Vehicle driving planning method, device, equipment and storage medium

Abstract

The present disclosure relates to a driving planning method, device and equipment of a vehicle and a storage medium. The present disclosure obtains driving decision information of the vehicle by analyzing the action trajectory of at least one obstacle according to the obtained dynamic information of the obstacle, wherein the driving decision information at least includes at least one driving decision point and a vehicle driving strategy corresponding to each driving decision point; performs tree search on the at least one driving decision point according to the driving decision information, plans the driving acceleration of the vehicle for the at least one driving decision point, and obtains the vehicle driving strategy according to the driving acceleration, so that the obtained vehicle driving speed is more accurate. Compared with the prior art, the present embodiment avoids returning to the initial position for decision planning when there is no vehicle driving strategy for the current obstacle, saves the time for planning the vehicle speed, and improves the planning efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a method, apparatus, device and storage medium for vehicle driving planning. Background Technology

[0002] Autonomous vehicles are intelligent vehicles that use onboard sensor systems to perceive the road environment, automatically plan driving routes, and control the vehicle to reach a predetermined destination. They rely on an Autonomous Driving System (ADS) to realize their functions.

[0003] In existing technologies, vehicle speed planning involves simultaneously outputting decisions on how to deal with all obstacles based on obstacle filling, and then planning the vehicle's speed. This planning method is time-consuming and inefficient. Summary of the Invention

[0004] To solve the above-mentioned technical problems, or at least partially solve them, this disclosure provides a vehicle driving planning method, apparatus, device, and storage medium to improve the accuracy of vehicle speed and increase planning efficiency.

[0005] In a first aspect, embodiments of this disclosure provide a vehicle driving planning method, comprising:

[0006] Obtain obstacle dynamic information of at least one obstacle on the road where the vehicle is traveling, wherein the obstacle dynamic information includes at least the type of obstacle, at least one predicted trajectory of the obstacle, and the probability level corresponding to each predicted trajectory;

[0007] Based on the obstacle dynamic information, the trajectory of the at least one obstacle is analyzed to obtain the vehicle's driving decision information, which includes at least one driving decision point and the vehicle driving strategy corresponding to each driving decision point.

[0008] Based on the driving decision information, a tree search is performed on the at least one driving decision point to plan the vehicle's driving acceleration for the at least one driving decision point, thereby obtaining the vehicle driving strategy based on the driving acceleration.

[0009] In some embodiments, acquiring obstacle dynamic information of at least one obstacle on the vehicle's driving road includes:

[0010] The vehicle's dynamic traffic information is acquired, including at least obstacle information, environmental information, and road network information.

[0011] Based on the dynamic traffic information, the trajectory of at least one obstacle is predicted to obtain at least one predicted trajectory for each obstacle and a prediction probability corresponding to each predicted trajectory.

[0012] For each predicted action trajectory, determine the probability level to which the predicted probability of the predicted action trajectory belongs;

[0013] Based on at least one predicted trajectory of each obstacle and the driving trajectory of the vehicle, an obstacle type analysis is performed on each obstacle to obtain the obstacle type of each obstacle.

[0014] In some embodiments, before determining the probability level to which the predicted probability belongs for each predicted action trajectory, the method further includes:

[0015] For each predicted action trajectory, the predicted probability corresponding to the predicted action trajectory is corrected to obtain the corrected predicted probability.

[0016] In some embodiments, the obstacle type includes collision-type obstacles, and the probability level includes a first probability level;

[0017] The step of analyzing the trajectory of the at least one obstacle based on the obstacle's dynamic information to obtain the vehicle's driving decision information includes:

[0018] If at least one first obstacle exists among the at least one obstacle, the at least one driving decision point is determined based on the at least one first obstacle, wherein the obstacle type of the first obstacle is the collision-type obstacle and the probability level corresponding to the predicted trajectory is the first probability level;

[0019] For each driving decision point, a driving decision analysis is performed based on the decision point's location and the vehicle's acceleration capability to obtain the corresponding vehicle driving strategy.

[0020] In some embodiments, the probability level further includes a second probability level, which is lower than the first probability level;

[0021] The step of analyzing the trajectory of the at least one obstacle based on the obstacle's dynamic information to obtain the vehicle's driving decision information further includes:

[0022] If at least one second obstacle exists among the at least one obstacle, the at least one second obstacle is ignored, and the obstacle type of the second obstacle is the collision-type obstacle and the probability level corresponding to the predicted trajectory is the second probability level.

[0023] In some embodiments, the obstacle type further includes dangerous obstacles, and the probability level further includes a second probability level and a third probability level, wherein the third probability level is lower than the first probability level and higher than the second probability level;

[0024] The step of analyzing the trajectory of the at least one obstacle based on the obstacle's dynamic information to obtain the vehicle's driving decision information further includes:

[0025] If at least one third obstacle exists among the at least one obstacle, analyze the encounter information between each third obstacle and the vehicle. The obstacle type of the third obstacle is a collision obstacle and the probability level corresponding to the predicted trajectory is the third probability level, or the obstacle type of the third obstacle is a danger obstacle. The encounter information includes the encounter position, the separation position, the encounter time, and the separation time.

[0026] Based on the encounter information, calculate the vehicle's expected speed;

[0027] The step of performing driving decision analysis on the driving decision point based on its location and the vehicle's acceleration capability to obtain the vehicle driving strategy corresponding to the driving decision point includes:

[0028] Based on the desired speed, the location of the decision point, and the vehicle's acceleration capability, calculate the vehicle driving strategy corresponding to the decision point.

[0029] In some embodiments, the vehicle driving strategy includes accelerating to overtake, maintaining a constant speed to ignore the obstacle, and slowing down to yield.

[0030] The calculation of the vehicle driving strategy corresponding to the driving decision point, based on the desired speed, the location of the driving decision point, and the vehicle's acceleration capability, includes:

[0031] The vehicle's acceleration capability is limited based on the desired speed to obtain the vehicle's limited acceleration capability.

[0032] Based on the defined acceleration capability and the location of the decision point, the vehicle's acceleration as it passes the decision point is calculated.

[0033] Based on the value of the driving acceleration, the vehicle driving strategy corresponding to the driving decision point is determined.

[0034] In some embodiments, the step of performing a tree search on the at least one driving decision point based on the driving decision information and planning the vehicle's driving acceleration for the at least one driving decision point includes:

[0035] Based on the position of the at least one driving decision point on the vehicle trajectory, the at least one driving decision point is sorted to obtain a driving decision point sequence;

[0036] Based on the sequence of driving decision points and the vehicle driving strategy for each decision point, a tree search is performed on the at least one driving decision point to plan the vehicle's driving acceleration for the at least one driving decision point.

[0037] In some embodiments, before performing a tree search on the at least one driving decision point based on the driving decision information and planning the vehicle's driving acceleration for the at least one driving decision point, the method further includes:

[0038] Based on preset driving safety rules, a safety test is performed on the vehicle driving strategy corresponding to each driving decision point to obtain the vehicle driving strategy corresponding to the target driving decision point that does not meet the safety expectations.

[0039] Based on preset driving safety rules, the vehicle driving strategy corresponding to the target driving decision point is modified to obtain the modified vehicle driving strategy corresponding to the target driving decision point.

[0040] Secondly, embodiments of this disclosure provide a vehicle driving planning device, comprising:

[0041] The acquisition module is used to acquire obstacle dynamic information of at least one obstacle on the road on which the vehicle is traveling. The obstacle dynamic information includes at least the obstacle type, at least one predicted trajectory of the obstacle, and the probability level corresponding to each predicted trajectory.

[0042] The analysis module is used to perform trajectory analysis on the at least one obstacle based on the obstacle dynamic information to obtain the vehicle's driving decision information, wherein the driving decision information includes at least one driving decision point and the vehicle driving strategy corresponding to each driving decision point.

[0043] The planning module is used to perform a tree search on the at least one driving decision point based on the driving decision information, plan the driving acceleration of the vehicle for the at least one driving decision point, and thus obtain the driving speed of the vehicle based on the driving acceleration.

[0044] Thirdly, embodiments of this disclosure provide an electronic device, including:

[0045] Memory;

[0046] Processor; and

[0047] Computer programs;

[0048] The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in the first aspect.

[0049] Fourthly, embodiments of this disclosure provide a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method described in the first aspect.

[0050] Fifthly, embodiments of this disclosure also provide a computer program product, which includes a computer program or instructions that, when executed by a processor, implement the method described in the first aspect.

[0051] The vehicle driving planning method, apparatus, device, and storage medium provided in this disclosure acquire obstacle dynamic information of at least one obstacle on the vehicle's driving path. This obstacle dynamic information includes at least the obstacle type, at least one predicted trajectory of the obstacle, and the probability level corresponding to each predicted trajectory, providing a data foundation for planning vehicle acceleration. Based on the obstacle dynamic information, the vehicle's driving decision information is obtained by analyzing the trajectory of at least one obstacle. This driving decision information includes at least one driving decision point and a vehicle driving strategy corresponding to each driving decision point. The entire planned path is segmented based on the vehicle driving strategy of each decision point, laying the foundation for subsequent tree search. Based on the driving decision information, a tree search is performed on at least one driving decision point to plan the vehicle's driving acceleration for at least one driving decision point. The vehicle driving strategy is then obtained based on the driving acceleration, resulting in higher accuracy in the planned vehicle speed. Compared to existing technologies that directly output the decision results of all obstacles after obstacle filling and then plan the vehicle speed, this embodiment avoids returning to the initial position for decision planning when there is no vehicle driving strategy for the current obstacle, saving vehicle speed planning time and improving planning efficiency. Attached Figure Description

[0052] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0053] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 A flowchart of a vehicle driving planning method provided in an embodiment of this disclosure;

[0055] Figure 2 A schematic diagram illustrating an application scenario provided by an embodiment of this disclosure;

[0056] Figure 3 A flowchart illustrating a method for acquiring obstacle dynamic information provided in this embodiment of the disclosure;

[0057] Figure 4 This is a schematic diagram of a vehicle overcoming an obstacle, provided in an embodiment of this disclosure.

[0058] Figure 5 This is a schematic diagram illustrating a vehicle ignoring obstacles, provided as an embodiment of the present disclosure.

[0059] Figure 6 A schematic diagram illustrating a vehicle yielding to an obstacle provided in an embodiment of this disclosure;

[0060] Figure 7 This is a schematic diagram illustrating obstacle and vehicle encounter information provided in an embodiment of the present disclosure.

[0061] Figure 8 This is a schematic diagram illustrating obstacle and vehicle encounter information provided in an embodiment of the present disclosure.

[0062] Figure 9 A schematic diagram illustrating obstacle and vehicle encounter information provided in an embodiment of this disclosure;

[0063] Figure 10 A schematic diagram illustrating a vehicle driving strategy provided in an embodiment of this disclosure;

[0064] Figure 11 This is a schematic diagram illustrating an application scenario of vehicles merging into the main road, as provided in an embodiment of this disclosure.

[0065] Figure 12 A schematic diagram of the vehicle driving planning device provided in an embodiment of this disclosure;

[0066] Figure 13 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0067] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0068] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0069] Autonomous vehicles are intelligent vehicles that use onboard sensor systems to perceive the road environment, automatically plan driving routes, and control the vehicle to reach a predetermined destination. They rely on an Autonomous Driving System (ADS) to realize their functions.

[0070] In existing technologies, vehicle speed planning involves generating a speed planning curve by simultaneously outputting decisions on all obstacles based on obstacle filling. This planning method is time-consuming and inefficient. To address this issue, this disclosure provides a vehicle driving planning method, which will be described below with reference to specific embodiments.

[0071] Figure 1 This is a flowchart illustrating a vehicle driving planning method provided in an embodiment of this disclosure. The method can be executed by a vehicle driving planning device, which can be implemented in software and / or hardware. This device can be configured in an electronic device, such as a server or terminal, where the terminal specifically includes a vehicle. Furthermore, this method can be applied to various vehicle driving planning scenarios. It is understood that the vehicle driving planning method provided in this embodiment can also be applied in other scenarios.

[0072] The following is about Figure 1 The driving planning method for the vehicle shown is described below, and the specific steps of this method are as follows:

[0073] S101. Obtain obstacle dynamic information of at least one obstacle on the road where the vehicle is traveling, wherein the obstacle dynamic information includes at least the type of obstacle, at least one predicted trajectory of the obstacle, and the probability level corresponding to each predicted trajectory.

[0074] The vehicle is equipped with sensors to acquire ultra-wide-angle image data in front of the vehicle. These sensors can be image sensors, point cloud sensors, lidar sensors, etc. The vehicle uses these sensors to acquire obstacle dynamic information of at least one obstacle on the road. The obstacle can be a vehicle, a person, a non-motorized vehicle, etc. The obstacle dynamic information includes at least the type of obstacle, at least one predicted trajectory of the obstacle, and the probability level corresponding to each predicted trajectory.

[0075] S102. Based on the obstacle dynamic information, perform trajectory analysis on the at least one obstacle to obtain the vehicle's driving decision information, wherein the driving decision information includes at least one driving decision point and the vehicle driving strategy corresponding to each driving decision point.

[0076] Based on the dynamic information of the obstacles, the vehicle performs trajectory analysis on at least one obstacle. For example, the trajectory of the obstacle may be that the obstacle is traveling straight in its original lane, changing lanes, turning, or making a U-turn. The vehicle can obtain driving decision information based on the trajectory of the obstacle. This driving decision information includes at least one driving decision point corresponding to at least one obstacle and a driving strategy corresponding to each driving decision point. Specifically, the driving strategies include overtaking, ignoring, and yielding.

[0077] S103. Based on the driving decision information, perform a tree search on the at least one driving decision point, plan the driving acceleration of the vehicle for the at least one driving decision point, and thus obtain the vehicle driving strategy based on the driving acceleration.

[0078] Based on the aforementioned driving decision information, the vehicle performs a tree search on at least one driving decision point. Specifically, the tree search employs a greedy strategy. In this strategy, the vehicle first searches whether it can overtake at the driving decision point. If it can, the driving strategy for that point is to overtake. If not, it searches whether it can be ignored. If it can, the driving strategy for that point is to ignore. If it cannot be ignored, it continues searching whether it can yield. If it can, the driving strategy for that point is to yield. If it cannot yield, meaning that overtaking, ignoring, and yielding all fail to meet the conditions for safe driving, the vehicle backtracks and re-searches the decision of the previous driving decision point. Based on the results of the tree search, the vehicle's acceleration for at least one of the aforementioned driving decision points is planned, and the driving strategy is derived based on this acceleration.

[0079] Specifically, Figure 2This is a schematic diagram illustrating an application scenario provided by an embodiment of the present disclosure, such as... Figure 2 As shown, at driving decision point A, which includes driving strategy B1 (rushing ahead), driving strategy B2 (ignoring), and driving strategy B3 (yielding), the vehicle's driving strategy at driving decision point A is first searched. If it is determined that the vehicle can rush ahead at driving decision point A, then the driving strategy at driving decision point A is to rush ahead, that is, to rush ahead of the obstacle at driving decision point A to reach driving decision point B1. At driving decision point B1, the vehicle's driving strategy at driving decision point B1 is first searched. If it is determined that the vehicle cannot rush ahead, cannot ignore, or cannot yield at driving decision point B1, then driving decision point B1 is backtracked, and the decision at driving decision point A is searched again. At this time, the previously selected driving strategy B1 (rushing ahead) at driving decision point A is removed, and it is determined whether the vehicle can ignore the obstacle at driving decision point A. If it can ignore the obstacle, then the driving strategy at driving decision point A is to ignore the obstacle, that is, to rush ahead of the obstacle at driving decision point A to reach driving decision point B2. The vehicle's driving strategy at driving decision point B2 is determined, which includes driving strategy B21 (rushing ahead), driving strategy B22 (ignoring), and driving strategy B23 (yielding).

[0080] This embodiment of the disclosure acquires obstacle dynamic information of at least one obstacle on the vehicle's driving path. This obstacle dynamic information includes at least the obstacle type, at least one predicted trajectory of the obstacle, and the probability level corresponding to each predicted trajectory, providing a data foundation for planning vehicle acceleration. Based on the obstacle dynamic information, the trajectory of at least one obstacle is analyzed to obtain vehicle driving decision information. This driving decision information includes at least one driving decision point and a vehicle driving strategy corresponding to each driving decision point. The entire planned path is segmented based on the vehicle driving strategy of each decision point, laying the foundation for subsequent tree search. Based on the driving decision information, a tree search is performed on at least one driving decision point to plan the vehicle's driving acceleration for at least one driving decision point. Thus, the vehicle driving strategy is obtained based on the driving acceleration, resulting in higher accuracy in vehicle speed planning. Compared to the prior art, which directly outputs the decision results of all obstacles after obstacle filling and then plans the vehicle speed, this embodiment avoids returning to the initial position for decision planning when there is no vehicle driving strategy for the current obstacle, saving vehicle speed planning time and improving planning efficiency.

[0081] Furthermore, the solution provided in this embodiment first determines the driving strategy for at least one driving decision point, and then compresses the range of acceleration obtained from the driving decision point, that is, refines the vehicle's driving acceleration, thereby planning the vehicle driving strategy. Compared with the prior art, which directly generates the range of acceleration based on obstacle filling optimization, and then samples to generate the vehicle driving plan, the vehicle driving strategy obtained in this embodiment is equivalent to filtering the range of acceleration, resulting in more accurate vehicle driving acceleration, shorter time consumption, and higher efficiency.

[0082] Figure 3 A flowchart of the method for acquiring obstacle dynamic information provided in this disclosure embodiment is shown below. Figure 3 As shown, the method includes the following steps:

[0083] S301. Obtain the dynamic traffic information of the vehicle, wherein the dynamic traffic information includes at least obstacle information, environmental information, and road network information.

[0084] The vehicle is equipped with sensors to acquire ultra-wide-angle image data in front of the vehicle. These sensors can be image sensors, point cloud sensors, lidar sensors, etc. The vehicle obtains dynamic traffic information based on these sensors, including obstacle information, environmental information, road network information, and interactive information.

[0085] S302. Based on the dynamic traffic information, predict the trajectory of at least one obstacle to obtain at least one predicted trajectory for each obstacle and a predicted probability corresponding to each predicted trajectory.

[0086] Based on dynamic traffic information, the vehicle predicts the trajectory of at least one obstacle. Due to the intersection of paths in the road network information, the vehicle will obtain at least one predicted trajectory for each obstacle, as well as a different prediction probability for each predicted trajectory. This prediction probability represents the probability value of the current obstacle traveling along this trajectory. For ease of description, this prediction probability is denoted as the initial value of trajectory prediction probability.

[0087] Optionally, for each predicted action trajectory, the predicted probability corresponding to the predicted action trajectory is corrected to obtain a corrected predicted probability.

[0088] Specifically, the predicted probability corresponding to the predicted trajectory obtained from the above trajectory prediction is inaccurate and cannot be used in the vehicle's driving decision information. Therefore, for each predicted trajectory, the vehicle corrects the predicted probability corresponding to that trajectory to obtain a corrected predicted probability.

[0089] The specific correction method is as follows:

[0090] k=base_k+scene_delta_k+type_delta_k+obj_dist_k

[0091] The calculation of k is also dynamic, mainly composed of four parts: base_k represents the initial value of k, scene_delta_k is obtained based on the relationship between obstacles and road network information, type_delta_k is obtained based on the type of obstacle, and obj_dist_k is obtained based on the distance from the obstacle to the collision point. These four parts constitute the dynamically changing value of k. Based on the value of k and the time obj_t from the obstacle to the collision point, the probability adjustment value delta_con_prob is obtained, and finally the corrected prediction probability is obtained.

[0092] obj_t=obj_dist_to_intersect / obj_vel

[0093] That is: the time it takes for the obstacle to reach the point of collision = the distance the obstacle travels to the point of collision / the speed of the obstacle at the point of collision.

[0094] delta_con_prob=2 / (e^(k*obj_t-4)+1)-1

[0095] That is: Probability adjustment value = 2 / (e^(k*time of obstacle reaching the collision point - 4) + 1) - 1

[0096] The independent variable of delta_con_prob is obj_t, which is the time when obj arrives at the collision point. k represents the coefficient of obj_t, which is used to characterize the trajectory probability change trend under different environmental information. The larger the value of k, the greater the change in trajectory probability adjustment value and the more aggressive the vehicle's behavior. The smaller the value of k, the smaller the trajectory probability adjustment value and the more conservative the vehicle's behavior.

[0097] traj_prob_ressult=init_prob+con_ratio*delta_con_prob

[0098] That is: Corrected prediction probability = Initial value of trajectory prediction probability + Weight ratio * Probability adjustment value

[0099] Where traj_prob_ressult is the corrected prediction probability, which is obtained by adding two parts: one part is the initial value of the obstacle trajectory prediction probability init_prob, and the other part is the product of the probability adjustment value delta_con_prob calculated based on the obstacle-to-collision point time as the independent variable and the weight ratio con_ratio of the probability adjustment value.

[0100] S303. For each predicted action trajectory, determine the probability level to which the predicted probability of the predicted action trajectory belongs.

[0101] For each predicted action trajectory, it is determined whether the predicted probability of the predicted action trajectory is higher than a first preset threshold. If so, the probability level corresponding to the predicted action trajectory is determined to be the first probability level; if not, it is determined whether the predicted probability of the predicted action trajectory is lower than a second preset threshold. If so, the probability level corresponding to the predicted action trajectory is determined to be the second probability level; if not, the probability level corresponding to the predicted action trajectory is determined to be the third probability level. Wherein, the first probability level > the third probability level > the second probability level. In other embodiments, the first probability level can also be described as high probability, the third probability level as medium probability, and the second probability level as low probability; this embodiment does not impose specific limitations.

[0102] Optionally, for each predicted trajectory, it is determined whether the corrected predicted probability is higher than a first preset threshold. If yes, the corrected predicted probability is assigned to the first probability level; if no, it is determined whether the corrected predicted probability is lower than a second preset threshold. If yes, the corrected predicted probability is assigned to the second probability level; if no, the corrected predicted probability is assigned to the third probability level. Wherein, the first probability level > the third probability level > the second probability level.

[0103] S304. Based on at least one predicted trajectory of each obstacle and the driving trajectory of the vehicle, perform obstacle type analysis on each obstacle to obtain the obstacle type of each obstacle.

[0104] The vehicle performs obstacle type analysis on each obstacle based on at least one predicted trajectory for each obstacle and the vehicle's own trajectory, thus determining the obstacle type for each obstacle. The obstacle types include collision-type obstacles and hazard-type obstacles. Collision-type obstacles are those where collision detection is performed based on the vehicle's local path and the obstacle's predicted trajectory, indicating a potential collision between the predicted trajectory and the vehicle's trajectory. Hazard-type obstacles are those that do not pose a collision risk but are marked as hazardous by the vehicle.

[0105] This disclosure clarifies how to obtain obstacle dynamic information by specifically describing how to obtain the obstacle type, at least one predicted trajectory of the obstacle, the predicted probability, the corrected predicted probability, and the probability level corresponding to each predicted trajectory. This provides a data foundation for vehicle driving planning, facilitates the vehicle to obtain driving decision information based on obstacle dynamic information, and improves the accuracy of planned vehicle speed.

[0106] Based on the above embodiments, the obstacle types include collision-type obstacles, and the probability levels include a first probability level;

[0107] Accordingly, the step of analyzing the trajectory of the at least one obstacle based on the obstacle dynamic information to obtain the vehicle's driving decision information includes: if there is at least one first obstacle among the at least one obstacles, determining the at least one driving decision point based on the at least one first obstacle, wherein the obstacle type of the first obstacle is the collision-type obstacle and the probability level corresponding to the predicted trajectory is the first probability level; for each driving decision point, performing driving decision analysis on the driving decision point based on the decision point location and the vehicle's acceleration capability to obtain the vehicle driving strategy corresponding to the driving decision point.

[0108] Specifically, if the obstacle is a collision-type obstacle, and the predicted trajectory of this collision-type obstacle corresponds to the first probability level, then this obstacle is designated as the first obstacle. Based on this first obstacle, at least one driving decision point is determined. For each of these at least one driving decision point, a driving decision analysis is performed based on the decision point's location and the vehicle's acceleration capability to obtain the corresponding vehicle driving strategy. Specifically, the vehicle driving strategy can be as follows: Figure 4 The act of rushing shown can be as follows: Figure 5 The ignoring shown can also be as follows: Figure 6 The yielding is shown.

[0109] Optionally, the probability level may further include a second probability level, which is lower than the first probability level;

[0110] Accordingly, the step of analyzing the movement trajectory of the at least one obstacle based on the obstacle dynamic information to obtain the driving decision information of the vehicle further includes: if there is at least one second obstacle among the at least one obstacle, ignoring the at least one second obstacle, wherein the obstacle type of the second obstacle is the collision-type obstacle and the probability level corresponding to the predicted movement trajectory is the second probability level.

[0111] Specifically, if an obstacle is a collision-type obstacle, and the predicted trajectory of this collision-type obstacle corresponds to the second probability level, which is lower than the first probability level, then the obstacle is designated as a second obstacle. This second obstacle satisfies certain ignoring logic, such as the ignoring logic for low-probability trajectories. For this second obstacle, the vehicle's driving strategy is to ignore it. For example, ignoring the predicted trajectory of the second obstacle eliminates unnecessary predicted trajectories, improving the vehicle's prediction efficiency. It is understandable that for other types of obstacle ignoring logic, such as relative position ignoring logic, collision semantic ignoring logic, pedestrian trajectory ignoring logic based on traffic flow, and ignoring logic for obstacles with left-turn trajectories, the decision to ignore the obstacle can be based on environmental and semantic information.

[0112] Optionally, the obstacle type also includes dangerous obstacles, and the probability level also includes a second probability level and a third probability level, wherein the third probability level is lower than the first probability level and higher than the second probability level;

[0113] Accordingly, the step of analyzing the trajectory of the at least one obstacle based on the obstacle dynamic information to obtain the vehicle's driving decision information further includes: if there is at least one third obstacle among the at least one obstacles, analyzing the encounter information between each third obstacle and the vehicle, wherein the obstacle type of the third obstacle is a collision obstacle and the probability level corresponding to the predicted trajectory is the third probability level, or the obstacle type of the third obstacle is a danger obstacle, and the encounter information includes the encounter position, separation position, encounter time, and separation time; and calculating the vehicle's expected speed and expected acceleration based on the encounter information.

[0114] Specifically, if an obstacle is a collision-type obstacle and its predicted trajectory corresponds to a probability level of the third probability level (where the second probability level < the third probability level < the first probability level), or if the obstacle is a hazard-type obstacle, then the obstacle is designated as a third obstacle. The encounter information between this third obstacle and the vehicle is analyzed. This encounter information includes the encounter position, separation position, encounter time, and separation time. Based on this encounter information, the vehicle's expected speed and expected acceleration are calculated. The encounter information, expected speed, and expected acceleration constitute a weak decision-making scenario. Specifically, as follows... Figure 7As shown, the horizontal axis represents the distance (s-axis), i.e., the distance the obstacle travels along the vehicle's planned path, and the vertical axis represents the time (t-axis), i.e., the time it takes for the obstacle to move from its current position along the predicted trajectory to the vehicle's path. The dashed area represents the weak decision scenario area, containing five variable values: start_s, end_s, start_t, end_t, and expect_vel. start_t is the start time of the weak decision scenario (meeting time); end_t is the end time of the weak decision scenario (separation time); start_s is the starting position of the weak decision scenario (meeting position); end_s is the ending position of the weak decision scenario (separation position); and expect_vel is the expected speed of the vehicle in the weak decision scenario. Whether a weak decision scenario needs to be generated is determined by whether the obstacle and the vehicle are running parallel. Specifically, the parallel time refers to the time interval from when the vehicle and the obstacle run parallel until they separate.

[0115] like Figure 8 As shown, assuming the vehicle is traveling at its maximum acceleration, by Figure 8 It can be known that:

[0116] At the meeting time start_t:

[0117] ego_start_s=ego_vel*start_t+0.5*ego_max_acc*start_t*start_t

[0118] That is: Vehicle meeting position = Vehicle speed * Meeting time + 0.5 * Maximum vehicle acceleration * Meeting time * Meeting time

[0119] obj_start_s = obj_vel * start_t

[0120] That is: the position where obstacles meet = the speed of obstacles * the time of meeting.

[0121] obj_start_s+delta_start_s=ego_start_s+obj_length

[0122] That is: the point where the vehicle meets the obstacle + the distance from the vehicle's position to the obstacle's position = the point where the vehicle meets the obstacle + the length of the obstacle.

[0123] At time end_t (the time of separation):

[0124] ego_end_s=ego_vel*end_t+0.5*ego_max_acc*end_t*end_t

[0125] That is: Vehicle separation position = Vehicle speed * Separation time + 0.5 * Vehicle maximum acceleration * Separation time * Separation time

[0126] obj_end_s = obj_vel * end_t

[0127] That is: Obstacle separation position = Obstacle velocity * Separation time

[0128] obj_end_s+delta_end_s+ego_lenght=ego_end_s

[0129] That is: Location of encounter with obstacle + Distance from vehicle position to obstacle position + Vehicle length = Vehicle position

[0130] Here, delta_s is calculated based on the longitudinal position of the obstacle projected onto the vehicle path. delta_s includes delta_start_s and delta_end_s. delta_start_s is calculated at the meeting time start_t based on the longitudinal position of the obstacle projected onto the vehicle path, and delta_end_s is calculated at the separation time end_t based on the longitudinal position of the obstacle projected onto the vehicle path. The maximum vehicle speed ego_max_vel, the obstacle length obj_length, and the vehicle length ego_length are obtained. Based on the above formula, the parallel time parallel_time = end_t - start_t is calculated. When the calculated parallel time for the vehicle and obstacle exceeds a preset parallel time threshold, the obstacle is considered to pose a risk, and weak decision-making scenario information is added. This preset parallel time threshold is determined based on the specific actual situation of the vehicle and obstacle.

[0131] Specifically, generally, `start_t` is set to 0; if there is interaction between the obstacle prediction trajectory and the vehicle trajectory, the start time of this interaction is obtained. Generally, `end_t` is set to infinity; if there is interaction between the obstacle prediction trajectory and the vehicle trajectory, the end time of this interaction is obtained. For example... Figure 9As shown, obj_start_s and obj_end_s are calculated. Using the vehicle's current planned path as a reference line, the two closest points of the corners of the obstacle's box 91 are found on the vehicle's reference line. A perpendicular line is drawn from the corner of the obstacle to the line connecting these two points. Finally, the obstacle's projection onto the vehicle's path, the obstacle meeting position obj_start_s and the obstacle separation position obj_end_s, can be obtained. It can be understood that the distance of the obstacle's projection onto the vehicle's path obtained by start_t is the obstacle meeting position obj_start_s, and the distance of the obstacle's projection onto the vehicle's path obtained by end_t is the obstacle separation position obj_end_s.

[0132] Optionally, based on this encounter information, the vehicle's expected speed is calculated as follows:

[0133] expect_vel=min(ego_vel,obj_vel)-delta_v

[0134] That is: Expected speed = Minimum of vehicle speed and obstacle speed - Longitudinal speed obtained from the obstacle projected onto the vehicle path.

[0135] Specifically, calculating the expected speed requires comparing the vehicle speed and the obstacle speed, and selecting a speed no higher than the obstacle speed as a reference speed for a weak decision-making scenario. When passing through this weak decision-making scenario, the vehicle's planned expected speed will be lower than the obstacle speed, thus maintaining a certain safe distance from the obstacle.

[0136] Optionally, the vehicle's expected acceleration can be calculated based on the encounter information and the expected speed.

[0137] Specifically, the vehicle's current speed and its desired speed are both known information, and the vehicle's desired acceleration can be calculated based on the vehicle's current speed and desired speed.

[0138] Accordingly, the step of performing driving decision analysis on the driving decision point based on the decision point location and the vehicle's acceleration capability to obtain the vehicle driving strategy corresponding to the driving decision point includes: calculating the vehicle driving strategy corresponding to the driving decision point based on the desired speed, the decision point location, and the vehicle's acceleration capability.

[0139] Specifically, based on the above-mentioned desired speed, desired acceleration, decision point position of the driving decision point, acceleration capability of the vehicle, and current environmental information, the vehicle calculates the vehicle driving strategy corresponding to the driving decision point. The vehicle driving strategy includes two driving strategies: overtaking and following. Generally, for the third obstacle with the vehicle driving strategy of overtaking, the vehicle needs to accelerate in this weak decision scenario information; for the third obstacle with the vehicle driving strategy of following, the vehicle needs to decelerate in this weak decision scenario information. When the vehicle driving strategy corresponding to the third obstacle in the weak decision scenario information is obtained, the weak decision scenario information is filled, specifically including the meeting position, separation position, meeting time, separation time, and desired speed.

[0140] Optionally, the vehicle driving strategy includes accelerating to overtake and pass through, passing through at a constant speed and ignoring, and decelerating to give way and pass through;

[0141] Correspondingly, based on the desired speed, the decision point position of the driving decision point, and the acceleration capability of the vehicle, calculating the vehicle driving strategy corresponding to the driving decision point includes: limiting the acceleration capability of the vehicle based on the desired speed to obtain the limited acceleration capability of the vehicle; based on the limited acceleration capability and the decision point position of the driving decision point, calculating the driving acceleration of the vehicle passing through the decision point position; and determining the vehicle driving strategy corresponding to the driving decision point according to the value of the driving acceleration.

[0142] Based on the above filling of the weak decision scenario information, the current acceleration capability of the vehicle is limited according to the desired speed and desired acceleration in the weak decision scenario information to obtain the limited acceleration capability of the vehicle. For example, the acceleration capability of the vehicle for acceleration is [-A, A], where -A is the maximum deceleration capability and A is the maximum acceleration capability. According to the desired speed, the acceleration capability of the vehicle is limited, and the limited acceleration capability is [-A, B], where B < A. According to the limited acceleration capability of the vehicle and the decision point position of the driving decision point, calculate the driving acceleration of the vehicle passing through the decision point position. It can be understood that this driving acceleration is within the range of the limited acceleration capability of the vehicle; according to the value of this driving acceleration, determine the vehicle driving strategy corresponding to the driving decision point.

[0143] Specifically, Figure 10 is a schematic diagram of the vehicle driving strategy provided by an embodiment of the present disclosure, as Figure 10 shown:

[0144] Overtaking condition: If the calculated driving acceleration required for the vehicle to overtake the obstacle is within the range of the limited acceleration capability of the vehicle, then the vehicle meets the overtaking condition.

[0145] Ignore condition: If the vehicle can pass through the obstacle at a constant speed when it reaches the collision point, then the vehicle satisfies the ignore condition.

[0146] Yielding condition: If the calculated acceleration required for the vehicle to yield to an obstacle is within the vehicle's limited acceleration capacity, then the vehicle meets the yielding condition.

[0147] Understandably, the calculation methods for driving acceleration in the forced passage condition and the yielding condition are different. A search is performed on the decision point 1 corresponding to the first obstacle obj1 to obtain the vehicle driving strategy corresponding to the driving decision point 1 of the first obstacle obj1. The time from the first obstacle obj1 to the driving decision point 1 is calculated. Within this time, if the driving acceleration required for the vehicle to pass through the driving decision point 1 is sufficient to satisfy the vehicle's acceleration and deceleration capabilities, then the vehicle driving strategy corresponding to the driving decision point 1 is to accelerate and forcibly pass. The vehicle's position is updated to point1. At point1, a search is performed on the decision point 2 corresponding to the first obstacle obj2. Weak decision scenario information is found around the first obstacle obj2. Since the filling of weak decision scenario information will affect the vehicle's acceleration and deceleration capabilities, the expected speed of weak decision scenario 1 is first calculated based on the information of weak decision scenario 1. Based on the magnitude of the expected speed in the information of weak decision scenario 1, the vehicle's acceleration capability is limited to obtain the vehicle's limited acceleration capability. The vehicle's acceleration and deceleration range 1 is updated. The search is performed again on the decision point 2 corresponding to the first obstacle obj2 to obtain the vehicle's driving strategy corresponding to the driving decision point 2 of the first obstacle obj2. The time from the first obstacle obj2 to the driving decision point 2 is calculated. Within this time, it is determined that the driving acceleration required for the vehicle to pass through the driving decision point 2 meets the vehicle's limited acceleration capability, that is, the vehicle's acceleration and deceleration range 1 is updated. Therefore, the vehicle's driving strategy corresponding to the driving decision point 2 is to accelerate and rush through.The vehicle's position is updated to point2. At point2, a search is performed on the decision point 3 corresponding to the first obstacle obj3. Weak decision scenario information is found around the first obstacle obj3. Since the presence of weak decision scenario information affects the vehicle's acceleration and deceleration capabilities, the expected speed of weak decision scenario 2 is first calculated based on this information. The vehicle's acceleration capability is then limited based on the magnitude of this expected speed, resulting in the limited acceleration capability. The vehicle's acceleration and deceleration range 2 is updated, and the decision point 3 corresponding to the first obstacle obj3 is searched again. A search is performed to obtain the vehicle driving strategy corresponding to the driving decision point 3 of the first obstacle obj3. The time from the first obstacle obj3 to the driving decision point 3 is calculated. Within this time, it is determined that the driving acceleration required for the vehicle to pass through the driving decision point 3 meets the vehicle's limited acceleration capability. That is, the vehicle's acceleration and deceleration range 2 is updated. It is found that the vehicle driving strategy corresponding to the driving decision point 3 cannot accelerate to pass, nor can the first obstacle obj3 be ignored. Therefore, the vehicle driving strategy corresponding to the driving decision point 3 is to decelerate and give way. The vehicle's position state is updated to point 3.

[0148] The embodiments of this disclosure use multiple algorithms to calculate the vehicle driving strategy at at least one driving decision point corresponding to an obstacle, thereby planning the vehicle's driving acceleration at at least one driving decision point, improving the compatibility of the algorithm and enhancing the accuracy of the driving acceleration.

[0149] In some embodiments, based on the driving decision information, performing a tree search on the at least one driving decision point and planning the vehicle's driving acceleration for the at least one driving decision point includes: sorting the at least one driving decision point according to its decision point position on the vehicle trajectory to obtain a driving decision point sequence; and performing a tree search on the at least one driving decision point based on the driving decision point sequence and the vehicle driving strategy for each decision point to plan the vehicle's driving acceleration for the at least one driving decision point.

[0150] The vehicle sorts at least one driving decision point according to its position on the vehicle trajectory, thus obtaining a decision point sequence. For example, at least one decision point could be... Figure 10Given points 1, 2, and 3, where point 1 precedes point 2 and 3, and point 2 precedes point 3, sort these points to obtain the decision point sequence: points1, 2, and 3. Based on this decision point sequence and the vehicle's driving strategy at each decision point (e.g., point 1 = accelerate to pass, point 2 = accelerate to pass, and point 3 = decelerate to pass), perform a tree search on at least one decision point to plan the vehicle's acceleration for that decision point.

[0151] This embodiment of the disclosure sorts at least one driving decision point according to its position on the vehicle trajectory to obtain a decision point sequence. The vehicle can then perform a tree search on each driving decision point based on the sequence to plan the vehicle's driving acceleration for at least one driving decision point. This orderly analysis and decision-making on at least one driving decision point avoids the vehicle analyzing and making decisions on all decision points simultaneously, reducing the vehicle's computational load, improving the efficiency of driving planning, and enhancing the flexibility of the driving planning method.

[0152] In some embodiments, before performing a tree search on the at least one driving decision point based on the driving decision information and planning the vehicle's driving acceleration for the at least one driving decision point, the method further includes: performing a safety test on the vehicle driving strategy corresponding to each driving decision point based on preset driving safety rules to obtain a vehicle driving strategy corresponding to a target driving decision point that does not meet safety expectations; and correcting the vehicle driving strategy corresponding to the target driving decision point based on preset driving safety rules to obtain a corrected vehicle driving strategy corresponding to the target driving decision point.

[0153] The vehicle performs a safety test on the vehicle driving strategy corresponding to each driving decision point according to the preset driving safety rules, and obtains the vehicle driving strategy corresponding to the target driving decision point that does not meet the safety expectations. According to the preset driving safety rules, the vehicle driving strategy corresponding to the target driving decision point is corrected to obtain the corrected vehicle driving strategy corresponding to the target driving decision point. It can be understood that the corrected vehicle driving strategy corresponding to the target driving decision point conforms to the preset driving safety rules.

[0154] Specifically, the preset driving safety rules stipulate that in the scenario of vehicles merging from the auxiliary road into the main road, as long as there are vehicles on the main road, vehicles on the auxiliary road cannot merge into the main road. Regardless of the speed of vehicles on the main road, vehicles on the auxiliary road can only merge into the main road when there are no vehicles on the main road. Figure 11 This is a schematic diagram illustrating an application scenario of vehicles merging into the main road, as provided in this embodiment of the disclosure. Figure 11 As shown, scene information is identified. When a customized scene is identified where a vehicle merges from an auxiliary road into the main road, the vehicle's driving strategy at the corresponding driving decision point on the main road is corrected according to preset driving safety rules. For example, if the driving strategy of the vehicle at the corresponding driving decision point on the main road is to speed through or ignore the constant speed, it is considered that speeding through or ignoring the constant speed is an unsafe and wrong decision. The driving strategy of speeding through is corrected to slow down and yield, so that the corrected driving strategy of the target driving decision point conforms to the preset driving safety rules. That is, the driving strategy of slowing down and yielding conforms to the preset driving safety rules. In other words, it ensures that the final driving strategy of the vehicle will not collide head-on with the obstacle.

[0155] This embodiment modifies the vehicle driving strategy corresponding to target driving decision points that do not meet safety expectations based on preset driving safety rules, thus obtaining a modified vehicle driving strategy for the target driving decision points, ensuring the safety and reliability of the vehicle driving strategy. This improves the flexibility of the vehicle driving planning method.

[0156] Figure 12 This is a schematic diagram of the structure of a vehicle driving planning device provided in an embodiment of this disclosure. The vehicle driving planning device can be a terminal as described in the above embodiment, or it can be a component or assembly within that terminal. The vehicle driving planning device provided in this embodiment can execute the processing flow provided in the vehicle driving planning method embodiment, such as... Figure 12As shown, the vehicle driving planning device 120 includes: an acquisition module 121, an analysis module 122, and a planning module 123; wherein, the acquisition module 121 is used to acquire obstacle dynamic information of at least one obstacle on the vehicle's driving road, the obstacle dynamic information including at least the obstacle type, at least one predicted trajectory of the obstacle, and the probability level corresponding to each predicted trajectory; the analysis module 122 is used to perform trajectory analysis on the at least one obstacle based on the obstacle dynamic information to obtain the vehicle's driving decision information, the driving decision information including at least one driving decision point and the vehicle driving strategy corresponding to each driving decision point; the planning module 123 is used to perform tree search on the at least one driving decision point based on the driving decision information, plan the vehicle's driving acceleration for the at least one driving decision point, and thus obtain the vehicle driving strategy based on the driving acceleration.

[0157] Optionally, the acquisition module 121 is further configured to acquire dynamic traffic information of the vehicle, the dynamic traffic information including at least obstacle information, environmental information, and road network information; based on the dynamic traffic information, predict the trajectory of at least one obstacle to obtain at least one predicted trajectory for each obstacle and a predicted probability corresponding to each predicted trajectory; for each predicted trajectory, determine the probability level to which the predicted probability corresponding to the predicted trajectory belongs; and based on at least one predicted trajectory of each obstacle and the vehicle's driving trajectory, perform obstacle type analysis on each obstacle to obtain the obstacle type of each obstacle.

[0158] Optionally, the acquisition module 121 is further configured to perform a correction process on the prediction probability corresponding to each predicted action trajectory to obtain a corrected prediction probability.

[0159] Optionally, the obstacle type includes collision-type obstacles, and the probability level includes a first probability level;

[0160] The analysis module 122 is further configured to, if at least one first obstacle exists among the at least one obstacle, determine at least one driving decision point based on the at least one first obstacle, wherein the obstacle type of the first obstacle is the collision-type obstacle and the probability level corresponding to the predicted trajectory is the first probability level; and for each driving decision point, perform driving decision analysis on the driving decision point based on the decision point location and the vehicle's acceleration capability to obtain the vehicle driving strategy corresponding to the driving decision point.

[0161] Optionally, the probability level may further include a second probability level, which is lower than the first probability level;

[0162] The analysis module 122 is further configured to ignore the at least one second obstacle if there is at least one second obstacle among the at least one obstacle, wherein the obstacle type of the second obstacle is the collision-type obstacle and the probability level corresponding to the predicted trajectory is the second probability level.

[0163] Optionally, the obstacle type also includes dangerous obstacles, and the probability level also includes a second probability level and a third probability level, wherein the third probability level is lower than the first probability level and higher than the second probability level;

[0164] The analysis module 122 is further configured to, if at least one third obstacle exists among the at least one obstacle, analyze the encounter information between each third obstacle and the vehicle, wherein the obstacle type of the third obstacle is a collision-type obstacle and the probability level corresponding to the predicted trajectory is the third probability level, or the obstacle type of the third obstacle is a danger-type obstacle, and the encounter information includes the encounter position, the separation position, the encounter time, and the separation time; and calculate the expected speed of the vehicle based on the encounter information.

[0165] The planning module 123 is further used to calculate the vehicle driving strategy corresponding to the driving decision point based on the expected speed, the decision point location of the driving decision point, and the vehicle's acceleration capability.

[0166] Optionally, the vehicle driving strategy includes accelerating to overtake, maintaining a constant speed to ignore the obstacle, and slowing down to yield.

[0167] The planning module 123 is further configured to limit the acceleration capability of the vehicle based on the desired speed to obtain the limited acceleration capability of the vehicle; calculate the driving acceleration of the vehicle when passing through the decision point based on the limited acceleration capability and the decision point position of the driving decision point; and determine the vehicle driving strategy corresponding to the driving decision point based on the value of the driving acceleration.

[0168] Optionally, the planning module 123 is further configured to sort the at least one driving decision point according to the decision point position of the at least one driving decision point on the vehicle trajectory to obtain a decision point sequence; and perform a tree search on the at least one driving decision point based on the driving decision point sequence and the vehicle driving strategy of each decision point to plan the driving acceleration of the vehicle for the at least one driving decision point.

[0169] Optionally, the vehicle driving planning device 120 further includes: a correction module 124, used to perform a safety test on the vehicle driving strategy corresponding to each driving decision point based on preset driving safety rules, to obtain the vehicle driving strategy corresponding to the target driving decision point that does not meet the safety expectations; and to correct the vehicle driving strategy corresponding to the target driving decision point based on preset driving safety rules, to obtain the corrected vehicle driving strategy corresponding to the target driving decision point.

[0170] Figure 12 The vehicle driving planning device in the illustrated embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and will not be repeated here.

[0171] Figure 13 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. The electronic device can be a terminal as described in the above embodiments. The electronic device provided in this disclosure can execute the processing flow provided in the vehicle driving planning method embodiments, such as... Figure 13 As shown, the electronic device 130 includes: a memory 131, a processor 132, a computer program, and a communication interface 133; wherein the computer program is stored in the memory 131 and is configured to be executed by the processor 132 of the vehicle driving planning method as described above.

[0172] In addition, this disclosure also provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the vehicle driving planning method described in the above embodiments.

[0173] Furthermore, this disclosure also provides a computer program product, which includes a computer program or instructions that, when executed by a processor, implement the vehicle driving planning method described above.

[0174] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0175] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0176] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0177] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to:

[0178] Obtain obstacle dynamic information of at least one obstacle on the road where the vehicle is traveling, wherein the obstacle dynamic information includes at least the type of obstacle, at least one predicted trajectory of the obstacle, and the probability level corresponding to each predicted trajectory;

[0179] Based on the obstacle dynamic information, the trajectory of the at least one obstacle is analyzed to obtain the vehicle's driving decision information, which includes at least one driving decision point and the vehicle driving strategy corresponding to each driving decision point.

[0180] Based on the driving decision information, a tree search is performed on the at least one driving decision point to plan the vehicle's driving acceleration for the at least one driving decision point, thereby obtaining the vehicle driving strategy based on the driving acceleration.

[0181] In addition, the electronic device can also perform other steps in the vehicle driving planning method described above.

[0182] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0183] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0184] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0185] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0186] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0187] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0188] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A travel planning method of a vehicle, characterized by, The method includes: Obtain obstacle dynamic information of at least one obstacle on the road where the vehicle is traveling, wherein the obstacle dynamic information includes at least the type of obstacle, at least one predicted trajectory of the obstacle, and the probability level corresponding to each predicted trajectory; Based on the obstacle dynamic information, the movement trajectory of the at least one obstacle is analyzed to obtain the vehicle's driving decision information, which includes at least one driving decision point and the vehicle driving strategy corresponding to each driving decision point. Based on the driving decision information, a tree search is performed on the at least one driving decision point to plan the vehicle's driving acceleration for the at least one driving decision point, thereby obtaining the vehicle driving strategy based on the driving acceleration. The types of obstacles include collision-type obstacles, and the probability levels include a first probability level; The step of analyzing the trajectory of at least one obstacle based on the obstacle's dynamic information to obtain the vehicle's driving decision information includes: If at least one first obstacle exists among the at least one obstacle, the at least one driving decision point is determined based on the at least one first obstacle, wherein the obstacle type of the first obstacle is the collision-type obstacle and the probability level corresponding to the predicted trajectory is the first probability level; For each driving decision point, a driving decision analysis is performed based on the decision point location and the vehicle's acceleration capability to obtain the vehicle driving strategy corresponding to the driving decision point.

2. The method of claim 1, wherein, The acquisition of obstacle dynamic information of at least one obstacle on the vehicle's driving road includes: The vehicle's dynamic traffic information is acquired, including at least obstacle information, environmental information, and road network information. Based on the dynamic traffic information, the trajectory of at least one obstacle is predicted to obtain at least one predicted trajectory for each obstacle and a prediction probability corresponding to each predicted trajectory. For each predicted action trajectory, determine the probability level to which the predicted probability of the predicted action trajectory belongs; Based on at least one predicted trajectory of each obstacle and the driving trajectory of the vehicle, an obstacle type analysis is performed on each obstacle to obtain the obstacle type of each obstacle.

3. The method of claim 2, wherein, Before determining the probability level to which the predicted probability belongs for each predicted action trajectory, the method further includes: For each predicted action trajectory, the predicted probability corresponding to the predicted action trajectory is corrected to obtain the corrected predicted probability.

4. The method of claim 1, wherein, The probability level also includes a second probability level, which is lower than the first probability level; The step of analyzing the trajectory of the at least one obstacle based on the obstacle's dynamic information to obtain the vehicle's driving decision information further includes: If at least one second obstacle exists among the at least one obstacle, the at least one second obstacle is ignored, and the obstacle type of the second obstacle is the collision-type obstacle and the probability level corresponding to the predicted trajectory is the second probability level.

5. The method of claim 1, wherein, The obstacle types also include dangerous obstacles, and the probability levels also include a second probability level and a third probability level, wherein the third probability level is lower than the first probability level and higher than the second probability level; The step of analyzing the trajectory of the at least one obstacle based on the obstacle's dynamic information to obtain the vehicle's driving decision information further includes: If at least one third obstacle exists among the at least one obstacle, analyze the encounter information between each third obstacle and the vehicle. The obstacle type of the third obstacle is a collision obstacle and the probability level corresponding to the predicted trajectory is the third probability level, or the obstacle type of the third obstacle is a danger obstacle. The encounter information includes the encounter position, the separation position, the encounter time, and the separation time. Based on the encounter information, calculate the vehicle's expected speed; The step of performing driving decision analysis on the driving decision point based on its location and the vehicle's acceleration capability to obtain the vehicle driving strategy corresponding to the driving decision point includes: Based on the desired speed, the location of the decision point, and the vehicle's acceleration capability, calculate the vehicle driving strategy corresponding to the decision point.

6. The method of claim 5, wherein, The vehicle driving strategies include accelerating to pass quickly, maintaining a constant speed to ignore the passage, and slowing down to give way. The calculation of the vehicle driving strategy corresponding to the driving decision point, based on the desired speed, the location of the driving decision point, and the vehicle's acceleration capability, includes: The vehicle's acceleration capability is limited based on the desired speed to obtain the vehicle's limited acceleration capability. Based on the defined acceleration capability and the location of the decision point, the vehicle's acceleration as it passes the decision point is calculated. Based on the value of the driving acceleration, the vehicle driving strategy corresponding to the driving decision point is determined.

7. The method of claim 1, wherein, The step of performing a tree search on the at least one driving decision point based on the driving decision information and planning the vehicle's driving acceleration for the at least one driving decision point includes: Based on the position of the at least one driving decision point on the vehicle trajectory, the at least one driving decision point is sorted to obtain a driving decision point sequence; Based on the sequence of driving decision points and the vehicle driving strategy for each decision point, a tree search is performed on the at least one driving decision point to plan the vehicle's driving acceleration for the at least one driving decision point.

8. The method of claim 1, wherein, Before performing a tree search on the at least one driving decision point based on the driving decision information and planning the vehicle's driving acceleration for the at least one driving decision point, the method further includes: Based on preset driving safety rules, a safety test is performed on the vehicle driving strategy corresponding to each driving decision point to obtain the vehicle driving strategy corresponding to the target driving decision point that does not meet the safety expectations. Based on preset driving safety rules, the vehicle driving strategy corresponding to the target driving decision point is modified to obtain the modified vehicle driving strategy corresponding to the target driving decision point.

9. A travel planning device of a vehicle characterized by comprising: The device includes: The acquisition module is used to acquire obstacle dynamic information of at least one obstacle on the road on which the vehicle is traveling. The obstacle dynamic information includes at least the obstacle type, at least one predicted trajectory of the obstacle, and the probability level corresponding to each predicted trajectory. The analysis module is used to perform trajectory analysis on the at least one obstacle based on the obstacle dynamic information to obtain the vehicle's driving decision information, wherein the driving decision information includes at least one driving decision point and the vehicle driving strategy corresponding to each driving decision point. The planning module is used to perform a tree search on the at least one driving decision point based on the driving decision information, plan the driving acceleration of the vehicle for the at least one driving decision point, and thus obtain the driving strategy of the vehicle based on the driving acceleration. The types of obstacles include collision-type obstacles, and the probability levels include a first probability level; The analysis module is further configured to, if at least one first obstacle exists among the at least one obstacle, determine at least one driving decision point based on the at least one first obstacle, wherein the obstacle type of the first obstacle is the collision-type obstacle and the probability level corresponding to the predicted trajectory is the first probability level; for each driving decision point, perform driving decision analysis on the driving decision point based on the decision point location of the driving decision point and the acceleration capability of the vehicle, and obtain the vehicle driving strategy corresponding to the driving decision point.

10. An electronic device, comprising: include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in any one of claims 1-8.

11. A computer readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-8.

Images