A motion planning method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a motion planning method, device, electronic equipment and storage medium, wherein the method comprises: acquiring a target image collected by a target vehicle in a driving process; determining a lateral position variance corresponding to an obstacle based on position information of the obstacle in the target image, the lateral position variance being used to represent a degree of deviation between a current lateral position of the obstacle and a position mean value; and adjusting a preset driving path of the target vehicle and a driving speed of each preset driving path point of the target vehicle in the driving process according to the preset driving path based on the lateral position variance, to obtain an adjusted motion planning result. The present disclosure can realize the related adjustment of the preset driving path and the driving speed of the preset driving path point based on the lateral position variance, so that the target vehicle can pass through the obstacle through a more gentle motion trajectory, thereby improving the passability, safety and comfort in the driving process of the vehicle.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of autonomous driving, in particular, to a motion planning method and device, an electronic device and a storage medium. BACKGROUND

[0002] Motion planning is one of the important technologies in the field of autonomous driving, and how to plan a safe and comfortable motion trajectory has become an urgent problem. Motion planning can be divided into path planning and speed planning. Path planning needs to determine the lateral position and vehicle heading angle of the vehicle at each longitudinal position (corresponding to the direction of vehicle travel); speed planning needs to determine the speed, acceleration and jerk of the vehicle at each longitudinal position, and the combination of the two can obtain a motion trajectory.

[0003] In the process of motion planning, obstacle avoidance operation is often needed. In order to facilitate road motion planning, in related technologies, either avoid obstacles in the lateral direction, that is, move away from obstacles in the lateral direction and pass through at normal speed in the longitudinal direction, or avoid obstacles in the longitudinal direction, that is, slow down and stop behind the obstacle in the longitudinal direction, and do not consider obstacles in the lateral direction.

[0004] However, only avoiding obstacles in the longitudinal direction will cause the host vehicle to stop and not move forward, reducing the passability of autonomous driving; only avoiding obstacles in the lateral direction will cause the vehicle to pass by the obstacle at too high a speed, even with an emergency brake and takeover, reducing the safety and comfort of autonomous driving. SUMMARY

[0005] The embodiments of the present disclosure at least provide a motion planning method, device, electronic device and storage medium.

[0006] In a first aspect, the embodiments of the present disclosure provide a motion planning method, comprising:

[0007] acquiring a target image collected by a target vehicle in a driving process;

[0008] determining a lateral position variance corresponding to an obstacle based on position information of the obstacle in the target image, the lateral position variance being used to represent a degree of deviation between a current lateral position of the obstacle and a position mean value;

[0009] adjusting a preset driving path of the target vehicle and a driving speed of each preset driving path point in a driving process of the target vehicle according to the preset driving path based on the lateral position variance, to obtain an adjusted motion planning result.

[0010] Here, in a case where a target image collected by a target vehicle is acquired, a lateral position variance corresponding to an obstacle can be determined based on obstacle analysis in the target image, the lateral position variance can represent a degree of deviation of the vehicle from the obstacle, and relevant adjustment of a driving speed on a preset driving path and preset driving path points thereof can be implemented based on the lateral position variance, so that the target vehicle can pass through the obstacle through a more gentle motion trajectory, rather than directly adopting a lateral or longitudinal obstacle avoidance manner, thereby improving passability, safety, and comfort during vehicle driving.

[0011] In a possible implementation, the determining of the lateral position variance corresponding to the obstacle based on the position information of the obstacle in the target image comprises:

[0012] determining a longitudinal distance between the target vehicle and the obstacle based on the position information of the obstacle in the target image;

[0013] determining the lateral position variance corresponding to the obstacle based on the longitudinal distance and type information of the obstacle.

[0014] Here, the longitudinal distance between the target vehicle and the obstacle can be determined based on the position information of the obstacle in the target image, the longitudinal distance can determine how far the target vehicle is from the obstacle, and the greater the distance, the greater the lateral position variance of the obstacle, and vice versa, in addition, the type of the obstacle also affects the lateral position variance, and the determined lateral position variance is accurate enough to well reflect the space that needs to be avoided.

[0015] In a possible implementation, the adjusted motion planning result comprises an adjusted driving path, and the adjusting of the preset driving path of the target vehicle based on the lateral position variance comprises:

[0016] determining a relaxation factor for lateral obstacle avoidance based on the lateral position variance;

[0017] adjusting the preset driving path based on the relaxation factor to obtain the adjusted driving path.

[0018] Here, the relaxation factor can be used as a penalty term of the preset driving path to achieve reasonable lateral obstacle avoidance.

[0019] In a possible implementation, the adjusted motion planning result comprises an adjusted driving speed, and the adjusting of the driving speed of each preset driving path point in a driving process of the target vehicle on the preset driving path based on the lateral position variance comprises:

[0020] determining, for each of the preset driving path points, a collision probability of the target vehicle at the preset driving path point based on the lateral position variance;

[0021] determining an adjusted driving speed of the target vehicle at each of the preset driving path points based on the collision probability determined for each of the preset driving path points.

[0022] The collision probability can represent a probability that the target vehicle may collide with the obstacle when driving according to the original trajectory at the corresponding preset driving path point. The greater the probability value, the greater the possibility of collision. Conversely, the smaller the probability value, the smaller the possibility of collision. Based on this, the adjusted driving speed at the corresponding preset driving path point can be determined, thereby achieving safe driving on the driving path.

[0023] In a possible implementation, the determining of the collision probability of the target vehicle at the preset driving path point based on the lateral position variance comprises:

[0024] obtaining a plurality of vehicle corner point position information of the target vehicle at a position where the preset driving path point is located, and a plurality of obstacle corner point position information of the obstacle;

[0025] determining a minimum lateral distance between the target vehicle and the obstacle at the preset driving path point based on the plurality of vehicle corner point position information and the plurality of obstacle corner point position information;

[0026] determining the collision probability of the target vehicle at the preset driving path point based on the minimum lateral distance and the lateral position variance.

[0027] The minimum lateral distance can represent the minimum distance of collision. For example, it can be the distance between the nearest corner points when the real position of the obstacle and the detection position of the target vehicle are in the same direction. Collision between the corner points means that the target vehicle will collide with the obstacle. The determined collision probability is more consistent with the actual application scenario.

[0028] In a possible implementation, the determining of the collision probability of the target vehicle at the preset driving path point based on the minimum lateral distance and the lateral position variance comprises:

[0029] determining the collision probability of the target vehicle at the preset driving path point based on the minimum lateral distance and the lateral position variance through a probability constraint relationship.

[0030] Here, considering that the lateral position of the obstacle conforms to a normal distribution, the corresponding collision probability can be determined based on a probability constraint relationship, which is easy to implement.

[0031] In a possible implementation, the determining, based on the minimum lateral distance and the lateral position variance, of the collision probability of the target vehicle at the preset driving path point by using the probability constraint relationship includes:

[0032] Converting the probability constraint relationship to obtain a probability constraint relationship conforming to a standard normal distribution;

[0033] Taking the minimum lateral distance and the lateral position variance as input parameters of the converted probability constraint relationship and inputting the minimum lateral distance and the lateral position variance into the probability constraint relationship to obtain the collision probability of the target vehicle at the preset driving path point.

[0034] In a possible implementation, the determining, based on the collision probability of each preset driving path point, of the adjusted driving speed of the target vehicle at each preset driving path point includes:

[0035] For each of the preset driving path points, a virtual obstacle is determined based on a longitudinal distance between the obstacle and the preset driving path point, and a first driving speed that should be adjusted by the target vehicle in a case where the target vehicle collides with the virtual obstacle is determined.

[0036] The adjusted driving speed of the target vehicle at the preset driving path point is determined based on the collision probability of the preset driving path point and the first driving speed.

[0037] Here, the adjusted speed required for the target vehicle to avoid the obstacle can be determined by simulating a virtual obstacle, which mainly refers to avoiding the static obstacle, ensuring that the adjusted speed is neither too low nor too high, and ensuring the comfort during driving.

[0038] In a possible implementation, in a case where the obstacle is a static obstacle, the determining, based on the collision probability of the preset driving path point and the first driving speed, of the adjusted driving speed of the target vehicle at the preset driving path point includes:

[0039] A second driving speed that should be adjusted by the target vehicle in a case where the target vehicle does not collide with the dynamic obstacle is obtained.

[0040] determine an adjusted driving speed of the target vehicle at the preset driving path point based on the collision probability of the preset driving path point, the first driving speed, and the second driving speed.

[0041] Here, the adjustment of the driving speed of the entire target vehicle can also be realized in combination with the adjustment of the second driving speed corresponding to the dynamic obstacle, so as to further ensure the driving safety while ensuring the comfort in the driving process.

[0042] In a second aspect, the embodiments of the present disclosure further provide a device for motion planning, comprising:

[0043] an acquisition module configured to acquire a target image collected by a target vehicle in a driving process;

[0044] a determination module configured to determine a lateral position variance of an obstacle corresponding to the obstacle based on position information of the obstacle in the target image, the lateral position variance being used to represent a deviation degree between a current lateral position of the obstacle and a position mean value;

[0045] a planning module configured to adjust a preset driving path of the target vehicle and a driving speed of each preset driving path point in a driving process of the target vehicle according to the preset driving path based on the lateral position variance, to obtain an adjusted motion planning result.

[0046] In a third aspect, the embodiments of the present disclosure further provide an electronic device, comprising a processor, a memory, and a bus, the memory stores machine readable instructions executable by the processor, when the electronic device is running, the processor and the memory communicate through the bus, and the machine readable instructions are executed by the processor to perform the steps of the motion planning method according to any one of the first aspect and various embodiments thereof.

[0047] In a fourth aspect, the embodiments of the present disclosure further provide a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by a processor to perform the steps of the motion planning method according to any one of the first aspect and various embodiments thereof.

[0048] For the effects of the above-mentioned device for motion planning, electronic device, and computer readable storage medium, refer to the description of the above-mentioned motion planning method, which will not be repeated here.

[0049] In order to make the above objectives, characteristics and advantages of the present disclosure more apparent and understandable, the following preferred embodiments are specifically described below with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following will briefly introduce the drawings needed to be used in the embodiments. The drawings incorporated into the specification and form a part of the specification, which show the embodiments consistent with the present disclosure and are used to explain the technical solutions of the present disclosure. It should be understood that the following drawings only show some of the embodiments of the present disclosure, and therefore should not be considered as a limitation to the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0051] Figure 1 A flow chart of a motion planning method provided by an embodiment of the present disclosure is shown;

[0052] Figure 2 A schematic diagram of a motion planning device provided by an embodiment of the present disclosure is shown;

[0053] Figure 3 A schematic diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0054] In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure clearer, the following will combine the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, but not all the embodiments. The components of the embodiments of the present disclosure described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the claimed present disclosure, but only represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present disclosure.

[0055] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0056] The term "and / or" herein only describes an association relationship, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the term "at least one" herein means any one of the plurality or any combination of at least two of the plurality, for example, including at least one of A, B and C can mean including any one or more elements selected from the set consisting of A, B and C.

[0057] It is found through research that obstacle avoidance operation is often needed in the process of motion planning. In order to facilitate road motion planning, in the related art, either the obstacle is avoided in the lateral direction, that is, the obstacle is kept away in the lateral direction, and the vehicle passes through at normal speed in the longitudinal direction, or the obstacle is avoided in the longitudinal direction, that is, the vehicle is stopped behind the obstacle by deceleration in the longitudinal direction, and the obstacle is not considered in the lateral direction.

[0058] However, only avoiding the obstacle in the longitudinal direction causes the ego vehicle to stop and reduces the passability of automatic driving; only avoiding the obstacle in the lateral direction causes the vehicle to pass by the obstacle at too high a speed, and even causes emergency braking and takeover, which reduces the safety and comfort of automatic driving.

[0059] Based on the above research, the present disclosure provides a motion planning method, device, electronic device and storage medium, which improves the passability, safety and comfort in the process of vehicle driving through a more gentle obstacle avoidance method.

[0060] To facilitate understanding of the present embodiment, first, a motion planning method disclosed by the present embodiment is described in detail. The execution subject of the motion planning method provided by the present embodiment is generally an electronic device with certain computing power, which includes, for example, a terminal device or a server or other processing device. The terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementation manners, the motion planning method can be realized by a processor calling computer readable instructions stored in a memory.

[0061] Referring to Figure 1 FIG. 1 shows a flowchart of the motion planning method provided by the present embodiment, and the method includes steps S101-S103, wherein:

[0062] S101: acquiring a target image collected by a target vehicle in a driving process;

[0063] S102: determining a lateral position variance corresponding to an obstacle based on position information of the obstacle in the target image, the lateral position variance being used to represent a degree of deviation between a current lateral position of the obstacle and a position mean value;

[0064] S103: adjusting a preset driving path of the target vehicle and a driving speed of each preset driving path point in a driving process of the target vehicle according to the preset driving path based on the lateral position variance, to obtain an adjusted motion planning result.

[0065] In order to facilitate understanding of the motion planning method provided by the embodiments of the present disclosure, the application scenario of the method is first simply described as follows. The motion planning method in the embodiments of the present disclosure can be mainly applied to the field of autonomous vehicles, and the adjusted motion planning result can be used to realize safe driving of a target vehicle. Here, the influence of static obstacles on safe driving is mainly considered, and the obstacles are weighed from the lateral and longitudinal directions, so that a safe and comfortable driving path can be output, and the passability, safety and comfort of autonomous driving can be improved.

[0066] In the embodiments of the present disclosure, the target vehicle can be any type of autonomous vehicle, including but not limited to fully autonomous vehicles and highly autonomous vehicles. In actual applications, the autonomous vehicle here can be a related motor vehicle that cooperates with artificial intelligence, visual computing, radar, monitoring devices and global positioning systems to enable a computer to operate automatically and safely without or with little human initiative. The vehicle here includes but is not limited to a car, and the autonomous vehicle is mainly exemplified in the following.

[0067] The target image can be an image collected by a camera device arranged on the target vehicle, for example, a road image captured by a camera installed on a suitable grid or a car logo in front of the car. In addition, it can also be a set of images captured by devices such as a dashcam and a laser radar, and the embodiments of the present disclosure do not make specific limitations on this.

[0068] In the embodiments of the present disclosure, obstacle identification can be first performed to determine the position information of the obstacles in the target image, and then the lateral position variance corresponding to the obstacles is determined based on the position information. Based on the determined lateral position variance, the driving path and the driving speed can be adjusted, so that a more reasonable motion planning result can be obtained.

[0069] The identification of the obstacles can be obtained based on a related obstacle identification model. The obstacle identification model here can be trained based on the relationship between image samples and the annotation information (for example, obstacle position, obstacle type, etc.) of the obstacles in the image samples, so that the information of the obstacles in the target image can be identified when the target image is input into the obstacle identification model.

[0070] The obstacles in the embodiments of the present disclosure can mainly refer to static obstacles, for example, can include stationary vehicles (vehicles that remain stationary for a few minutes), fences, cone cylinders and other partial road-occupying obstacles. In actual applications, the obstacles can also be dynamic obstacles, which are not specifically limited here.

[0071] In the case of determining the position information of the obstacle in the target image, the longitudinal distance between the target vehicle and the obstacle can be determined based on the conversion relationship between the image coordinate system and the physical coordinate system, and the lateral position variance of the obstacle in the current driving process can be determined based on the longitudinal distance. The greater the lateral position variance, the more the current lateral position of the obstacle deviates from the mean value, indicating a lower demand for lateral obstacle avoidance. Conversely, the smaller the lateral position variance, the smaller the current lateral position of the obstacle deviates from the mean value, indicating a higher demand for lateral obstacle avoidance. Based on this, the preset driving path can be adjusted to achieve lateral adjustment.

[0072] In addition, the lateral position variance can also affect the collision probability of the target vehicle in the longitudinal direction. Therefore, based on the lateral position variance, the driving speed of the preset driving path point can also be adjusted, converting the discrete system with a passing probability of "1" and a non-passing probability of "0" for part of the lane-occupying obstacle into a continuous system, so that more reasonable motion planning results can be obtained.

[0073] In the process of determining the lateral position variance corresponding to the obstacle, the embodiment of the present disclosure can not only consider the longitudinal distance between the target vehicle and the obstacle, but also determine the type information of the obstacle, which is mainly considered because different types of obstacles have different effects on the lateral position variance.

[0074] In actual application, the adjustment and optimization of the preset driving path can be realized by introducing a relaxation factor. Specifically, the following steps can be used to achieve this:

[0075] Step one, based on the lateral position variance, determine the relaxation factor for avoiding obstacles in the lateral direction;

[0076] Step two, adjust the preset driving path based on the relaxation factor to obtain the adjusted driving path.

[0077] Here, based on the lateral position variance, the relaxation factor can be determined, and the two are inversely proportional. For example, in the case of a large lateral position variance, a small relaxation factor can be introduced, and vice versa, in the case of a small lateral position variance, a large relaxation factor can be introduced. Once a large relaxation factor is introduced, the preset driving path can be punished by such a high value to achieve lateral obstacle avoidance, and vice versa, once a small relaxation factor is introduced, the preset driving path can be punished by such a low value to perform driving almost according to the preset driving path.

[0078] In the embodiment of the present disclosure, the lateral position variance can also be used to achieve longitudinal obstacle avoidance, which can be described by the following steps:

[0079] Step one, for each of the preset driving path points, determine the collision probability of the target vehicle at the preset driving path point based on the lateral position variance;

[0080] Step two, based on the collision probability determined for each preset driving path point, determine the adjusted driving speed of the target vehicle at each preset driving path point.

[0081] Here, first, the collision probability of the target vehicle colliding with the obstacle can be determined for each preset driving path point, and then the driving speed is adjusted based on the collision probability corresponding to each preset driving path point.

[0082] Wherein, the collision probability can be determined in combination with the minimum lateral distance between the target vehicle and the obstacle and the lateral position variance, including the following steps:

[0083] Step one, obtain the position information of multiple vehicle corner points of the target vehicle at the position of the preset driving path point, and the position information of multiple obstacle corner points of the obstacle;

[0084] Step two, based on the position information of the multiple vehicle corner points and the position information of the multiple obstacle corner points, determine the minimum lateral distance between the target vehicle and the obstacle at the preset driving path point;

[0085] Step three, based on the minimum lateral distance and the lateral position variance, determine the collision probability of the target vehicle at the preset driving path point.

[0086] Here, first, the position information of multiple vehicle corner points and the position information of multiple obstacle corner points can be obtained, then the minimum lateral distance between the target vehicle and the obstacle at the preset driving path point is determined, and finally the collision probability is determined based on the minimum lateral distance and the lateral position variance.

[0087] Taking a stationary vehicle as an example, the obstacle detection information can still be determined by using the obstacle recognition model, and the obstacle detection information can be a detection box including four corner points. The target vehicle can also correspond to four corner points. In this case, the pair of corner points closest to each other can be selected from the two vehicles, and the minimum lateral distance can be determined.

[0088] In this actual scenario, if the deviation between the lateral detection position and the lateral actual position of the stationary vehicle in front is greater than the minimum lateral distance, and the actual position of the stationary vehicle and the actual position of the target vehicle are in the same direction of the detection position, the stationary vehicle in front and the target vehicle will collide. Based on this, the collision probability can be determined by using the probability constraint relationship previously constructed for the obstacle, and the minimum lateral distance and the lateral position variance.

[0089] wherein the above probability constraint relationship is used to indicate that the lateral position of the obstacle conforms to a normal distribution, that is, the lateral position d of the obstacle is subject to a normal distribution with a mean of μ and a variance of σ, d ~ N(μ, σ), and the probability density function of d is

[0090] In actual applications, the variance of the normal distribution can be determined based on existing road test data, mainly including the following steps:

[0091] First, obstacles that are stationary in all frames of data obtained are filtered from the frames of data, and the positions, numbers, and types of the obstacles are added, wherein the frames of data can be frames of point cloud data, frames of video, or other frames of data; then, for each numbered obstacle, a criterion is designed to obtain the true value of the position of the numbered obstacle; finally, for each type of obstacle, the position deviation of each numbered obstacle is calculated, and the position deviation is converted to the road coordinate system to obtain the relationship between the overall variance of the lateral position of each type of obstacle and the longitudinal distance in the road coordinate system, and then the variance of the normal distribution can be determined.

[0092] In actual applications, the normal distribution can be converted into a standard normal distribution, and then the minimum lateral distance and the lateral position variance are substituted into the probability constraint relationship obtained by the conversion, and the collision probability corresponding to the preset driving path point can be obtained.

[0093] In the embodiments of the present disclosure, based on the determined collision probability, the adjustment of the driving speed can be realized, specifically including the following steps:

[0094] Step one, for each of the preset driving path points, based on the longitudinal distance between the obstacle and the preset driving path point, a virtual obstacle predicted at the preset driving path point is determined, and a first driving speed that the target vehicle should adjust in the case of a collision between the target vehicle and the virtual obstacle is determined.

[0095] Step two, based on the collision probability of the preset driving path point and the first driving speed, the adjusted driving speed of the target vehicle at the preset driving path point is determined.

[0096] Here, based on the longitudinal distance between the obstacle and the preset driving path point, a virtual obstacle simulated at the preset driving path point can be determined, and the virtual obstacle is simulated on the corresponding preset driving path, so that if the speed of the target vehicle is not adjusted, a vehicle collision will occur, and based on this, the driving speed needs to be adjusted.

[0097] In actual application, the Intelligent Driver Model (IDM) can be used to determine the speed and corresponding acceleration and other information that should be adjusted in the case of collision with the simulated virtual obstacle.

[0098] It should be noted that considering that there can be multiple static obstacles that need to be avoided in actual application scenarios, in this case, the key obstacle can be screened based on the collision probability corresponding to each static obstacle and the longitudinal distance between the corresponding target vehicle and the static obstacle, and then the simulation operation of the virtual obstacle is performed on the key obstacle, thereby ensuring the maximum possibility of avoiding the obstacle that can collide as soon as possible, and further ensuring the safety of driving.

[0099] In addition, in actual scenarios, there can be other dynamic obstacles, and here, the second driving speed that the target vehicle should adjust in the case of no collision between the target vehicle and the dynamic obstacle can be obtained, and then the adjusted driving speed of the target vehicle at the preset driving path point is determined based on the collision probability of the preset driving path point, the first driving speed and the second driving speed.

[0100] In actual application, the collision probability can be assigned as a weight for the speed adjustment strategy taken when the static obstacle collides, and the remaining probability (i.e., 1 minus the collision probability) can be assigned as a weight for the speed adjustment strategy taken when the dynamic obstacle does not collide, and the final adjusted driving speed can be obtained by weighted summation, and then the obstacle avoidance strategy for the static obstacle and the dynamic obstacle can be obtained, and finally a safe and comfortable driving path can be output.

[0101] Those skilled in the art can understand that the writing order of the steps in the above method of the specific embodiment does not mean a strict execution order and does not constitute any limitation on the implementation process, and the specific execution order of the steps should be determined by its function and possible internal logic.

[0102] Based on the same inventive concept, the motion planning method of the present disclosure is also provided. Since the principle of solving problems in the device of the present disclosure is similar to the motion planning method of the present disclosure, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be described here.

[0103] Referring to Figure 2 Fig. 1 shows a schematic diagram of a motion planning device provided by the present disclosure, the device comprises an acquisition module 201, a determination module 202 and a planning module 203.

[0104] The acquisition module 201 is configured to acquire a target image collected by a target vehicle during driving.

[0105] The determining module 202 is configured to determine a lateral position variance corresponding to the obstacle based on the position information of the obstacle in the target image, the lateral position variance being used to represent a deviation degree between a current lateral position of the obstacle and a position mean value;

[0106] The planning module 203 is configured to adjust a preset driving path of the target vehicle and a driving speed of each preset driving path point in a driving process of the target vehicle along the preset driving path based on the lateral position variance, to obtain an adjusted motion planning result.

[0107] With the above motion planning device, when the target image collected by the target vehicle is obtained, the obstacle in the target image is analyzed, the lateral position variance corresponding to the obstacle is determined, the lateral position variance can represent a deviation degree between the vehicle and the obstacle, and the preset driving path and the driving speed of each preset driving path point are adjusted based on the lateral position variance, so that the target vehicle can pass through the obstacle by a more gentle motion trajectory, rather than directly adopting a lateral or longitudinal obstacle avoidance mode, thereby improving the passability, safety and comfort in the driving process of the vehicle.

[0108] In a possible implementation, the determining module 202 is configured to determine the lateral position variance corresponding to the obstacle based on the position information of the obstacle in the target image according to the following steps:

[0109] Based on the position information of the obstacle in the target image, a longitudinal distance between the target vehicle and the obstacle is determined.

[0110] Based on the longitudinal distance and type information of the obstacle, the lateral position variance corresponding to the obstacle is determined.

[0111] In a possible implementation, the adjusted motion planning result includes an adjusted driving path, and the planning module 203 is configured to adjust the preset driving path of the target vehicle based on the lateral position variance according to the following steps:

[0112] Based on the lateral position variance, a relaxation factor for avoiding the obstacle in the lateral direction is determined.

[0113] The preset driving path is adjusted based on the relaxation factor to obtain the adjusted driving path.

[0114] In a possible implementation, the adjusted motion planning result includes an adjusted driving speed, and the planning module 203 is configured to adjust the driving speed of each preset driving path point in a driving process of the target vehicle along the preset driving path based on the lateral position variance according to the following steps:

[0115] For each of the preset driving path points, determine a collision probability of the target vehicle at the preset driving path point based on the lateral position variance;

[0116] Determine the adjusted driving speed of the target vehicle at each of the preset driving path points based on the collision probability determined for each of the preset driving path points.

[0117] In a possible implementation, the planning module 203 is configured to determine the collision probability of the target vehicle at the preset driving path point based on the lateral position variance by the following steps:

[0118] Obtain a plurality of vehicle corner point position information of the target vehicle at a position where the preset driving path point is located, and a plurality of obstacle corner point position information of the obstacle;

[0119] Determine a minimum lateral distance between the target vehicle and the obstacle at the preset driving path point based on the plurality of vehicle corner point position information and the plurality of obstacle corner point position information;

[0120] Determine the collision probability of the target vehicle at the preset driving path point based on the minimum lateral distance and the lateral position variance.

[0121] In a possible implementation, the planning module 203 is configured to determine the collision probability of the target vehicle at the preset driving path point based on the minimum lateral distance and the lateral position variance by the following steps:

[0122] Determine the collision probability of the target vehicle at the preset driving path point based on the minimum lateral distance and the lateral position variance by a probability constraint relationship.

[0123] In a possible implementation, the planning module 203 is configured to determine the collision probability of the target vehicle at the preset driving path point based on the minimum lateral distance and the lateral position variance by the probability constraint relationship by the following steps:

[0124] Convert the probability constraint relationship to obtain a probability constraint relationship conforming to a standard normal distribution;

[0125] Take the minimum lateral distance and the lateral position variance as input parameters of the converted probability constraint relationship, and input the input parameters into the probability constraint relationship to obtain the collision probability of the target vehicle at the preset driving path point.

[0126] In a possible implementation, the planning module 203 is configured to determine the adjusted driving speed of the target vehicle at each of the preset driving path points based on the collision probability determined for each of the preset driving path points by the following steps:

[0127] For each preset driving path point, based on the longitudinal distance between the obstacle and the preset driving path point, determine the virtual obstacle predicted at the preset driving path point; and determine the first driving speed that the target vehicle should adjust in the event of a collision between the target vehicle and the virtual obstacle.

[0128] Based on the collision probability of the preset driving path points and the first driving speed, the adjusted driving speed of the target vehicle at the preset driving path points is determined.

[0129] In one possible implementation, when the obstacle is a static obstacle, the planning module 203 is configured to determine the adjusted driving speed of the target vehicle at the preset driving path point based on the collision probability of the preset driving path point and the first driving speed, according to the following steps:

[0130] The second driving speed that the target vehicle should adjust to if it does not collide with a dynamic obstacle is determined.

[0131] Based on the collision probability of the preset driving path point, the first driving speed, and the second driving speed, the adjusted driving speed of the target vehicle at the preset driving path point is determined.

[0132] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0133] This disclosure also provides an electronic device, such as... Figure 3 The diagram shown is a schematic representation of an electronic device structure provided in this embodiment of the present disclosure, including: a processor 301, a memory 302, and a bus 303. The memory 302 stores machine-readable instructions executable by the processor 301 (e.g., ...). Figure 2 The device includes modules 201 for acquiring, 202 for determining, and 203 for planning execution instructions. When the electronic device is running, the processor 301 communicates with the memory 302 via the bus 303. When a machine-readable instruction is executed by the processor 301, the following processing is performed:

[0134] Acquire target images of the target vehicle during its movement;

[0135] Based on the location information of obstacles in the target image, the lateral position variance of the obstacle is determined. The lateral position variance is used to characterize the degree of deviation between the current lateral position of the obstacle and the position mean.

[0136] The preset driving path of the target vehicle is adjusted based on the lateral position variance, and the driving speed of each preset driving path point in the driving process of the target vehicle according to the preset driving path is adjusted to obtain an adjusted motion planning result.

[0137] The embodiment of the present disclosure further provides a computer readable storage medium, and the computer readable storage medium stores a computer program. When the computer program is run by a processor, the steps of the motion planning method described in the method embodiment are executed. The storage medium can be a volatile or non-volatile computer readable storage medium.

[0138] The embodiment of the present disclosure further provides a computer program product, which carries a program code. The instructions included in the program code can be used to execute the steps of the motion planning method described in the method embodiment. For details, refer to the method embodiment, which will not be described here.

[0139] The computer program product can be specifically implemented by hardware, software or a combination thereof. In an optional embodiment, the computer program product is specifically embodied as a computer storage medium, and in another optional embodiment, the computer program product is specifically embodied as a software product, such as a software development kit (SDK) and the like.

[0140] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the foregoing method embodiment, which will not be described here. In several embodiments provided by the present disclosure, it should be understood that the disclosed system, device and method can be implemented by other ways. The device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interface, device or unit, which can be electrical, mechanical or other forms.

[0141] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place or distributed on multiple network units. According to actual needs, some or all of the units can be selected to achieve the purpose of the embodiment.

[0142] In addition, each functional unit in various embodiments of the present disclosure can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0143] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a nonvolatile computer readable storage medium readable by a processor. Based on this understanding, the technical solutions of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling an electronic device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present disclosure. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various other media capable of storing program codes.

[0144] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present disclosure, used to illustrate the technical solutions of the present disclosure, rather than limit the scope thereof. Although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that, within the technical scope disclosed by the present disclosure, any modifications or changes to the technical solutions described in the foregoing embodiments, or any easy-to-think-of variations, or equivalent replacements of some technical features, can be made by those skilled in the art; and these modifications, changes or replacements do not cause the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method of motion planning, characterized by, The method comprises: acquiring a target image collected by a target vehicle during driving; determining a lateral position variance corresponding to an obstacle based on position information of the obstacle in the target image, the lateral position variance being used to represent a degree of deviation between a current lateral position of the obstacle and a position mean value; adjusting a preset driving path of the target vehicle and a driving speed of each preset driving path point passed through by the target vehicle during driving according to the preset driving path based on the lateral position variance, to obtain an adjusted motion planning result; the adjusted motion planning result comprises an adjusted driving speed; adjusting the driving speed of each preset driving path point passed through by the target vehicle during driving according to the preset driving path based on the lateral position variance comprises: for each preset driving path point of the preset driving path points, determining a collision probability of the target vehicle at the preset driving path point based on the lateral position variance; determining an adjusted driving speed of the target vehicle at each preset driving path point based on the collision probability determined for each preset driving path point; the determining of the collision probability of the target vehicle at the preset driving path point based on the lateral position variance comprises: acquiring a plurality of vehicle corner position information of the target vehicle at a position of the preset driving path point and a plurality of obstacle corner position information of the obstacle; determining a minimum lateral distance between the target vehicle and the obstacle at the preset driving path point based on the plurality of vehicle corner position information and the plurality of obstacle corner position information; determining the collision probability of the target vehicle at the preset driving path point based on the minimum lateral distance and the lateral position variance.

2. The method of claim 1, wherein, the determining of the lateral position variance corresponding to the obstacle based on the position information of the obstacle in the target image comprises: determining a longitudinal distance between the target vehicle and the obstacle based on the position information of the obstacle in the target image; determining the lateral position variance corresponding to the obstacle based on the longitudinal distance and type information of the obstacle.

3. The method according to claim 1 or 2, characterized in that, the adjusted motion planning result comprises an adjusted driving path; the adjusting of the preset driving path of the target vehicle based on the lateral position variance comprises: determining a relaxation factor for obstacle avoidance in the lateral direction based on the lateral position variance; adjusting the preset driving path based on the relaxation factor to obtain the adjusted driving path.

4. The method of claim 1, wherein, the determining of the collision probability of the target vehicle at the preset driving path point based on the minimum lateral distance and the lateral position variance comprises: determining the collision probability of the target vehicle at the preset driving path point based on the minimum lateral distance and the lateral position variance through a probabilistic constraint relationship.

5. The method of claim 4, wherein, the determining of the collision probability of the target vehicle at the preset driving path point based on the minimum lateral distance and the lateral position variance through a probabilistic constraint relationship comprises: The probability constraint relationship is converted to obtain a probability constraint relationship conforming to a standard normal distribution; The minimum lateral distance and the lateral position variance are taken as input parameters of the converted probability constraint relationship, and are input into the probability constraint relationship to obtain a collision probability of the target vehicle at the preset driving path point.

6. The method of any one of claims 1, 4, or 5, wherein, The collision probability determined based on each preset driving path point is used to determine an adjusted driving speed of the target vehicle at each preset driving path point. For each of the preset driving path points, a virtual obstacle predicted at the preset driving path point is determined based on a longitudinal distance between the obstacle and the preset driving path point, and a first driving speed that should be adjusted for the target vehicle in a case where the target vehicle collides with the virtual obstacle is determined. The collision probability of the preset driving path point and the first driving speed are used to determine an adjusted driving speed of the target vehicle at the preset driving path point.

7. The method of claim 6, wherein, In a case where the obstacle is a static obstacle, the collision probability of the preset driving path point and the first driving speed are used to determine an adjusted driving speed of the target vehicle at the preset driving path point. A second driving speed that should be adjusted for the target vehicle in a case where the target vehicle does not collide with a dynamic obstacle is obtained. The collision probability of the preset driving path point, the first driving speed, and the second driving speed are used to determine an adjusted driving speed of the target vehicle at the preset driving path point.

8. An apparatus for motion planning, the apparatus comprising: The method comprises: An acquisition module is configured to acquire a target image collected by a target vehicle during driving; A determination module is configured to determine a lateral position variance corresponding to an obstacle based on position information of the obstacle in the target image, the lateral position variance being used to represent a degree of deviation between a current lateral position of the obstacle and a position mean value. A planning module is configured to adjust a preset driving path of the target vehicle and a driving speed of each preset driving path point in a driving process of the target vehicle along the preset driving path based on the lateral position variance, to obtain an adjusted motion planning result. The adjusted motion planning result comprises an adjusted driving speed. The planning module is specifically configured to: For each of the preset driving path points, a collision probability of the target vehicle at the preset driving path point is determined based on the lateral position variance. The collision probability determined based on each preset driving path point is used to determine an adjusted driving speed of the target vehicle at each preset driving path point. The planning module is specifically configured to: Obtain a plurality of vehicle corner position information of the target vehicle at a position of the preset driving path point and a plurality of obstacle corner position information of the obstacle. determine a minimum lateral distance between the target vehicle and the obstacle at the preset driving path point based on the plurality of vehicle corner point position information and the plurality of obstacle corner point position information; determine a collision probability of the target vehicle at the preset driving path point based on the minimum lateral distance and the lateral position variance.

9. An electronic device, comprising: comprising: a processor, a memory and a bus, the memory storing machine readable instructions executable by the processor, when the electronic device is running, the processor and the memory communicate through the bus, the machine readable instructions are executed by the processor to execute the steps of the motion planning method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, which is executed by the processor to execute the steps of the motion planning method of any one of claims 1 to 7.

Images