Lane-changing trajectory planning method, autonomous driving method, and related apparatus

Abstract

A lane-changing trajectory planning method, an autonomous driving method, and a related apparatus. The autonomous driving method comprises: on the basis of first motion state information of an intelligent driving device and second motion state information of an opponent, controlling the intelligent driving device to change to a target lane within a first lane-changing time period and to be located in front of the opponent, wherein the opponent is located on the target lane for the intelligent driving device, and is located between a first position and a second position, wherein the first position is located behind the intelligent driving device and longitudinally distant from the intelligent driving device by a first distance, and the second position is located in front of the intelligent driving device and longitudinally distant from the intelligent driving device by a second distance. The technical solution of the present application can be applied to intelligent vehicles such as a new energy vehicle and an electric vehicle, and facilitates improvement of lane-changing success rates and traffic efficiency when the vehicles are in an autonomous driving mode in complex lane-changing scenarios such as merging into congested roads and merging into ramps.

Description

Lane changing trajectory planning method, automatic driving method and related device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on March 1, 2024, with application number 202410240094.3 and invention name “Lane change trajectory planning method, autonomous driving method and related devices”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of intelligent driving, and more specifically, to a lane change trajectory planning method, an automatic driving method, and related devices. Background Art

[0003] As vehicles evolve toward intelligence and automation, more and more are equipped with intelligent driving technology to reduce driving stress and improve safety. However, current intelligent driving technology has limited planning capabilities in lane-changing scenarios and can generally only handle simple lane-changing scenarios. It is unable to quickly plan safe lane-changing paths for complex lane-changing scenarios, such as merging into congestion or merging onto ramps, resulting in low lane-changing success rates and traffic efficiency.

[0004] In view of this, a technical solution that can improve the lane changing success rate and traffic efficiency in complex lane changing scenarios is in urgent need of development. Summary of the Invention

[0005] The present application provides a lane change trajectory planning method, an autonomous driving method and related devices, which can improve the lane change success rate and traffic efficiency in complex lane change scenarios (such as congested merging and ramp merging).

[0006] In a first aspect, a lane change trajectory planning method is provided, which can be executed by an intelligent driving device or a component of the intelligent driving device (such as a chip or a chip system), and the method includes: obtaining first motion state information of a game target and second motion state information of the intelligent driving device, the game target is located in a target lane of the intelligent driving device, and the game target is located between a first position and a second position; wherein the first position is located behind the intelligent driving device and the longitudinal distance between the game target and the intelligent driving device is a first distance, and the second position is located in front of the intelligent driving device and the longitudinal distance between the game target and the intelligent driving device is a second distance; based on the first motion state information and the second motion state information, planning a target trajectory for the intelligent driving device to change lanes to the target lane, and the intelligent driving device rushing to the game target when driving along the target trajectory.

[0007] In the above technical solution, in the lane-changing scenario of the intelligent driving device, the driving trajectory of the target of the overtaking game is planned for the intelligent driving device. When the target lane is a more congested lane, or when the current lane of the intelligent driving device is a ramp and the target lane is a relatively busy highway, it helps to improve the merging success rate and traffic efficiency of the intelligent driving device into the target lane.

[0008] In combination with the first aspect, in certain implementations of the first aspect, a target trajectory of the intelligent driving device for changing lanes to the target lane is planned based on the first motion state information and the second motion state information, including: planning the target trajectory based on the intelligent driving device's occupancy priority for the target lane, the first motion state information, and the second motion state information.

[0009] For example, the intelligent driving device's occupation priority for the target lane can indicate the priority of the intelligent driving device in occupying the right-of-way in the target lane. A higher occupation priority indicates a greater advantage in the game between the intelligent driving device and the target; a lower occupation priority indicates a smaller advantage in the game between the intelligent driving device and the target. It is understood that the intelligent driving device's driving path can influence the target's behavior to a certain extent. For example, when the intelligent driving device's lane-changing behavior is more aggressive, the target may be forced to brake to avoid the intelligent driving device. Therefore, when the intelligent driving device's occupation priority for the target lane is higher, a more aggressive lane-changing trajectory can be planned for the intelligent driving device. For example, a conflicting area between the lane-changing trajectory and the target's predicted trajectory can be allowed, or when the intelligent driving device is traveling along the lane-changing trajectory and the target is traveling along the predicted trajectory, a certain degree of lateral overlap between the intelligent driving device and the target is allowed at the same time. Furthermore, when the intelligent driving device's occupation priority for the target lane is lower, a more conservative lane-changing trajectory can be planned for the intelligent driving device. For example, no conflicting areas are allowed between the lane-changing trajectory and the predicted trajectory of the game target. Furthermore, when the intelligent driving device is traveling along the lane-changing trajectory and the game target is traveling along the predicted trajectory, no lateral overlap between the intelligent driving device and the game target is allowed at the same time. In the above technical solution, since the lane-changing behavior of the intelligent driving device can affect the behavior of the game target to a certain extent, considering the priority of the intelligent driving device and the game target in occupying the right of way in the target lane during the target trajectory planning process helps improve the rationality and feasibility of the planned lane-changing trajectory, thereby helping to improve safety during the lane-changing process.

[0010] In combination with the first aspect, in certain implementations of the first aspect, the first motion state information includes a planned trajectory of the intelligent driving device, and the second motion state information includes a predicted trajectory of the game target. The method also includes: determining a conflict position based on the planned trajectory and the predicted trajectory, the conflict position being a position where the lateral distance between the planned trajectory and the predicted trajectory is less than or equal to a third distance; determining the priority of the intelligent driving device for occupying the target lane based on the conflict position, the lateral distance corresponding to the conflict position, the first time required for the intelligent driving device to reach the conflict position, and the second time required for the game target to reach the conflict position; planning the target trajectory, including: when the priority of the intelligent driving device for occupying the target lane is greater than or equal to a first threshold, planning the target trajectory based on a first lateral overlap degree; or, when the priority of the intelligent driving device for occupying the target lane is less than the first threshold, planning the target trajectory based on a second lateral overlap degree; wherein the first lateral overlap degree and the second lateral overlap degree indicate the degree of lateral overlap between the intelligent driving device and the game target at the conflict position, and the first lateral overlap degree is greater than the second lateral overlap degree.

[0011] For example, if both the intelligent driving device and the game target are vehicles, the lateral overlap indicates the degree of lateral overlap between the two vehicles at the collision point. In other words, the greater the lateral overlap, the greater the degree of lateral overlap between the intelligent driving device and the game target at the collision point, and the higher the risk of a collision between the two.

[0012] In the above technical solution, the lateral overlap is adjusted according to the occupancy priority, and then the lane change trajectory is adjusted, which helps to improve the comfort of the driver and passenger of the intelligent driving equipment while ensuring driving safety during the lane change process.

[0013] In combination with the first aspect, in certain implementations of the first aspect, a target trajectory of the intelligent driving device for changing lanes to a target lane is planned based on the first motion state information and the second motion state information, including: determining a first time distance between the intelligent driving device and a game target based on the first motion state information and the second motion state information; determining a lane change start time for the intelligent driving device to change from a current lane to a target lane based on the first time distance, with the game target being located behind the intelligent driving device at the lane change start time; and planning the target trajectory based on the lane change start time and the lane change end time for the intelligent driving device to change from the current lane to the target lane.

[0014] In some implementations, the time when the first time distance is greater than or equal to the safety time distance is determined as the lane change start time.

[0015] In some implementations, if there is no obstacle in front of the intelligent driving device in the target lane, the lane change end time can be determined based on the lane change start time and a preset time length, which can be any time length between 2.5 seconds and 6 seconds, or the preset time length can also be other time lengths.

[0016] In the above technical solution, determining the lane-changing time period based on the time distance between the intelligent driving device and the game target helps improve the rationality of intelligent driving lane-changing behavior. Furthermore, initiating the lane change when the time distance between the intelligent driving device and the game target is greater than or equal to the safe time distance helps improve the game target's coordination, thereby improving lane-changing efficiency.

[0017] In combination with the first aspect, in certain implementations of the first aspect, when there is an obstacle in the target lane and the obstacle is located in front of the game target and the intelligent driving device, the method also includes: determining a second time distance between the intelligent driving device and the obstacle; and determining the lane change termination time based on the second time distance.

[0018] In some implementations, during a lane change, the distance between the intelligent driving device and the obstacle ahead may decrease. Therefore, the lane change termination time may be determined as the time when the second time distance is less than or equal to the safety time distance. Alternatively, the lane change termination time may be determined as the time when either the first time distance or the second time distance is less than or equal to the safety time distance.

[0019] In the above technical solution, when planning the lane-changing trajectory, considering the obstacles in front and behind the intelligent driving device helps to improve safety during the lane-changing process.

[0020] In combination with the first aspect, in certain implementations of the first aspect, a target trajectory of the intelligent driving device for changing lanes to the target lane is planned based on the first motion state information and the second motion state information, including: determining a conflict area in which the intelligent driving device and the game target have a longitudinal overlap based on the first motion state information and the second motion state information; determining a longitudinal planned speed of the intelligent driving device and a longitudinal predicted speed of the game target based on a first time period from the current position of the intelligent driving device to the conflict area; wherein, when the intelligent driving device travels at the longitudinal planned speed and the game target travels at the longitudinal predicted speed, the intelligent driving device overtakes the game target; and planning the target trajectory based on the longitudinal planned speed and the longitudinal predicted speed.

[0021] In some implementations, if the speed and / or acceleration of the game target is too fast, the game target may overtake the intelligent driving device. When the above situation occurs, the intelligent driving device uses the vehicle behind the game target as the new game target and executes the above method.

[0022] In combination with the first aspect, in certain implementations of the first aspect, determining the longitudinal planning speed of the intelligent driving device and the longitudinal predicted speed of the game target based on the first time period includes: determining the longitudinal planning speed and the longitudinal predicted speed based on the first time period, the forward collision risk of the intelligent driving device, and the rearward collision risk of the intelligent driving device.

[0023] Among them, the rear collision risk indicates the collision risk between the intelligent driving device and the game target.

[0024] In the above technical solution, the longitudinal planning speed and the longitudinal prediction speed are preliminarily determined based on the forward collision risk and the rearward collision risk, which helps to improve the convergence speed of the optimization results (such as the longitudinal planning speed and the longitudinal prediction speed), and then the target trajectory is planned based on the constraints of the longitudinal planning speed and the longitudinal prediction speed, which helps to improve the efficiency of obtaining the target trajectory, thereby improving the intelligence of the intelligent driving device and the lane changing efficiency of the intelligent driving device.

[0025] In a second aspect, an automatic driving method is provided, which can be executed by an intelligent driving device or a component of the intelligent driving device (such as a chip or a chip system), and the method includes: obtaining first motion state information of a game target and second motion state information of the intelligent driving device, the game target is located in a target lane of the intelligent driving device, and the game target is located between a first position and a second position; wherein the first position is located behind the intelligent driving device and the longitudinal distance between the game target and the intelligent driving device is a first distance, and the second position is located in front of the intelligent driving device and the longitudinal distance between the game target and the intelligent driving device is a second distance; according to the first motion state information and the second motion state information, the intelligent driving device is controlled to change to the target lane within a first lane change time period and be located in front of the game target.

[0026] In the above technical solution, if the intelligent driving device needs to change lanes and there is an object (such as a vehicle) in the target lane that affects the intelligent driving device's lane change trajectory, the intelligent driving device can overtake the object to change to the target lane. In autonomous driving scenarios, the above solution can achieve lane changes with similar behavior to human drivers in complex lane change scenarios such as congested merging and ramp merging, preventing vehicles from getting stuck in such complex lane change scenarios, helping to improve lane change success rates and traffic efficiency.

[0027] In combination with the second aspect, in certain implementations of the second aspect, the method further includes: determining a first time distance between the intelligent driving device and the game target based on the first motion state information and the second motion state information; determining a starting time of a first lane change time period based on the first time distance, and the game target is located behind the intelligent driving device at the starting time.

[0028] In combination with the second aspect, in certain implementations of the second aspect, when there is an obstacle on the target lane and the obstacle is located in front of the game target and the intelligent driving device, the method also includes: determining a second time distance between the intelligent driving device and the obstacle; and determining the end time of the first lane change time period based on the second time distance.

[0029] In combination with the second aspect, in certain implementations of the second aspect, the method further includes: determining a conflict area in which the intelligent driving device and the game target have longitudinal overlap based on the first motion state information and the second motion state information; determining the longitudinal planned speed of the intelligent driving device and the longitudinal predicted speed of the game target based on a first time period when the intelligent driving device travels from the current position to the conflict area; wherein, when the intelligent driving device travels at the longitudinal planned speed and the game target travels at the longitudinal predicted speed, the intelligent driving device overtakes the game target; planning a target trajectory based on the first lane change time period, the longitudinal planned speed and the longitudinal predicted speed; controlling the intelligent driving device to change to the target lane within the first lane change time period, including: controlling the intelligent driving device to change to the target lane and be in front of the game target according to the target trajectory within the first lane change time period.

[0030] In the above technical solution, when planning the longitudinal planning speed of the intelligent technology equipment during the lane changing process, the game relationship with the game target is taken into consideration. Based on the predicted behavior of the game target, the lane changing trajectory of the intelligent driving equipment is adjusted, which helps to improve the safety during the lane changing process and ensure the success rate of lane changing.

[0031] In combination with the second aspect, in certain implementations of the second aspect, the longitudinal planning speed of the intelligent driving device and the longitudinal predicted speed of the game target are determined based on a first time period of the intelligent driving device traveling from the current position to the conflict area, including: determining the longitudinal planning speed and the longitudinal predicted speed based on the first time period, the forward collision risk of the intelligent driving device, and the rearward collision risk of the intelligent driving device.

[0032] In the above technical solution, the longitudinal planning speed of the intelligent technology equipment during the lane changing process is planned in combination with the forward collision risk and the rear collision risk, which helps to reduce the probability of collision with the vehicle in front and the game target during the lane changing process, and can improve the safety of lane changing.

[0033] In combination with the second aspect, in certain implementations of the second aspect, the target trajectory is planned based on the first lane change time period, the longitudinal planned speed, and the longitudinal predicted speed, including: planning the target trajectory based on the occupancy priority of the intelligent driving device for the target lane, the first lane change time period, the longitudinal planned speed, and the longitudinal predicted speed.

[0034] In conjunction with the second aspect, in certain implementations of the second aspect, planning a target trajectory based on the intelligent driving device's occupation priority for the target lane, a first lane change time period, a longitudinal planned speed, and a longitudinal predicted speed includes: determining the planned trajectory of the intelligent driving device based on the first lane change time period and the longitudinal planned speed; determining the predicted trajectory of the game target based on the first lane change time period and the longitudinal predicted speed; determining a conflict position based on the planned trajectory and the predicted trajectory, where the conflict position is a position where a lateral distance between the planned trajectory and the predicted trajectory is less than or equal to a third distance; determining the intelligent driving device's occupation priority for the target lane based on the conflict position, the lateral distance corresponding to the conflict position, a first time required for the intelligent driving device to reach the conflict position, and a second time required for the game target to reach the conflict position; when the intelligent driving device's occupation priority for the target lane is greater than or equal to a first threshold, planning the target trajectory based on a first lateral overlap; or, when the intelligent driving device's occupation priority for the target lane is less than the first threshold, planning the target trajectory based on a second lateral overlap; wherein the first lateral overlap and the second lateral overlap indicate a degree of lateral overlap between the intelligent driving device and the game target at the conflict position, and the first lateral overlap is greater than the second lateral overlap.

[0035] In combination with the second aspect, in certain implementations of the second aspect, the first lane change time period ranges from 2.5 seconds to 7 seconds.

[0036] For beneficial effects that are not described in detail in some implementations of the second aspect, reference can be made to the description in the first aspect and will not be repeated here.

[0037] In a third aspect, a lane change trajectory planning device is provided, comprising an acquisition unit and a processing unit. Specifically, the acquisition unit is configured to: acquire first motion state information of a game target and second motion state information of an intelligent driving device, wherein the game target is located in a target lane of the intelligent driving device and is located between a first position and a second position; wherein the first position is located behind the intelligent driving device and is at a first longitudinal distance from the intelligent driving device, and the second position is located in front of the intelligent driving device and is at a second longitudinal distance from the intelligent driving device; and the processing unit is configured to: plan a target trajectory for the intelligent driving device to change lanes to the target lane based on the first motion state information and the second motion state information, and the intelligent driving device overtakes the game target while driving along the target trajectory.

[0038] In combination with the third aspect, in certain implementations of the third aspect, the processing unit is used to: plan the target trajectory based on the occupancy priority of the intelligent driving device for the target lane, the first motion state information, and the second motion state information.

[0039] In combination with the third aspect, in certain implementations of the third aspect, the processing unit is further used to: the first motion state information includes a planned trajectory of the intelligent driving device, the second motion state information includes a predicted trajectory of the game target, and the processing unit is further used to: determine a conflict position based on the planned trajectory and the predicted trajectory, the conflict position being a position where the lateral distance between the planned trajectory and the predicted trajectory is less than or equal to a third distance; determine the occupation priority of the intelligent driving device for the target lane based on the conflict position, the lateral distance corresponding to the conflict position, the first time required for the intelligent driving device to reach the conflict position, and the second time required for the game target to reach the conflict position; the processing unit is used to: when the occupation priority of the intelligent driving device for the target lane is greater than or equal to a first threshold, plan the target trajectory according to a first lateral overlap degree; or, when the occupation priority of the intelligent driving device for the target lane is less than the first threshold, plan the target trajectory according to a second lateral overlap degree; wherein the first lateral overlap degree and the second lateral overlap degree indicate the degree of lateral overlap between the intelligent driving device and the game target at the conflict position, and the first lateral overlap degree is greater than the second lateral overlap degree.

[0040] In combination with the third aspect, in certain implementations of the third aspect, the processing unit is used to: determine a first time distance between the intelligent driving device and the game target based on the first motion state information and the second motion state information; determine a lane change start time for the intelligent driving device to change from the current lane to the target lane based on the first time distance, and the game target is located behind the intelligent driving device at the lane change start time; plan the target trajectory based on the lane change start time and the lane change end time for the intelligent driving device to change from the current lane to the target lane.

[0041] In combination with the third aspect, in certain implementations of the third aspect, when there is an obstacle on the target lane and the obstacle is located in front of the game target and the intelligent driving device, the processing unit is also used to: determine a second time distance between the intelligent driving device and the obstacle; and determine the lane change termination time based on the second time distance.

[0042] In combination with the third aspect, in certain implementations of the third aspect, the processing unit is used to: determine a conflict area where the intelligent driving device and the game target have longitudinal overlap based on the first motion state information and the second motion state information; determine the longitudinal planned speed of the intelligent driving device and the longitudinal predicted speed of the game target based on a first time period when the intelligent driving device travels from the current position to the conflict area; wherein, when the intelligent driving device travels at the longitudinal planned speed and the game target travels at the longitudinal predicted speed, the intelligent driving device overtakes the game target; and plan the target trajectory based on the longitudinal planned speed and the longitudinal predicted speed.

[0043] In combination with the third aspect, in certain implementations of the third aspect, the processing unit is used to: determine the longitudinal planned speed and the longitudinal predicted speed based on the first time period, the forward collision risk of the intelligent driving device, and the rearward collision risk of the intelligent driving device.

[0044] In a fourth aspect, an autonomous driving device is provided, comprising an acquisition unit and a processing unit. Specifically, the acquisition unit is configured to: acquire first motion state information of a game target and second motion state information of an intelligent driving device, wherein the game target is located in a target lane of the intelligent driving device and is between a first position and a second position; wherein the first position is located behind the intelligent driving device and has a first longitudinal distance from the intelligent driving device, and the second position is located in front of the intelligent driving device and has a second longitudinal distance from the intelligent driving device; and the processing unit is configured to: control the intelligent driving device to change to the target lane and to be located in front of the game target within a first lane change time period based on the first motion state information and the second motion state information.

[0045] In combination with the fourth aspect, in certain implementations of the fourth aspect, the processing unit is further used to: determine a first time distance between the intelligent driving device and the game target based on the first motion state information and the second motion state information; determine a starting time of a first lane change time period based on the first time distance, and the game target is located behind the intelligent driving device at the starting time.

[0046] In combination with the fourth aspect, in certain implementations of the fourth aspect, when there is an obstacle on the target lane and the obstacle is located in front of the game target and the intelligent driving device, the processing unit is further used to: determine a second time distance between the intelligent driving device and the obstacle; and determine the end time of the first lane change time period based on the second time distance.

[0047] In combination with the fourth aspect, in certain implementations of the fourth aspect, the processing unit is further used to: determine a conflict area where the intelligent driving device and the game target have longitudinal overlap based on the first motion state information and the second motion state information; determine the longitudinal planned speed of the intelligent driving device and the longitudinal predicted speed of the game target based on a first time period when the intelligent driving device travels from the current position to the conflict area; wherein, when the intelligent driving device travels at the longitudinal planned speed and the game target travels at the longitudinal predicted speed, the intelligent driving device overtakes the game target; plan the target trajectory based on the first lane change time period, the longitudinal planned speed and the longitudinal predicted speed; and control the intelligent driving device to change to the target lane and be in front of the game target according to the target trajectory within the first lane change time period.

[0048] In combination with the fourth aspect, in certain implementations of the fourth aspect, the processing unit is used to: determine the longitudinal planned speed and the longitudinal predicted speed based on the first time period, the forward collision risk of the intelligent driving device, and the rearward collision risk of the intelligent driving device.

[0049] In combination with the fourth aspect, in certain implementations of the fourth aspect, the target trajectory is planned based on the first lane change time period, the longitudinal planned speed, and the longitudinal predicted speed, including: planning the target trajectory based on the occupancy priority of the target lane by the intelligent driving device, the first lane change time period, the longitudinal planned speed, and the longitudinal predicted speed.

[0050] In conjunction with the fourth aspect, in certain implementations of the fourth aspect, the processing unit is configured to: determine a planned trajectory of the intelligent driving device based on the first lane change time period and the longitudinal planned speed; determine a predicted trajectory of the game target based on the first lane change time period and the longitudinal predicted speed; determine a conflict position based on the planned trajectory and the predicted trajectory, the conflict position being a position where a lateral distance between the planned trajectory and the predicted trajectory is less than or equal to a third distance; determine an occupation priority of the target lane by the intelligent driving device based on the conflict position, the lateral distance corresponding to the conflict position, a first time required for the intelligent driving device to reach the conflict position, and a second time required for the game target to reach the conflict position; when the occupation priority of the target lane by the intelligent driving device is greater than or equal to a first threshold, plan the target trajectory based on a first lateral overlap degree; or, when the occupation priority of the target lane by the intelligent driving device is less than the first threshold, plan the target trajectory based on a second lateral overlap degree; wherein the first lateral overlap degree and the second lateral overlap degree indicate a degree of lateral overlap between the intelligent driving device and the game target at the conflict position, and the first lateral overlap degree is greater than the second lateral overlap degree.

[0051] In combination with the fourth aspect, in certain implementations of the fourth aspect, the first lane change time period ranges from 2.5 seconds to 7 seconds.

[0052] In a fifth aspect, a lane change trajectory planning device is provided, which includes: a processor for executing a computer program stored in the memory, so that the device executes the method in any possible implementation of the first aspect above.

[0053] In combination with the fifth aspect, in certain implementations of the fifth aspect, the lane change trajectory planning device also includes a memory.

[0054] In a sixth aspect, an automatic driving device is provided, which includes: a processor for executing a computer program stored in the memory so that the device performs the method in any possible implementation of the second aspect above.

[0055] In combination with the sixth aspect, in certain implementations of the sixth aspect, the automatic driving device also includes a memory.

[0056] In a seventh aspect, an intelligent driving device is provided, which includes an apparatus as in any possible implementation of the third to fifth aspects.

[0057] In combination with the seventh aspect, in some implementations of the seventh aspect, the intelligent driving device is a vehicle.

[0058] In an eighth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in any possible implementation of the first or second aspect.

[0059] It should be noted that the above-mentioned computer program code may be stored in whole or in part on a storage medium, wherein the storage medium may be packaged together with the processor or separately from the processor.

[0060] In a ninth aspect, a computer-readable medium is provided, wherein the computer-readable medium stores instructions. When the instructions are executed by a processor, the processor implements the method in any possible implementation of the first aspect or the second aspect.

[0061] In a tenth aspect, a chip is provided, which includes a circuit for executing the method in any possible implementation of the first aspect or the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] FIG1 is a functional schematic block diagram of an intelligent driving device provided in an embodiment of the present application;

[0063] FIG2 is a schematic diagram of the architecture of an intelligent driving system provided in an embodiment of the present application;

[0064] FIG3 is a schematic flowchart of a lane change trajectory planning method provided in an embodiment of the present application;

[0065] FIG4 is a schematic diagram of an application scenario of the lane change trajectory planning method provided in an embodiment of the present application;

[0066] FIG5 is a schematic diagram of another application scenario of the lane change trajectory planning method provided in an embodiment of the present application;

[0067] FIG6 is another schematic flowchart of the lane change trajectory planning method provided in an embodiment of the present application;

[0068] FIG7 is a schematic diagram of another application scenario of the lane change trajectory planning method provided in an embodiment of the present application;

[0069] FIG8 is a schematic diagram of another application scenario of the lane change trajectory planning method provided in an embodiment of the present application;

[0070] FIG9 is another schematic flowchart of the lane change trajectory planning method provided in an embodiment of the present application;

[0071] FIG10 is a schematic diagram of another application scenario of the lane change trajectory planning method provided in an embodiment of the present application;

[0072] FIG11 is another schematic flowchart of the lane change trajectory planning method provided in an embodiment of the present application;

[0073] FIG12 is a schematic flowchart of an autonomous driving method provided in an embodiment of the present application;

[0074] FIG13 is a schematic block diagram of a related device provided in an embodiment of the present application;

[0075] FIG14 is another schematic block diagram of a related device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0076] The technical solution in this application will be described below with reference to the accompanying drawings.

[0077] FIG1 is a functional block diagram of an intelligent driving device provided in an embodiment of the present application. As shown in FIG1 , the intelligent driving device 100 may include a perception system 120 and a computing platform 150, wherein the perception system 120 may include several sensors for sensing information about the environment surrounding the intelligent driving device 100. For example, the perception system 120 may include a positioning system, and the positioning system may be a global positioning system (GPS), a Beidou system, or other positioning systems. For another example, the perception system 120 may also include one or more of an inertial measurement unit (IMU), a laser radar, a millimeter-wave radar, an ultrasonic radar, and a camera device.

[0078] Some or all functions of the intelligent driving device 100 can be controlled by a computing platform 150. The computing platform 150 may include processors 151 to 15n. A processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with the ability to read and execute instructions, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the hardware circuits are fixed or reconfigurable. For example, the processor is 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 the processor loading a configuration file to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, the processor may also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc. In addition, the computing platform 150 may also include a memory for storing instructions, and some or all of the processors 151 to 15n may call the instructions in the memory to implement corresponding functions.

[0079] The intelligent driving device 100 may include an advanced driving assistant system (ADAS). ADAS uses multiple sensors on the intelligent driving device (including but not limited to: lidar, millimeter wave radar, camera device, ultrasonic sensor, global positioning system, inertial measurement unit) to obtain information from the surrounding of the intelligent driving device, and analyzes and processes the obtained information to achieve functions such as obstacle perception, target recognition, intelligent driving device positioning, path planning, driver monitoring / reminder, etc., thereby improving the safety, automation and comfort of driving the intelligent driving device.

[0080] From a logical function perspective, ADAS systems generally include three main functional modules: perception module, decision module and execution module. The perception module perceives the surrounding environment of the vehicle body through sensors and inputs corresponding real-time data to the decision-making layer processing center. The perception module mainly includes on-board cameras / ultrasonic radars / millimeter-wave radars / lidars, etc.; the decision module uses computing devices and algorithms to make corresponding decisions based on the information obtained by the perception module; the execution module takes corresponding actions after receiving the decision signal from the decision module, such as driving, changing lanes, steering, braking, warnings, etc.

[0081] ADAS can provide varying degrees of automated driving assistance at different levels of automation (L0-L5), based on artificial intelligence algorithms and information from multiple sensors. These levels are based on the Society of Automotive Engineers (SAE) grading standards. L0 is no automation; L1 is driving assistance; L2 is partial automation; L3 is conditional automation; L4 is high automation; and L5 is full automation. At L1-L3, monitoring and responding to road conditions are performed jointly by the driver and the system, with the driver taking over dynamic driving tasks. At L4 and L5, the driver transitions completely to the role of passenger. Currently, ADAS features include, but are not limited to, adaptive cruise control, automatic emergency braking, automated parking, blind spot monitoring, front cross-traffic alert / braking, rear cross-traffic alert / braking, forward collision warning, lane departure warning, lane keep assist, rear collision warning, traffic sign recognition, traffic jam assistance, and highway assistance. It should be understood that the various functions described above may have specific modes at different autonomous driving levels (L0-L5). The higher the autonomous driving level, the smarter the corresponding mode.

[0082] The intelligent driving devices involved in the embodiments of the present application may include road vehicles, water vehicles, air vehicles, industrial equipment, agricultural equipment, or entertainment equipment, etc. For example, the intelligent driving device can be a vehicle, which is a vehicle in a broad sense, and can be a vehicle (such as a commercial vehicle, a passenger car, a motorcycle, a flying car, a train, etc.), an industrial vehicle (such as a forklift, a trailer, a tractor, etc.), an engineering vehicle (such as an excavator, a bulldozer, a crane, etc.), agricultural equipment (such as a mower, a harvester, etc.), amusement equipment, a toy vehicle, etc. The embodiments of the present application do not specifically limit the type of vehicle. For ease of understanding, the following description is based on the intelligent driving device being a vehicle as an example.

[0083] FIG2 shows a schematic diagram of the intelligent driving system architecture provided by an embodiment of the present application. As shown in FIG2 , the system includes a perception module 210, a planning module 220, a control module 230, and an actuator 240. The perception module 210 may include one or more sensors in the perception system 120 shown in FIG1 , and the planning module 220 and the control module 230 may each include one or more processors in the computing platform 150 shown in FIG1 . The planning module 220 includes a longitudinal joint planning module 221, a transverse and longitudinal joint planning module 222, and a vehicle trajectory optimization module 223.

[0084] Specifically, the perception module 210 obtains environmental information surrounding the ego vehicle, such as road information and the position and speed information of each vehicle in the target lane, and then transmits this environmental information to the planning module 220. Each vehicle in the target lane includes a game target, which can be a vehicle located within a preset range of the ego vehicle and affecting the safety of the ego vehicle's lane change. The longitudinal joint planning module 221 in the planning module 220 determines the forward collision risk, rearward collision risk, and game information of the ego vehicle during the lane change process based on the predicted trajectory of the game target and the planned trajectory of the ego vehicle. Based on the forward and backward collision risks and game information, it then generates a planned longitudinal velocity profile for the ego vehicle and a predicted longitudinal velocity profile for the game target. The longitudinal joint planning module 221 inputs the planned longitudinal speed curve of the ego vehicle and the predicted longitudinal speed curve of the game target into the transverse and longitudinal joint planning module 222. The transverse and longitudinal joint planning module 222 determines the time period in which the ego vehicle can merge based on the planned trajectory with speed information of the ego vehicle and the trajectory with speed information of the game target. Based on the time period in which the ego vehicle can merge and the Euclidean collision avoidance constraints of the ego vehicle and the game target, the optimized planned trajectory of the ego vehicle and the optimized predicted trajectory of the game target are obtained. This allows the ego vehicle and the game target to reasonably overtake the game target and merge into the target lane in a timely manner while minimizing collision. The transverse and longitudinal joint planning module 222 outputs the optimized planned trajectory of the ego vehicle with game information and the optimized predicted trajectory of the game target, which are input into the ego vehicle trajectory optimization module 223. Based on the optimized planned trajectory of the ego vehicle and the optimized predicted trajectory of the game target, the ego vehicle trajectory optimization module 223 determines the avoidance priority and the lateral overlap between the two trajectories. The avoidance priority indicates the priority of the ego vehicle and the game target in occupying the right-of-way of the target lane. The ego vehicle's lane change position and longitudinal speed are then adjusted based on the avoidance priority and the lateral overlap between the two trajectories. Lane change trajectory information, including lane change path and lane change speed information, is determined based on the adjusted lane change position and longitudinal speed. This lane change trajectory information ensures smooth trajectory and precise obstacle avoidance capabilities. The ego vehicle trajectory optimization module 223 transmits the lane change trajectory information to the control module 230. The control module 230 calculates corresponding control variables based on the planned lane change trajectory information and outputs these control variables to the actuator 240. When the actuator 240 executes the control variables, the vehicle is controlled to travel according to the planned lane change path and speed. In some possible implementations, the actuator may include the steering and braking control systems of the intelligent driving device 100.

[0085] It should be understood that the above system is only an example, and in actual applications, the modules in the above system may be added or deleted according to actual needs. For example, the planning module 220 and the control module 230 can be combined into one module.

[0086] The above introduces the intelligent driving system provided by the embodiment of the present application. The detailed working process of the above system is explained below with reference to Figures 3 to 10.

[0087] FIG3 shows a schematic flow chart of a lane change trajectory planning method provided by an embodiment of the present application. The method can be executed by the intelligent driving device 100 shown in FIG1 , or can also be executed by the planning module 220 shown in FIG2 . More specifically, the method 300 can be executed by the longitudinal joint planning module 221. The method 300 may include:

[0088] S301 , determining a conflict area between the ego vehicle and the game target based on the planned trajectory 1 of the ego vehicle and the predicted trajectory 1 of the game target.

[0089] For example, the target can be a vehicle in the target lane that affects the ego vehicle's trajectory. The target lane is the adjacent lane to the ego vehicle's current lane, for example, the left or right lane of the ego vehicle. The target can be located within a preset range of the ego vehicle. For example, the longitudinal distance between the target and the ego vehicle is less than or equal to a preset distance. The preset distance can be 5 meters, 10 meters, or other distances. The preset distance can also be determined based on the target's speed.

[0090] It should be noted that the target can be located to the side and rear of the ego vehicle. Alternatively, if the target is slower than the ego vehicle, the target can be located to the side and slightly ahead of the ego vehicle, meaning that the target is ahead of the ego vehicle by the preset distance. For example, as shown in Figure 4, the ego vehicle is traveling in lane 2 and needs to change to lane 1. Lane 1 currently contains other vehicles 1, 2, and 3. The longitudinal distance between other vehicle 2 and the ego vehicle is less than or equal to the preset distance, so other vehicle 2 is the target.

[0091] It should also be noted that the "longitudinal" involved in the embodiments of the present application can be understood as the direction parallel to the longitudinal symmetry plane of the vehicle in a plane parallel to the ground, that is, the direction of travel of the vehicle; the "lateral" involved in the embodiments of the present application can be understood as the direction perpendicular to the longitudinal symmetry plane of the vehicle, that is, in a plane parallel to the ground, perpendicular to the direction of travel of the vehicle.

[0092] Exemplarily, the planned trajectory 1 of the ego vehicle can be a trajectory from the current road to the target road, planned based on the lane change decision, the ego vehicle's position, and its speed. The predicted trajectory of the game target can be the game target's driving trajectory predicted based on information such as the game target's position, speed, and acceleration. Exemplarily, the predicted trajectory 1 can be calculated by the ego vehicle using radar sensors or other means to measure the game target's position and / or speed information; alternatively, the predicted trajectory 1 can be received via vehicle-to-infrastructure (V2I) communication, vehicle-to-everything (V2X) communication, vehicle-to-vehicle (V2V) communication, or other means.

[0093] The lane change decision can be generated by the vehicle based on navigation information and road information. This road information includes, but is not limited to, lane markings for the vehicle's current road and the guidance rules for one or more lanes within the vehicle's current road. For example, if the vehicle is in the rightmost lane and needs to turn left at the upcoming intersection based on its destination, the vehicle can make a lane change decision based on this road information. This road information can be received by the vehicle via V2I, V2V, or V2X, or collected and / or calculated by the vehicle using radar sensors or cameras.

[0094] The predicted trajectory 1 can be understood as the predicted movement trajectory of the game target within a certain period of time in the future. For example, the "future period of time" can be 10 seconds, or 20 seconds, or other time periods, such as the time between the game target starting and completing the lane change.

[0095] S302: Determine a time window according to the conflict area, and adjust the speeds of the ego vehicle and the game target within the time window.

[0096] In this application, a "trajectory" is a path with speed information. The conflict area in this step can be the area determined by the overlapping portion of the path indicated by planned trajectory 1 and the path indicated by predicted trajectory 1. For example, as shown in Figure 5, path 1 is the path indicated by planned trajectory 1, and path 2 is the path indicated by predicted trajectory 1. The overlapping portion of path 1 and path 2 can be considered the starting position of the conflict area. Furthermore, the time window is the time required for the vehicle to travel from the current position to the starting position of the conflict area.

[0097] In one example, adjusting the speeds of the ego vehicle and the target within the time window includes increasing the ego vehicle's planned speed and decreasing the target's predicted speed, so that the ego vehicle can overtake the target. In another example, adjusting the speeds of the ego vehicle and the target within the time window includes increasing the target's planned speed and decreasing the target's predicted speed, so that the target can overtake the ego vehicle. It is understood that after the target overtakes the ego vehicle, if there is another vehicle behind the target, the ego vehicle will use the vehicle behind the target as the new target.

[0098] The following is an example of the game goal of self-driving car rushing.

[0099] S303: Determine the rear collision risk of the ego vehicle based on the adjusted speed of the ego vehicle and the adjusted speed of the game target.

[0100] After the ego vehicle overtakes the game target and changes to the target lane, the game target is located behind the ego vehicle. At this time, there may be a collision risk between the game target and the ego vehicle. This collision risk is the rearward collision risk of the ego vehicle.

[0101] For example, the rearward collision risk can be determined based on the distance between the ego vehicle and the following vehicle when the ego vehicle changes to the target lane, as well as the speed and acceleration (or deceleration) of the following vehicle. The greater the distance, the lower the speed of the following vehicle, and the greater the deceleration of the following vehicle, the lower the rearward collision risk. For example, if the speed of the following vehicle is less than or equal to the speed of the ego vehicle, and the acceleration of the following vehicle is zero or the deceleration is non-zero, the rearward collision risk is zero.

[0102] S303', determining the forward collision risk of the vehicle according to the adjusted speed of the vehicle.

[0103] For example, when the ego vehicle is traveling in its current lane, it may accelerate during a lane change. If there is another vehicle or obstacle ahead of the ego vehicle in the current lane, there is a potential collision risk between the ego vehicle and the vehicle ahead. Furthermore, after the ego vehicle changes to the target lane in the game of overtaking, there may be another vehicle or obstacle ahead of the ego vehicle, in which case there is a potential collision risk between the ego vehicle and the vehicle ahead. In other words, the forward collision risk includes forward collision risk 1 in the ego vehicle's current lane and forward collision risk 2 after the ego vehicle changes to the target lane.

[0104] In one example, the risk of a forward collision can be determined based on the time to collision (TTC), where a smaller TTC indicates a higher risk of a forward collision. The time to collision is the ratio of the distance between two vehicles to their relative speed.

[0105] In another example, the risk of a forward collision can be determined based on the headway, where the smaller the headway, the higher the risk of a forward collision. The headway is the ratio of the distance between the two vehicles to the vehicle's speed.

[0106] It can be understood that when the vehicle is traveling in the current lane, there is no other vehicle in front of the vehicle, and after the vehicle changes to the target lane, there is still no other vehicle or obstacle in front of the vehicle, then the forward collision risk of the vehicle is 0.

[0107] S304: Determine the longitudinal speed and / or acceleration of the ego vehicle and the game target based on the rear collision risk and the front collision risk.

[0108] In some implementations, the longitudinal speed of the ego vehicle may include the longitudinal speed of the ego vehicle within the time window and the longitudinal speed of the ego vehicle during the lane change process.

[0109] For example, when both the rearward and forward collision risks are zero, the adjusted ego vehicle speed can be used as the longitudinal speed of the ego vehicle, and the adjusted game target speed can be used as the longitudinal speed of the game target. When the rearward and / or forward collision risks are not zero, the longitudinal speeds and / or accelerations of the ego vehicle and the game target are adjusted. For details, refer to Table 1 for adjusting the planned speed and / or acceleration of the ego vehicle and the predicted speed and / or acceleration of the game target.

[0110] Table 1

[0111] It should be understood that Table 1 is merely an example. In actual implementation, when the forward and rearward collision risks are the same as those in Table 1, the planned vehicle speed and acceleration, as well as the game target predicted speed and acceleration, can also be in other forms. Furthermore, in actual implementation, the acceleration and / or jerk can be adjusted based on the degree of forward and / or rearward collision risk.

[0112] In some implementations, S304 may be further refined as follows: preliminarily determining the longitudinal speed and / or acceleration of the ego vehicle and the game target based on the rearward collision risk; adjusting the longitudinal speed and / or acceleration of the ego vehicle and the game target based on the forward collision risk and the actual trajectory of the game target; and outputting the final longitudinal speed and / or acceleration of the ego vehicle and the game target. For example, if the actual speed and / or acceleration of the game target is faster than the speed and / or acceleration of predicted trajectory 1, or if the forward collision risk is high, the longitudinal speed and / or acceleration of the ego vehicle may be reduced based on the preliminarily determined longitudinal speed and / or acceleration of the ego vehicle to increase the probability of the ego vehicle yielding to the game target.

[0113] The lane change trajectory planning method provided in this embodiment of the application first determines the longitudinal planned speed of the ego vehicle and the longitudinal predicted speed of the game target, which helps improve the convergence of the optimization results of the subsequent lane change trajectory. It also reduces the risk of collision with other vehicles before and after the lane change, helping to improve the human-like nature of the planned lane change trajectory.

[0114] FIG6 shows another schematic flow chart of a lane change trajectory planning method provided by an embodiment of the present application. This method can be executed by the intelligent driving device 100 shown in FIG1 , or can also be executed by the planning module 220 shown in FIG2 . More specifically, the method 400 can be executed by the horizontal and vertical joint planning module 222 . The method 400 may include:

[0115] S401: Determine a lane-changing time period based on the planned trajectory 2 of the ego vehicle, the predicted trajectory 2 of the game target, and the predicted trajectory of the preceding vehicle. The lane-changing time period is a time period during which the ego vehicle can change to the target lane.

[0116] For example, planned trajectory 2 of the ego vehicle can be a longitudinal planned trajectory generated based on the longitudinal velocity and acceleration of the ego vehicle determined in S304, and predicted trajectory 2 of the game target can be a longitudinal predicted trajectory generated based on the longitudinal velocity and acceleration of the game target determined in S304. The preceding vehicle is the vehicle located in front of the ego vehicle after the ego vehicle changes to the target lane. The method for obtaining the predicted trajectory of the preceding vehicle can be referred to the description in S301 and will not be repeated here.

[0117] For example, the start and end time of the lane change period are determined based on the time distance between the vehicle and the game target, and between the vehicle and the preceding vehicle. The time distance can be the headway or the TTC. Specifically, the start time of the lane change period is t start The earliest time when the time distance between the vehicle and the game target and the preceding vehicle meets the safety time distance, and the end time of the lane change period is t end The latest time at which the distance between the ego vehicle and both the game target and the preceding vehicle meet the safe distance. In practice, if there are no preceding vehicles or other obstacles ahead of the ego vehicle, the earliest time at which the distance between the ego vehicle and the game target meets the safe distance can be used as the starting time of the lane change period.

[0118] In some implementations, the starting time t start and the end time t end The relationship between t is as follows: end ≥t start +△t min , and t end ≤t start- +△t maxTo prevent the lateral lane change from being too slow or too fast. That is, when there is no vehicle or other obstacle in front of the vehicle, or the distance between the vehicle and the vehicle or other obstacle is too far, the lateral lane change can be adjusted according to △t min and △t max Determine the termination time. min is the minimum time required for lane change, △t max is the maximum time required for lane change. min It can take any value from 2.5 seconds to 3 seconds, △t max It can be 6 seconds or 7 seconds. In actual implementation, △t min and △t max Other values ​​are also possible.

[0119] In actual implementation, other methods can also be used to determine the lane change start and end times. For example, the lane change start and end times can be determined based on the ratio of the distance between the ego vehicle and the game target to the distance between the ego vehicle and the preceding vehicle in the target lane (hereinafter referred to as the gap ratio). More specifically, the earliest time when the gap ratio satisfies the minimum gap ratio is used as the start time t of the lane change period. start , the latest time when the gap ratio meets the minimum gap ratio is taken as the end time of the lane change period t end .

[0120] For example, the starting time of the lane change period is t start and the end time t end The schematic diagram of the lane change path is shown in FIG7 .

[0121] It is understandable that the starting time t start and the end time t end The larger the difference, the slower the trajectory of the lane change part.

[0122] S402 : Determine the planned trajectory 3 of the ego vehicle and the predicted trajectory 3 of the game target according to the lane change time period.

[0123] For example, the ego vehicle's initial lane-changing trajectory is determined based on the lane-changing time period, the ego vehicle's longitudinal speed, and its acceleration. Furthermore, it is determined whether there is a conflict between the ego vehicle's initial lane-changing trajectory and the game target's predicted trajectory 2. If there is no conflict between the ego vehicle's initial lane-changing trajectory and predicted trajectory 2, the ego vehicle's initial lane-changing trajectory becomes planned trajectory 3, and the game target's predicted trajectory 2 becomes predicted trajectory 3. If there is a conflict between the ego vehicle's initial lane-changing trajectory and predicted trajectory 2, the ego vehicle's planned speed is increased based on the initial lane-changing trajectory to obtain planned trajectory 3, while the game target's predicted speed is reduced based on predicted trajectory 2 to obtain predicted trajectory 3. This ensures that when the ego vehicle travels along planned trajectory 3 and the game target travels along predicted trajectory 3, the ego vehicle can overtake the game target without colliding with it.

[0124] For example, Figure 8 shows a schematic diagram of the ego vehicle's initial lane change trajectory and predicted trajectory 2, where the black solid-line box represents the current position of the game target, and the gray solid-line box represents the current position of the ego vehicle. The black dashed-line box represents the predicted position of the game target at different times, and the gray dashed-line box represents the planned position of the ego vehicle at different times. More specifically, a1 and b1 represent the positions of the game target and the ego vehicle at the current moment, respectively; a2 and b2 represent the positions of the game target and the ego vehicle at the next moment, respectively; and so on. an and bn represent the corresponding positions of the game target and the ego vehicle at the same moment (n is a positive integer between 1 and 9). As can be seen from Figure 8 (a), the ego vehicle begins to change lanes at position b5. At this time, the game target is at position a5, far away from the ego vehicle. That is, the game target and the ego vehicle do not overlap in the longitudinal direction at any time. At this point, it can be considered that the ego vehicle's initial lane change trajectory does not conflict with the predicted trajectory 2 of the game target. As can be seen from (b) of Figure 8, the ego vehicle's position b2 overlaps with the game target's position a2 in the longitudinal direction. That is, the distance between the ego vehicle's rear at b2 and the game target's front at a2 is negative. At this time, it can be considered that there is a conflict between the ego vehicle's initial lane change trajectory and the game target's predicted trajectory 2.

[0125] The lane-changing trajectory planning method provided by the embodiments of the present application can determine a reasonable lane-changing time period during the lane-changing process, thereby improving the safety of the lane-changing trajectory. Furthermore, the planned speed of the vehicle is adjusted based on the lane-changing time period, thereby reducing the risk of collision with other vehicles after the lane change, thus helping to improve the human-like nature of the planned lane-changing trajectory.

[0126] FIG9 shows another schematic flow chart of a lane change trajectory planning method provided in an embodiment of the present application. This method can be executed by the intelligent driving device 100 shown in FIG1 , or can also be executed by the planning module 220 shown in FIG2 . More specifically, the method 400 can be executed by the vehicle trajectory optimization module 223. The method 500 may include:

[0127] S501 , determining an avoidance priority based on the planned trajectory 3 of the ego vehicle and the predicted trajectory 3 of the game target, where the avoidance priority indicates the priority of the ego vehicle and the game target in occupying the right of way of the target lane.

[0128] For example, the conflict point of the two trajectories is determined based on the planned trajectory 3 and the predicted trajectory 3. The conflict point is the position where the lateral distance between the two trajectories is equal to the preset distance, and then the avoidance priority is determined according to the moment when the self-vehicle and the other vehicle reach the conflict point.

[0129] For example, the avoidance priority can be determined according to the following formula (1):

[0130] Among them, priority represents the avoidance priority, which can be any value between -1 and 1, Δt1 is the time required for the ego vehicle to reach the conflict point from the current position, Δt2 is the time required for the game target to reach the conflict point from the current position, and t penalty1 The penalty introduced for the vehicle crossing the lane line. penalty1 It can be associated with the lane line type. Different types of lane lines correspond to different values. More specifically, t penalty1 It can take any value between 0 and 2 seconds. As shown in Figure 10, points a and b can be considered conflict points, with the lateral distance between them being ΔL. Point c is where the ego vehicle crosses the lane line. A larger priority value indicates a higher priority for the ego vehicle to occupy the target lane's right-of-way; a smaller priority value indicates a higher priority for the target vehicle to occupy the target lane's right-of-way.

[0131] S502: Optimize the trajectory according to the avoidance priority to obtain a lane-changing trajectory.

[0132] For example, trajectory optimization can be performed based on model predictive control (MPC). During the optimization process, the lateral overlap between the ego vehicle's planned trajectory and the predicted trajectory of the game target is used as an optimization constraint. This lateral overlap indicates the degree of lateral overlap between the ego vehicle and the intelligent driving device at the conflict point. A lateral overlap of 0 indicates no lateral overlap between the ego vehicle and the intelligent driving device, meaning there will be no collision between the ego vehicle and the game target. A non-zero lateral overlap indicates lateral overlap between the ego vehicle and the game target. A larger value indicates greater lateral overlap and a more severe potential collision. Furthermore, if the avoidance priority value is large (e.g., priority greater than or equal to 0), meaning the ego vehicle has a higher priority for occupying the target lane, a certain amount of overlap between the ego vehicle's planned trajectory and the predicted trajectory of the game target can be tolerated. Therefore, the lateral overlap between the ego vehicle and the game target can be set to a non-zero value. If the avoidance priority value is small (e.g., priority less than 0), meaning the game target has a higher priority for occupying the target lane, the lateral overlap between the ego vehicle and the game target can be set to 0.

[0133] It should be noted that the predicted trajectory of the above-mentioned game target can be predicted trajectory 3, or it can also be a new predicted trajectory obtained by updating (or optimizing) the real trajectory of the game target in real time. Specifically, in the process of trajectory optimization based on the avoidance priority, the actual motion state of the game target is monitored in real time to determine the real trajectory of the game target. In each optimization cycle, the predicted trajectory and avoidance priority of the game target can be updated according to the degree of match between the predicted trajectory and the real trajectory of the game target for optimization in the next cycle. For example, if the real trajectory of the game target is more radical than the predicted trajectory (such as a sudden increase in the actual speed), the avoidance priority in the next optimization cycle will be reduced, and the lateral overlap will be reduced accordingly; if the real trajectory of the game target is milder than the predicted trajectory (such as a decrease in the actual speed compared to the predicted), the avoidance priority in the next optimization cycle will be increased, and the lateral overlap will be increased accordingly.

[0134] In actual implementation, when the avoidance priority is high and the actual trajectory of the game target is closely aligned with the predicted trajectory during lane change planning, a more aggressive lane change trajectory can be planned for the ego vehicle (e.g., a shorter lane change period and a faster lane change speed). This allows the ego vehicle to quickly cut into the target lane while the game target avoids the ego vehicle. When the avoidance priority is low, or the actual trajectory of the game target is more aggressive than the predicted trajectory during lane change planning, a more conservative lane change trajectory can be planned for the ego vehicle (e.g., a longer lane change period), or lane change trajectory planning can be stopped. In other words, the ego vehicle can be controlled to abandon the lane change process with the game target as the target to ensure driving safety.

[0135] It is understandable that the planned trajectory 3 output by method 400 is a relatively rough lane-changing trajectory. When the game target is more aggressive (such as faster acceleration), the vehicle may collide with the game target when traveling according to the planned trajectory 3. Alternatively, when the avoidance priority of the vehicle is higher, the vehicle can change lanes with a slower lane-changing trajectory. If the vehicle still travels according to the planned trajectory 3, it may cause poor comfort for the driver and passengers of the vehicle.

[0136] The lane-changing trajectory planning method provided by the embodiment of the present application helps the lane-changing behavior of the ego vehicle to influence the behavior of the game target to a certain extent. By optimizing the lane-changing trajectory of the ego vehicle based on the avoidance priority, when the avoidance priority is high, a larger lateral overlap is adopted to increase the aggressiveness of the ego vehicle during the lane-changing process, which can better alert the game target and make it take avoidance measures in a timely manner; when the avoidance priority is low, a smaller lateral overlap (even zero lateral overlap) is adopted to help reduce the risk of collision with the game target. In summary, optimizing the lane-changing trajectory of the ego vehicle based on the avoidance priority helps to further improve the safety of the lane-changing process and can ensure the feasibility and comfort of the lane-changing trajectory.

[0137] In actual implementation, some or all of methods 300 through 500 may be implemented to obtain the target lane-changing trajectory of the ego vehicle. For example, methods 300 and 400 may be combined to obtain planned trajectory 3 as the target lane-changing trajectory. For another example, methods 300, 400, and 500 may be combined to use the lane-changing trajectory obtained by method 500 as the target lane-changing trajectory.

[0138] FIG11 shows another schematic flow chart of a lane change trajectory planning method provided by an embodiment of the present application. The method can be executed by the intelligent driving device 100 shown in FIG1 or by the planning module 220 shown in FIG2. The method 1100 may include:

[0139] S1110 , obtaining first motion state information of a game target and second motion state information of an intelligent driving device, wherein the game target is located in a target lane of the intelligent driving device and is located between a first position and a second position.

[0140] The first distance is defined as the longitudinal distance between the first position, which is located behind the intelligent driving device, and the second distance is defined as the longitudinal distance between the second position, which is located in front of the intelligent driving device. For example, the first distance can be 5 meters, 10 meters, or another value; the second distance can be 5 meters, 10 meters, or another value. The first and second distances can be the same or different.

[0141] Exemplarily, the intelligent driving device may include the vehicle in the above embodiment, and the game target may include the game target in the above embodiment.

[0142] Exemplarily, the first motion state information may include the position information, speed, acceleration, etc. of the intelligent driving device, or the first motion state information may also include the planned motion trajectory of the intelligent driving device. The second motion state information may include the position information, speed, acceleration, etc. of the game target, or the second motion state information may also include the predicted motion trajectory of the game target. For example, the first motion state information may include the planned trajectory 1 in method 300, and the second motion state information may include the predicted trajectory 1 in method 300; or the first motion state information may include the planned trajectory 2 in method 400, and the second motion state information may include the predicted trajectory 2 in method 400; or the first motion state information may include the planned trajectory 3 in method 400, and the second motion state information may include the predicted trajectory 3 in method 400.

[0143] S1120: Planning a target trajectory for the intelligent driving device to change lanes to a target lane based on the first motion state information and the second motion state information, and achieving a lane-grabbing game goal when the intelligent driving device drives along the target trajectory.

[0144] In some implementations, S1120 can be further refined as follows: determining a conflict area where the intelligent driving device and the game target have longitudinal overlap based on the first motion state information and the second motion state information; determining the longitudinal planned speed of the intelligent driving device and the longitudinal predicted speed of the game target based on a first time period when the intelligent driving device travels from the current position to the conflict area; wherein, when the intelligent driving device travels at the longitudinal planned speed and the game target travels at the longitudinal predicted speed, the intelligent driving device overtakes the game target; and planning the target trajectory based on the longitudinal planned speed and the longitudinal predicted speed.

[0145] Exemplarily, the conflict area may include the conflict area in method 300, the first time period may include the time window in method 300, the longitudinal planned speed may include the longitudinal speed of the vehicle determined in S304, and the longitudinal predicted speed may include the longitudinal speed of the game target determined in S304.

[0146] In some implementations, determining the longitudinal planning speed of the intelligent driving device and the longitudinal predicted speed of the game target based on the first time period can be further refined as: determining the longitudinal planning speed and the longitudinal predicted speed based on the first time period, the forward collision risk of the intelligent driving device, and the rearward collision risk of the intelligent driving device.

[0147] For example, the forward collision risk may include the forward collision risk in method 300, and the rearward collision risk may include the rearward collision risk in method 300. It is understood that in actual implementation, the forward collision risk and / or the rearward collision risk may be zero. For more specific methods of determining the longitudinal planned speed and the longitudinal predicted speed, reference may be made to the description in S304 and will not be repeated here.

[0148] In some implementations, the first motion state information may include the planned trajectory 2 in method 400, and the second motion state information may include the predicted trajectory 2 in method 400, then S1120 may be refined as follows: determining the first time distance between the intelligent driving device and the game target based on the first motion state information and the second motion state information; determining the lane change start time of the intelligent driving device from the current lane to the target lane based on the first time distance, and the game target is located behind the intelligent driving device at the lane change start time; planning the target trajectory based on the lane change start time and the lane change end time.

[0149] For example, the lane change end time is determined based on the lane change start time and a preset time duration, wherein the preset time duration can be any value between a minimum lane change time duration and a maximum lane change time duration.

[0150] For example, the first time distance may be the headway, or may be the TTC, or may be a time distance determined in other ways. The specific implementation of determining the lane change start time according to the first time distance may refer to the description in method 400 and will not be repeated here.

[0151] In some implementations, the first motion state information may include the longitudinal planned speed in the above implementation, and the second motion state information may include the longitudinal predicted speed in the above implementation. Then, the first time distance between the intelligent driving device and the game target is determined based on the first motion state information and the second motion state information, which can be further refined as: the first time distance between the intelligent driving device and the game target is determined based on the longitudinal planned speed and the longitudinal predicted speed.

[0152] In some implementations, when there is an obstacle in the target lane and the obstacle is located in front of the game target and the intelligent driving device, the method further includes: determining a second time distance between the intelligent driving device and the obstacle; and determining the lane change termination time based on the second time distance.

[0153] For example, the obstacle can be a moving obstacle, such as a moving vehicle; alternatively, it can be a static obstacle, such as a mountain, a green belt, a road barrier, or a stationary vehicle. The second time headway can be a headway, a time interval between vehicles, or a time interval determined by other means. The specific implementation of determining the lane change termination time based on the second time headway can be referenced to the description of method 400 and will not be further elaborated here.

[0154] In combination with the above implementation, the target trajectory is planned according to the longitudinal planning speed and the longitudinal predicted speed, which can be refined as follows: according to the longitudinal planning speed and the longitudinal predicted speed, the first time distance between the intelligent driving device and the game target is determined; according to the first time distance, the lane change start time of the intelligent driving device from the current lane to the target lane is determined, and the game target is located behind the intelligent driving device at the lane change start time; according to the longitudinal planning speed, the lane change start time and the lane change end time, the target trajectory is planned. Exemplarily, the target trajectory includes driving at the longitudinal planning speed from the lane change start time to the lane change end time, thereby achieving the trajectory of changing lanes from the current lane to the target lane in a manner that preempts the game target. For a more specific implementation of this example, please refer to the description in method 300 and method 400, which will not be repeated here.

[0155] In some implementations, a target trajectory is planned based on the occupancy priority of the intelligent driving device for the target lane, the first motion state information, and the second motion state information.

[0156] Specifically, the first motion state information may include the planned trajectory 3 (hereinafter referred to as the planned trajectory) in method 400, and the second motion state information may include the predicted trajectory 3 (hereinafter referred to as the predicted trajectory) in method 400, then S1120 may be refined as follows: determining the conflict position according to the planned trajectory and the predicted trajectory, the conflict position being a position where the lateral distance between the planned trajectory and the predicted trajectory is less than or equal to a third distance; determining the occupation priority of the target lane by the intelligent driving device according to the conflict position, the lateral distance corresponding to the conflict position, the first time required for the intelligent driving device to reach the conflict position, and the second time required for the game target to reach the conflict position; when the occupation priority of the target lane by the intelligent driving device is greater than or equal to a first threshold, planning the target trajectory according to the first lateral overlap degree; or, when the occupation priority of the target lane by the intelligent driving device is less than the first threshold, planning the target trajectory according to the second lateral overlap degree; wherein the first lateral overlap degree and the second lateral overlap degree indicate the degree of lateral overlap between the intelligent driving device and the game target at the conflict position, and the first lateral overlap degree is greater than the second lateral overlap degree.

[0157] Exemplarily, the above-mentioned conflict position may include the conflict point in method 500, and the third distance may be 1 meter, or 1.5 meters, or other values. The occupation priority of the target lane of the intelligent driving device may include the avoidance priority in the above-mentioned embodiment, and the first threshold value may be 0, or other values. The second lateral overlap may be zero, and the first lateral overlap may be a certain value greater than zero. The specific value may be determined according to the size of the occupation priority of the target lane of the intelligent driving device. For example, the greater the occupation priority of the target lane of the intelligent driving device, the greater the first lateral overlap may be. The specific implementation of planning the target trajectory according to the lateral overlap can refer to the description in method 500 and will not be repeated here.

[0158] In combination with the above implementation method, the first motion state information may include the longitudinal planned speed in the above implementation method, and the second motion state information may include the longitudinal predicted speed in the above implementation method. Then, according to the occupation priority of the target lane of the intelligent driving device, the first motion state information and the second motion state information, the target trajectory is planned. It can be: according to the occupation priority of the target lane of the intelligent driving device, the longitudinal planned speed and the longitudinal predicted speed, the target trajectory is planned. Specifically, a target trajectory is planned based on the intelligent driving device's occupation priority for the target lane, the longitudinal planned speed, and the longitudinal predicted speed, including: determining a lane change start time and a lane change end time based on the longitudinal planned speed and the longitudinal predicted speed, and determining the planned trajectory and the predicted trajectory based on the lane change start time and the lane change end time; determining a conflict position based on the planned trajectory and the predicted trajectory, where the conflict position is a position where a lateral distance between the planned trajectory and the predicted trajectory is less than or equal to a third distance; determining the intelligent driving device's occupation priority for the target lane based on the conflict position, the lateral distance corresponding to the conflict position, a first time required for the intelligent driving device to reach the conflict position, and a second time required for the game target to reach the conflict position; when the intelligent driving device's occupation priority for the target lane is greater than or equal to a first threshold, planning the target trajectory based on a first lateral overlap; or, when the intelligent driving device's occupation priority for the target lane is less than the first threshold, planning the target trajectory based on a second lateral overlap; wherein the first lateral overlap and the second lateral overlap indicate a degree of lateral overlap between the intelligent driving device and the game target at the conflict position, and the first lateral overlap is greater than the second lateral overlap. The specific implementation of determining the lane change start time and lane change end time, and determining the planned trajectory and predicted trajectory can be referred to the description in method 400 and will not be repeated here.

[0159] It should be understood that, in actual implementation, the lateral overlap may increase as the occupancy priority of the intelligent driving device for the target lane increases.

[0160] In some implementations, when the intelligent driving device's priority for occupying the target lane is greater than or equal to a second threshold, the target trajectory is planned. When the intelligent driving device's priority for occupying the target lane is less than the second threshold, the intelligent driving device abandons the lane-grabbing game objective. The second threshold can be less than or equal to the first threshold, for example, -0.5, or other values.

[0161] In some implementations, the method further includes planning a target trajectory based on the degree of match between the predicted trajectory of the game target and the actual trajectory of the game target. When the predicted trajectory differs significantly from the actual trajectory of the game target, the predicted trajectory of the game target and the occupancy priority of the intelligent driving device for the target lane are corrected based on the actual trajectory of the game target. Furthermore, the target trajectory is planned based on the corrected occupancy priority. For more specific methods of correcting the occupancy priority and the predicted trajectory of the game target, please refer to the description of method 500 and will not be repeated here.

[0162] The lane change trajectory planning method provided in the embodiment of the present application can improve the merging capability of intelligent driving equipment in congested merging and ramp merging scenarios in an autonomous driving scenario, thereby improving the merging success rate and traffic efficiency.

[0163] FIG12 shows a schematic flow chart of an autonomous driving method provided by an embodiment of the present application. The method may be executed by the intelligent driving device 100 shown in FIG1 , or may also be executed by the planning module 220 shown in FIG2 . The method 1200 may include:

[0164] S1210: Acquire first motion state information of a game target and second motion state information of an intelligent driving device, wherein the game target is located in a target lane of the intelligent driving device and is located between a first position and a second position.

[0165] The first position is located behind the intelligent driving device and the longitudinal distance between the first position and the intelligent driving device is a first distance, and the second position is located in front of the intelligent driving device and the longitudinal distance between the first position and the intelligent driving device is a second distance.

[0166] For example, the first distance may be 5 meters, or 10 meters, or other values; the second distance may be 5 meters, or 10 meters, or other values. The first distance and the second distance may be the same or different.

[0167] Exemplarily, the intelligent driving device may include the vehicle in the above embodiment, and the game target may include the game target in the above embodiment.

[0168] Exemplarily, the first motion state information may include the position information, speed, acceleration, etc. of the intelligent driving device, or the first motion state information may also include the planned motion trajectory of the intelligent driving device. The second motion state information may include the position information, speed, acceleration, etc. of the game target, or the second motion state information may also include the predicted motion trajectory of the game target. For example, the first motion state information may include the planned trajectory 1 in method 300, and the second motion state information may include the predicted trajectory 1 in method 300; or the first motion state information may include the planned trajectory 2 in method 400, and the second motion state information may include the predicted trajectory 2 in method 400; or the first motion state information may include the planned trajectory 3 in method 400, and the second motion state information may include the predicted trajectory 3 in method 400.

[0169] S1220: Control the intelligent driving device to change to the target lane and be located in front of the game target within the first lane change time period according to the first motion state information and the second motion state information.

[0170] For example, the start time of the first lane changing time period may be the lane changing start time in method 1100 , and the end time of the first lane changing time period may be the lane changing end time in method 1100 .

[0171] For example, S1220 may be further refined as follows: determining a target trajectory based on the first motion state information and the second motion state information, and controlling the intelligent driving device to change to a target lane according to the target trajectory within a first lane change time period, and to be positioned in front of the game target. The specific implementation of determining the target trajectory and / or the first lane change time period can be found in the description of method 1100 and is not further elaborated here.

[0172] The autonomous driving method provided by the embodiments of this application allows the intelligent driving device to preempt the target lane in complex lane-changing scenarios, such as merging into congested traffic or merging onto ramps, thereby preventing the intelligent driving device from becoming stuck in these complex lane-changing scenarios and helping to improve lane-changing success rates and traffic efficiency. Furthermore, the autonomous driving method can enhance the human-like and intelligent nature of the intelligent driving device.

[0173] In the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between the various embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0174] The lane change trajectory planning method and autonomous driving method provided by the embodiments of the present application are described in detail above with reference to Figures 1 to 12 . The apparatus provided by the embodiments of the present application will be described in detail below with reference to Figures 13 and 14 . It should be understood that the description of the apparatus embodiment corresponds to the description of the method embodiment. Therefore, any details not described in detail can be referred to the method embodiment above, and for the sake of brevity, they will not be repeated here.

[0175] Figure 13 shows a schematic block diagram of an apparatus 2000 provided in an embodiment of the present application. The apparatus 2000 may include units for executing methods 300, 400, 500, 1100, and 1200. Furthermore, the units in the apparatus 2000 implement the corresponding processes of the above-mentioned method embodiments. The apparatus 2000 includes an acquisition unit 2010, which can be used to implement corresponding data acquisition or transceiver functions. The apparatus 2000 also includes a processing unit 2020, which can be used to implement corresponding processing functions.

[0176] Optionally, the device 2000 also includes a storage unit, which can be used to store instructions and / or data. The processing unit 2020 can read the instructions and / or data in the storage unit so that the device implements the relevant actions in the aforementioned method embodiments.

[0177] It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0178] It should also be understood that the apparatus 2000 herein is embodied in the form of functional units. The term "module" or "unit" herein may refer to an application-specific ASIC, electronic circuitry, a processor (e.g., a shared processor, a dedicated processor, or a group of processors, etc.) and memory for executing one or more software or firmware programs, combined logic circuitry, and / or other suitable components that support the described functionality.

[0179] The apparatuses of each of the above-described solutions have the functionality to implement the corresponding steps performed by the computing platform 150 in the above-described methods. These functions can be implemented in hardware, or by hardware executing corresponding software implementations. The hardware or software includes one or more modules corresponding to the above-described functions; for example, the acquisition unit 2010 can be replaced by a transceiver, and other units, such as the processing unit, can be replaced by a processor to perform the relevant processing operations in each method embodiment.

[0180] Exemplarily, the acquisition unit 2010 and the processing unit 2020 may be provided in the intelligent driving device 100 shown in FIG1 , or may also be provided in the system shown in FIG2 . More specifically, the acquisition unit 2010 and the processing unit 2020 may be provided in the planning module 220 . Exemplarily, the operations performed by the acquisition unit 2010 and the processing unit 2020 may be performed by a single processor, or by different processors. In a specific implementation, the one or more processors may be provided in the intelligent driving device 100 shown in FIG1 ; alternatively, the apparatus 2000 may be provided in a chip in the intelligent driving device 100 .

[0181] In a specific implementation process, the various units in the above apparatus may be fully or partially integrated together, or may also be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-a-chip (SoC).

[0182] Figure 14 is another schematic block diagram of the device provided by an embodiment of the present application. The device 2100 shown in Figure 14 may include: a processor 2110, a transceiver 2120, and a memory 2130. The device 2100 can be used to implement the above-mentioned lane change trajectory planning method and / or automatic driving method, wherein the processor 2110, the transceiver 2120, and the memory 2130 are connected through an internal connection path, the memory 2130 is used to store instructions, and the processor 2110 is used to execute the instructions stored in the memory 2130 to implement the methods in the above-mentioned embodiments. Optionally, the memory 2130 can be coupled to the processor 2110 through an interface, or can be integrated with the processor 2110.

[0183] It should be noted that the transceiver 2120 may include but is not limited to a transceiver device such as an input / output interface to implement communication between the device 2100 and other devices or a communication network.

[0184] Memory 2130 may be a volatile memory and / or a non-volatile memory. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM). For example, RAM may be used as an external cache. By way of example and not limitation, RAM includes the following forms: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0185] The transceiver 2120 uses a transceiver device such as but not limited to a transceiver to implement communication between the device 2100 and other devices or communication networks to receive / send data / information used to implement the methods in the above embodiments.

[0186] An embodiment of the present application further provides an intelligent driving device, which includes the device 2000 or the device 2100 in the above embodiment.

[0187] An embodiment of the present application further provides a computer program product, which includes computer program code. When the computer program code runs on a computer, the computer implements the methods in the above embodiments of the present application.

[0188] An embodiment of the present application further provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed on a computer, the computer implements the methods in the above embodiments of the present application.

[0189] An embodiment of the present application also provides a chip, including a circuit, for executing the methods in the above embodiments of the present application.

[0190] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0191] In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is a kind of association relationship that describes associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In this application, "at least one" refers to one or more, and "more than one" refers to two or more. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0192] In the embodiments of this application, prefixes such as "first" and "second" are used only to distinguish different description objects and have no limiting effect on the position, order, priority, quantity, or content of the described objects. The use of prefixes such as ordinal numbers in the embodiments of this application to distinguish description objects does not constitute a limitation on the described objects. For a statement of the described objects, please refer to the description in the context of the claims or embodiments, and the use of such prefixes should not constitute an unnecessary limitation.

[0193] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0194] In the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between the various embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0195] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0196] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0197] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A lane-changing trajectory planning method, characterized in that: include: Acquire first motion state information of a game target and second motion state information of an intelligent driving device, wherein the game target is located in a target lane of the intelligent driving device and is between a first position and a second position; The first position is located behind the intelligent driving device and the longitudinal distance between the first position and the intelligent driving device is a first distance, and the second position is located in front of the intelligent driving device and the longitudinal distance between the second position and the intelligent driving device is a second distance; A target trajectory of the intelligent driving device for changing lanes to the target lane is planned according to the first motion state information and the second motion state information, and the intelligent driving device rushes to achieve the game target when driving along the target trajectory.

2. The method according to claim 1, characterized in that The planning, based on the first motion state information and the second motion state information, of a target trajectory for the intelligent driving device to change lanes to the target lane includes: The target trajectory is planned according to the occupancy priority of the intelligent driving device for the target lane, the first motion state information, and the second motion state information.

3. The method according to claim 2, characterized in that The first motion state information includes a planned trajectory of the intelligent driving device, and the second motion state information includes a predicted trajectory of the game target. The method further includes: determining a conflict position according to the planned trajectory and the predicted trajectory, the conflict position being a position where a lateral distance between the planned trajectory and the predicted trajectory is less than or equal to a third distance; Determining an occupation priority of the target lane by the intelligent driving device according to the conflict position, a lateral distance corresponding to the conflict position, a first time required for the intelligent driving device to reach the conflict position, and a second time required for the game target to reach the conflict position; The planning of the target trajectory includes: When the occupancy priority of the intelligent driving device for the target lane is greater than or equal to a first threshold, planning the target trajectory according to the first lateral overlap; or When the occupation priority of the intelligent driving device for the target lane is less than the first threshold, planning the target trajectory according to the second lateral overlap; The first lateral overlap degree and the second lateral overlap degree indicate the degree of lateral overlap between the intelligent driving device and the game target at the conflict position, and the first lateral overlap degree is greater than the second lateral overlap degree.

4. The method according to any one of claims 1 to 3, characterized in that The planning, based on the first motion state information and the second motion state information, of a target trajectory for the intelligent driving device to change lanes to the target lane includes: Determining a first time distance between the intelligent driving device and the game target according to the first motion state information and the second motion state information; determining, based on the first time interval, a lane change start time for the intelligent driving device to change from the current lane to the target lane, wherein the game target is located behind the intelligent driving device at the lane change start time; The target trajectory is planned according to the lane change start time and the lane change end time when the intelligent driving device changes from the current lane to the target lane.

5. The method according to claim 4, characterized in that When there is an obstacle on the target lane, and the obstacle is located in front of the game target and the intelligent driving device, the method further includes: Determining a second time distance between the intelligent driving device and the obstacle; The lane change termination time is determined according to the second time interval.

6. The method according to any one of claims 1 to 5, characterized in that The planning, based on the first motion state information and the second motion state information, of a target trajectory for the intelligent driving device to change lanes to the target lane includes: Determining, based on the first motion state information and the second motion state information, a conflict area where the intelligent driving device and the game target overlap vertically; Determining a longitudinal planning speed of the intelligent driving device and a longitudinal predicted speed of the game target based on a first time period of the intelligent driving device traveling from a current position to the conflict area; Wherein, when the intelligent driving device is traveling according to the longitudinal planned speed and the game target is traveling according to the longitudinal predicted speed, the intelligent driving device rushes to drive the game target; The target trajectory is planned according to the longitudinal planned speed and the longitudinal predicted speed.

7. The method according to claim 6, characterized in that The determining, based on a first time period of the intelligent driving device traveling from a current position to the conflict area, a longitudinal planning speed of the intelligent driving device and a longitudinal predicted speed of the game target includes: The longitudinal planned speed and the longitudinal predicted speed are determined according to the first time period, the forward collision risk of the intelligent driving device, and the rearward collision risk of the intelligent driving device.

8. An automatic driving method, characterized in that: include: Acquire first motion state information of a game target and second motion state information of an intelligent driving device, wherein the game target is located in a target lane of the intelligent driving device and is between a first position and a second position; The first position is located behind the intelligent driving device and the longitudinal distance between the first position and the intelligent driving device is a first distance, and the second position is located in front of the intelligent driving device and the longitudinal distance between the second position and the intelligent driving device is a second distance; According to the first motion state information and the second motion state information, the intelligent driving device is controlled to change to the target lane and be located in front of the game target within a first lane change time period.

9. The method according to claim 8, characterized in that The method further comprises: Determining a first time distance between the intelligent driving device and the game target according to the first motion state information and the second motion state information; A starting time of the first lane change time period is determined according to the first time distance, and the game target is located behind the intelligent driving device at the starting time.

10. The method according to claim 9, characterized in that When there is an obstacle on the target lane, and the obstacle is located in front of the game target and the intelligent driving device, the method further includes: Determining a second time distance between the intelligent driving device and the obstacle; An end time of the first lane-changing time period is determined according to the second time interval.

11. The method according to any one of claims 8 to 10, characterized in that The method further comprises: Determining, based on the first motion state information and the second motion state information, a conflict area where the intelligent driving device and the game target overlap vertically; Determining a longitudinal planning speed of the intelligent driving device and a longitudinal predicted speed of the game target based on a first time period of the intelligent driving device traveling from a current position to the conflict area; Wherein, when the intelligent driving device is traveling according to the longitudinal planned speed and the game target is traveling according to the longitudinal predicted speed, the intelligent driving device rushes to drive the game target; planning a target trajectory according to the first lane change time period, the longitudinal planned speed, and the longitudinal predicted speed; The controlling the intelligent driving device to change to the target lane within the first lane-changing time period includes: The intelligent driving device is controlled to change to the target lane and be located in front of the game target according to the target trajectory within the first lane change time period.

12. The method according to claim 11, characterized in that The determining, based on a first time period of the intelligent driving device traveling from a current position to the conflict area, a longitudinal planning speed of the intelligent driving device and a longitudinal predicted speed of the game target includes: The longitudinal planned speed and the longitudinal predicted speed are determined according to the first time period, the forward collision risk of the intelligent driving device, and the rearward collision risk of the intelligent driving device.

13. The method according to claim 11 or 12, characterized in that The planning of the target trajectory according to the first lane change time period, the longitudinal planned speed, and the longitudinal predicted speed includes: The target trajectory is planned according to the occupancy priority of the intelligent driving device for the target lane, the first lane change time period, the longitudinal planned speed, and the longitudinal predicted speed.

14. The method according to claim 13, characterized in that The planning of the target trajectory according to the occupancy priority of the target lane by the intelligent driving device, the first lane change time period, the longitudinal planned speed, and the longitudinal predicted speed includes: determining a planned trajectory of the intelligent driving device according to the first lane change time period and the longitudinal planned speed; determining a predicted trajectory of the game target based on the first lane change time period and the predicted longitudinal speed; determining a conflict position according to the planned trajectory and the predicted trajectory, the conflict position being a position where a lateral distance between the planned trajectory and the predicted trajectory is less than or equal to a third distance; Determining an occupation priority of the target lane by the intelligent driving device according to the conflict position, a lateral distance corresponding to the conflict position, a first time required for the intelligent driving device to reach the conflict position, and a second time required for the game target to reach the conflict position; When the occupancy priority of the intelligent driving device for the target lane is greater than or equal to a first threshold, planning the target trajectory according to the first lateral overlap; or When the occupation priority of the intelligent driving device for the target lane is less than the first threshold, planning the target trajectory according to the second lateral overlap; The first lateral overlap degree and the second lateral overlap degree indicate the degree of lateral overlap between the intelligent driving device and the game target at the conflict position, and the first lateral overlap degree is greater than the second lateral overlap degree.

15. The method according to any one of claims 8 to 14, characterized in that The first lane-changing time period ranges from 2.5 seconds to 7 seconds.

16. A lane-changing trajectory planning device, characterized in that: include: an acquiring unit, configured to acquire first motion state information of a game target and second motion state information of an intelligent driving device, wherein the game target is located in a target lane of the intelligent driving device and is located between a first position and a second position; The first position is located behind the intelligent driving device and the longitudinal distance between the first position and the intelligent driving device is a first distance, and the second position is located in front of the intelligent driving device and the longitudinal distance between the second position and the intelligent driving device is a second distance; A processing unit is configured to plan a target trajectory for the intelligent driving device to change lanes to the target lane based on the first motion state information and the second motion state information, wherein the intelligent driving device rushes to achieve the game target when driving along the target trajectory.

17. The device according to claim 16, characterized in that The processing unit is used for: The target trajectory is planned according to the occupancy priority of the intelligent driving device for the target lane, the first motion state information, and the second motion state information.

18. The device according to claim 17, characterized in that The first motion state information includes a planned trajectory of the intelligent driving device, the second motion state information includes a predicted trajectory of the game target, and the processing unit is further configured to: determining a conflict position according to the planned trajectory and the predicted trajectory, the conflict position being a position where a lateral distance between the planned trajectory and the predicted trajectory is less than or equal to a third distance; Determining an occupation priority of the target lane by the intelligent driving device according to the conflict position, a lateral distance corresponding to the conflict position, a first time required for the intelligent driving device to reach the conflict position, and a second time required for the game target to reach the conflict position; The planning of the target trajectory includes: When the occupancy priority of the intelligent driving device for the target lane is greater than or equal to a first threshold, planning the target trajectory according to the first lateral overlap; or When the occupation priority of the intelligent driving device for the target lane is less than the first threshold, planning the target trajectory according to the second lateral overlap; The first lateral overlap degree and the second lateral overlap degree indicate the degree of lateral overlap between the intelligent driving device and the game target at the conflict position, and the first lateral overlap degree is greater than the second lateral overlap degree.

19. The device according to any one of claims 16 to 18, characterized in that The processing unit is used for: determining a first time interval between the intelligent driving device and the game target based on the first motion state information and the second motion state information; determining, based on the first time interval, a lane change start time for the intelligent driving device to change from the current lane to the target lane, wherein the game target is located behind the intelligent driving device at the lane change start time; The target trajectory is planned according to the lane change start time and the lane change end time when the intelligent driving device changes from the current lane to the target lane.

20. The device according to claim 19, characterized in that When there is an obstacle on the target lane and the obstacle is located in front of the game target and the intelligent driving device, the processing unit is further configured to: Determining a second time distance between the intelligent driving device and the obstacle; The lane change termination time is determined according to the second time interval.

21. The device according to any one of claims 16 to 20, characterized in that The processing unit is used for: Determining, based on the first motion state information and the second motion state information, a conflict area where the intelligent driving device and the game target overlap vertically; Determining a longitudinal planning speed of the intelligent driving device and a longitudinal predicted speed of the game target based on a first time period of the intelligent driving device traveling from a current position to the conflict area; Wherein, when the intelligent driving device is traveling according to the longitudinal planned speed and the game target is traveling according to the longitudinal predicted speed, the intelligent driving device rushes to drive the game target; The target trajectory is planned according to the longitudinal planned speed and the longitudinal predicted speed.

22. The device according to claim 21, characterized in that The processing unit is used for: The longitudinal planned speed and the longitudinal predicted speed are determined according to the first time period, the forward collision risk of the intelligent driving device, and the rearward collision risk of the intelligent driving device.

23. An automatic driving device, characterized in that: include: an acquiring unit, configured to acquire first motion state information of a game target and second motion state information of an intelligent driving device, wherein the game target is located in a target lane of the intelligent driving device and is located between a first position and a second position; The first position is located behind the intelligent driving device and the longitudinal distance between the first position and the intelligent driving device is a first distance, and the second position is located in front of the intelligent driving device and the longitudinal distance between the second position and the intelligent driving device is a second distance; A processing unit is used to: control the intelligent driving device to change to the target lane and be located in front of the game target within a first lane change time period based on the first motion state information and the second motion state information.

24. The device according to claim 23, characterized in that The processing unit is further configured to: Determining a first time distance between the intelligent driving device and the game target according to the first motion state information and the second motion state information; A starting time of the first lane change time period is determined according to the first time distance, and the game target is located behind the intelligent driving device at the starting time.

25. The device according to claim 24, characterized in that When there is an obstacle on the target lane and the obstacle is located in front of the game target and the intelligent driving device, the processing unit is further configured to: Determining a second time distance between the intelligent driving device and the obstacle; An end time of the first lane-changing time period is determined according to the second time interval.

26. The device according to any one of claims 23 to 25, characterized in that The processing unit is further configured to: Determining, based on the first motion state information and the second motion state information, a conflict area where the intelligent driving device and the game target overlap vertically; Determining a longitudinal planning speed of the intelligent driving device and a longitudinal predicted speed of the game target based on a first time period of the intelligent driving device traveling from a current position to the conflict area; Wherein, when the intelligent driving device is traveling according to the longitudinal planned speed and the game target is traveling according to the longitudinal predicted speed, the intelligent driving device rushes to drive the game target; planning a target trajectory according to the first lane change time period, the longitudinal planned speed, and the longitudinal predicted speed; The intelligent driving device is controlled to change to the target lane and be located in front of the game target according to the target trajectory within the first lane change time period.

27. The device according to claim 26, characterized in that The processing unit is used for: The longitudinal planned speed and the longitudinal predicted speed are determined according to the first time period, the forward collision risk of the intelligent driving device, and the rearward collision risk of the intelligent driving device.

28. The device according to claim 26 or 27, characterized in that The planning of the target trajectory according to the first lane change time period, the longitudinal planned speed, and the longitudinal predicted speed includes: The target trajectory is planned according to the occupancy priority of the intelligent driving device for the target lane, the first lane change time period, the longitudinal planned speed, and the longitudinal predicted speed.

29. The device according to claim 28, characterized in that The processing unit is used for: determining a planned trajectory of the intelligent driving device according to the first lane change time period and the longitudinal planned speed; determining a predicted trajectory of the game target based on the first lane change time period and the predicted longitudinal speed; determining a conflict position according to the planned trajectory and the predicted trajectory, the conflict position being a position where a lateral distance between the planned trajectory and the predicted trajectory is less than or equal to a third distance; Determining an occupation priority of the target lane by the intelligent driving device according to the conflict position, a lateral distance corresponding to the conflict position, a first time required for the intelligent driving device to reach the conflict position, and a second time required for the game target to reach the conflict position; When the occupancy priority of the intelligent driving device for the target lane is greater than or equal to a first threshold, planning the target trajectory according to a first lateral overlap degree; or, When the occupation priority of the intelligent driving device for the target lane is less than the first threshold, planning the target trajectory according to the second lateral overlap; The first lateral overlap degree and the second lateral overlap degree indicate the degree of lateral overlap between the intelligent driving device and the game target at the conflict position, and the first lateral overlap degree is greater than the second lateral overlap degree.

30. The device according to any one of claims 23 to 29, characterized in that The first lane-changing time period ranges from 2.5 seconds to 7 seconds.

31. A lane-changing trajectory planning device, characterized in that: include: A processor, configured to execute a computer program stored in a memory, so that the apparatus performs the method according to any one of claims 1 to 7.

32. An automatic driving device, characterized in that: include: A processor, configured to execute a computer program stored in the memory, so that the apparatus performs the method according to any one of claims 8 to 15.

33. The device according to claim 31 or 32, characterized in that The apparatus further comprises the memory.

34. An intelligent driving device, characterized in that: Comprising the apparatus of any one of claims 16 to 33.

35. A computer-readable storage medium, characterized in that Instructions are stored thereon, and when the instructions are executed by a processor, the method according to any one of claims 1 to 7 or the method according to any one of claims 8 to 15 is implemented.

36. A computer program product, characterized in that The computer program product comprises: a computer program code, and when the computer program code is executed, the method according to any one of claims 1 to 7 or the method according to any one of claims 8 to 15 is implemented.

37. A chip, characterized in that: The chip comprises a circuit configured to execute the method according to any one of claims 1 to 7 or the method according to any one of claims 8 to 15.

Images