent driving device will not collide with the first object or that the first object will collide with a side housing or rear of the first intelligent driving device in the driving direction of the first object at a first time point, the first time point being a time point after the current time point.

12. The first motion parameter includes the velocity and / or the acceleration of the first intelligent driving device, and the processing unit: configured to determine a first estimated sub-trajectory based on the first sampled acceleration and the velocity and / or acceleration of the first intelligent driving device, wherein the velocity of the first intelligent driving device at an end point of the first estimated sub-trajectory is the first preset velocity; The processing unit configured to determine a second estimated sub-trajectory based on the first preset velocity, the end point of the first estimated sub-trajectory being a start point of the second estimated sub-trajectory; The processing unit The apparatus of claim 11 , configured to determine the first estimated trajectory based on the first estimated sub-trajectory and the second estimated sub-trajectory.

13. The processing unit further configured to determine a first game strategy based on the first estimated trajectory and the second estimated trajectory, the first game strategy instructing the first intelligent driving device to intercept or yield to the first object at the first preset speed; The processing unit 13. The device of claim 11 or 12, further configured to determine the planned movement trajectory based on the first game strategy, the planned travel path, and the second estimated trajectory when a duration of the first game strategy is greater than a first time threshold.

14. The processing unit Determine a time period during which a first position space of the first object occupies a second position space of the first intelligent driving device based on the planned driving path and the second estimated trajectory; The device of claim 13, configured to determine the planned motion trajectory based on the first game strategy, the second position space, and the time period, wherein the planned motion trajectory includes a trajectory along which the first intelligent driving device travels in the second position space at the first preset speed, or the planned motion trajectory includes a trajectory along which the first intelligent driving device travels at the first preset speed during the time period.

15. The processing unit The apparatus of claim 13 , further configured to determine that a strategy cost of an estimated trajectory pair including the first estimated trajectory and the second estimated trajectory is smallest.

16. The processing unit 16. The apparatus of claim 11, configured to determine the first estimated trajectory based on a lateral offset of the first intelligent driving device, the first sampled acceleration, and the first motion parameter, wherein the lateral offset is an offset perpendicular to a driving direction of the first intelligent driving device.

17. The processing unit 17. The apparatus of claim 10, further configured to determine that a distance between the first object and the first intelligent driving device is less than or equal to a first distance threshold and greater than or equal to a second distance threshold.

18. 18. The apparatus of any one of claims 10 to 17, wherein the first preset speed is greater than or equal to 3 kilometers per hour and less than or equal to 15 kilometers per hour.

19. A motion trajectory planning device, a memory configured to store a computer program; a processor configured to execute the computer program stored in the memory so that the motion trajectory planning device performs the method according to any one of claims 1 to 9; An apparatus comprising:

20. An intelligent driving device comprising an apparatus according to any one of claims 10 to 19.

21. A chip comprising a processor and a data interface, the processor reading instructions stored in a memory via the data interface to perform the method of any one of claims 1 to 9.

Images