Vehicle speed planning method, device and equipment and storage medium

Abstract

The invention provides a vehicle speed planning method, device and equipment and a storage medium, and relates to the technical field of artificial intelligence such as automatic driving and intelligent transportation. The method comprises the following steps: according to a planned trajectory of a target vehicle and a predicted trajectory of an obstacle, determining an overlapped conflict area generated by the planned trajectory and the predicted trajectory; constructing a driving semantic decision tree based on the candidate decision result of the target vehicle in the conflict area; pruning the driving semantic decision tree according to a predetermined pruning condition, and generating a driving semantic decision for the target vehicle according to the pruned decision tree; and determining a speed planning decision of the target vehicle relative to all the obstacles according to the driving semantic decision, and adjusting the driving speed of the target vehicle according to the speed planning decision. According to the method provided by the invention, the speed planning decision of the target vehicle in the conflict area is generated, the conflict with the obstacle is avoided, and the safety of vehicle driving is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to the field of autonomous driving and intelligent transportation technology, and in particular to a vehicle speed planning method, device, equipment and storage medium. Background Art

[0002] When the predicted trajectory of the autonomous vehicle conflicts with the predicted trajectory of other obstacles, the speed of the autonomous vehicle needs to be planned to avoid collisions and scrapes with other obstacles. Establishing an ST graph (a coordinate system with time as the horizontal axis and the distance s of the planned path as the vertical axis) is a common method for speed planning. Summary of the invention

[0003] The present disclosure provides a vehicle speed planning method, device, equipment and storage medium.

[0004] According to a first aspect of the present disclosure, a vehicle speed planning method is provided, comprising: determining, based on a planned trajectory of a target vehicle and a predicted trajectory of an obstacle, a conflict zone where the planned trajectory and the predicted trajectory overlap; constructing a driving semantic decision tree based on candidate decision results of the target vehicle in the conflict zone; pruning the driving semantic decision tree according to a predetermined pruning condition, and generating a driving semantic decision for the target vehicle according to the pruned decision tree; determining a speed planning decision of the target vehicle relative to all obstacles according to the driving semantic decision, and adjusting the driving speed of the target vehicle according to the speed planning decision.

[0005] According to a second aspect of the present disclosure, a vehicle speed planning device is provided, comprising: a determination module, configured to determine, based on a planned trajectory of a target vehicle and a predicted trajectory of an obstacle, a conflict zone where a planned trajectory and a predicted trajectory overlap; a construction module, configured to construct a driving semantic decision tree based on candidate decision results of the target vehicle in the conflict zone; a pruning module, configured to prune the driving semantic decision tree according to a predetermined pruning condition, and generate a driving semantic decision for the target vehicle according to the pruned decision tree; and a planning module, configured to determine a speed planning decision of the target vehicle relative to all obstacles based on the driving semantic decision, and adjust the driving speed of the target vehicle according to the speed planning decision.

[0006] According to a third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any implementation manner in the first aspect.

[0007] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method described in any implementation manner of the first aspect.

[0008] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program, when executed by a processor, performs the method described in any implementation manner of the first aspect.

[0009] According to a sixth aspect of the present disclosure, an autonomous driving vehicle is provided, which includes the electronic device as described in the third aspect.

[0010] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. Figure 1 is a flow chart of a first embodiment of a vehicle speed planning method according to the present disclosure; Figure 2 It is a schematic diagram of the conflict zone; Figure 3 is a flow chart of a second embodiment of a vehicle speed planning method according to the present disclosure; Figure 4-1 It is a schematic diagram of the decision-making results of grab near and let far when the conflict zones intersect; Figure 4-2 It is a schematic diagram of the decision-making results of giving way to the near and grabbing the far when the conflict zones intersect; Figure 4-3 It is a schematic diagram of the decision-making results of near-seize and far-seize in the case of intersection of conflict zones; Figure 4-4 It is a schematic diagram of the decision results of near-by giving way and far-by giving way when the conflict zones intersect; Figure 5-1 It is a schematic diagram of the decision-making results of grab near and let far when the conflict zone is included; Figure 5-2 It is a schematic diagram of the decision-making results of giving way to the near and grabbing the far when the conflict zone is included; Figure 5-3 It is a schematic diagram of the decision-making results of near-seize and far-seize in the case of conflict zone inclusion; Figure 5-4 It is a schematic diagram of the decision results of near-give-way and far-give-way when the conflict zone is included; Figure 6 is a flow chart of a third embodiment of a vehicle speed planning method according to the present disclosure; Figure 7is a structural schematic diagram of an embodiment of a vehicle speed planning device according to the present disclosure; Figure 8 It is a block diagram of an electronic device used to implement the vehicle speed planning method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0012] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0013] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0014] An exemplary system architecture for implementing the vehicle speed planning method provided by the present disclosure may include a terminal device, a network, and a server. The network is used to provide a communication link between the terminal device and the server, and may include various connection types, such as a wired communication link, a wireless communication link, or an optical fiber cable, etc.

[0015] The user can use the terminal device to interact with the server through the network to receive or send information, etc. Various client applications can be installed on the terminal device, for example, map, navigation, entertainment and other client applications.

[0016] The terminal device may be, for example, a vehicle computer system of a self-driving car, a delivery robot, or the like. The system may be implemented by hardware, by software, or by a combination of hardware and software.

[0017] The server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, used to provide distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0018] It should be noted that the execution subject of the vehicle speed planning method provided by the present disclosure (hereinafter referred to as the "execution subject") can be executed by the server in the above-mentioned system architecture, or can be implemented by the above-mentioned terminal device. For example, when the server executes, the server sends the control command to the client, such as the vehicle's on-board system, and then controls the vehicle according to the control command through the on-board system, such as adjusting the vehicle's driving speed. For another example, when the terminal device (such as the vehicle's on-board system) executes, the terminal device controls the vehicle according to the control command, such as adjusting the vehicle's driving speed.

[0019] Figure 1 A process 100 of a first embodiment of a vehicle speed planning method according to the present disclosure is shown. The vehicle speed planning method comprises the following steps: Step 101 : determining a conflict area where the planned trajectory and the predicted trajectory overlap according to the planned trajectory of the target vehicle and the predicted trajectory of the obstacle.

[0020] In this embodiment, the execution entity determines whether there is a conflict zone based on the trajectory information (planned trajectory) of the target vehicle and the trajectory information (predicted trajectory) of the obstacle, wherein the conflict zone is the overlapping area between the planned trajectory of the target vehicle and the predicted trajectory of the obstacle.

[0021] Specifically, the above-mentioned execution subject will first obtain the planned trajectory of the self-vehicle (i.e., the target vehicle), which is the planned trajectory information of the self-vehicle in the next period of time. The planned trajectory can be generated by the path planning algorithm, and the position, speed and other information of the self-vehicle will also be obtained. Then the above-mentioned execution subject will also obtain the predicted trajectory of other interactive vehicles (i.e., obstacles), which is the predicted trajectory information of the obstacle in the next period of time, and the position, speed and other information of the obstacle will also be obtained. The obstacle here can be one or more, and this embodiment does not limit the number of obstacles.

[0022] Afterwards, the above-mentioned execution entity will determine whether the planned trajectory of the target vehicle overlaps with the predicted trajectory of the obstacle, or whether a conflict occurs. That is, based on the speed, trajectory and other information of the target vehicle and the speed, trajectory and other information of the obstacle, it will be determined whether the trajectory of the obstacle and the trajectory of the target vehicle will conflict at a certain moment or over a certain period of time, that is, whether there is an overlapping area between the two trajectories, and the area where the conflict (or overlap) occurs will be regarded as the conflict area.

[0023] It should be noted that there may be multiple conflict zones, that is, the planned trajectory of the target vehicle may conflict with the predicted trajectories of multiple obstacles, thereby forming multiple conflict zones.

[0024] It should be noted that the boundary of the conflict zone is taken from the projection position of the overlapping area of ​​the vehicle path and other obstacle trajectory information on their respective paths. Figure 2 A schematic diagram of the conflict zone is shown in Figure 2. Figure 2 As shown, ABCD is the interactive conflict area between the ego vehicle and the other vehicle, A is the front boundary of the ego vehicle arriving at the conflict area, B is the rear boundary of the ego vehicle leaving the conflict area, C is the front boundary of the other vehicle arriving at the conflict area, and D is the rear boundary of the other vehicle leaving the conflict area.

[0025] Step 102: construct a driving semantic decision tree based on candidate decision results of the target vehicle in the conflict zone.

[0026] In this embodiment, after determining the conflict zone, the above-mentioned execution entity will construct a driving semantic decision tree based on the candidate decision results of the target vehicle in the conflict zone. Here, the candidate decision results include overtaking or giving way, that is, the target vehicle in the conflict zone can give way (let the obstacle pass through the conflict zone first) or overtake (the vehicle passes through the conflict zone first).

[0027] The driving semantics decision tree constructed based on the candidate decision results is a full binary tree, and the actions at each level of the driving semantics decision tree are rush or yield semantics. When there are multiple conflict zones, each branch of the driving semantics decision tree represents each of the multiple conflict zones, and the candidate decision results of the target vehicle in each conflict zone include rush and yield.

[0028] Step 103, pruning the driving semantics decision tree according to a predetermined pruning condition, and generating a driving semantics decision for the target vehicle according to the pruned decision tree.

[0029] In this embodiment, the execution subject prunes the driving semantic decision tree according to the pre-built pruning conditions, and obtains the driving semantic decision according to the pruned semantic decision tree. Here, the pruning conditions may include but are not limited to timing constraints, constraints on ST (advance distance and advance time) information during execution, etc.

[0030] As an example, since there are timing constraints between the previous and next semantic decisions in the semantic decision sequence corresponding to the driving semantic decision, if the timing constraints are violated, pruning should be performed. As another example, the semantic decision sequence that cannot be executed under the speed limit constraint should be pruned. As another example, if the semantic decision in the proximal conflict area is to cut in, and the semantic decision in the distal conflict area is to yield, and the ST information conflicts during the execution process, pruning should be performed.

[0031] Finally, the above-mentioned execution entity will generate the corresponding driving semantic decision according to the pruned semantic decision tree. The driving semantic decision here is the decision result in the pruned semantic decision tree, such as {cut in, give way, cut in...}. Therefore, the length of the semantic decision sequence corresponding to the driving semantic decision is the tree depth of the semantic decision tree.

[0032] Step 104 , determining a speed planning decision of the target vehicle relative to all obstacles according to the driving semantic decision, and adjusting the driving speed of the target vehicle according to the speed planning decision.

[0033] In this embodiment, the above-mentioned execution subject will determine the speed planning decision of the target vehicle relative to all obstacles based on the generated driving semantic decision. For example, the speed planning strategy can be determined by the quadratic speed planning problem, that is, the quadratic speed planning problem is solved and the obtained solution is used as the speed planning strategy. The quadratic speed planning problem here is the QP problem. The QP (Quadratic Programming) problem is to process the speed planning problem and solve a set of reasonable speeds, such as X1, X2, X3..., so as to complete the rushing / yielding processing of all obstacles. Finally, the driving speed of the target vehicle in the conflict zone is adjusted according to the obtained solution, thereby ensuring the safe driving of the vehicle.

[0034] In one example, the execution subject will first generate a rough solution by solving the optimal boundary value problem according to the semantic decision sequence corresponding to the driving semantic decision. Since the rough solution is processed one obstacle at a time sequence, the rough solutions will be pieced together in time sequence to obtain the initial solution. Then, the execution subject will optimize the initial solution to obtain the optimized solution, and use the optimized solution as the final solution (i.e., the speed planning decision). According to the speed planning decision, the target vehicle's driving speed is adjusted to control the ego vehicle and the obstacle vehicle to not appear in the conflict zone at the same time, so that the ego vehicle has the ability to predict and handle conflicts, so as to avoid collisions between the ego vehicle and the obstacle vehicle in the conflict zone.

[0035] The vehicle speed planning method provided by the embodiment of the present disclosure first determines the conflict zone where the planned trajectory and the predicted trajectory overlap based on the planned trajectory of the target vehicle and the predicted trajectory of the obstacle; then, a driving semantic decision tree is constructed based on the candidate decision results of the target vehicle in the conflict zone; then, the driving semantic decision tree is pruned according to a predetermined pruning condition, and a driving semantic decision for the target vehicle is generated according to the pruned decision tree; finally, the speed planning decision of the target vehicle relative to all obstacles is determined according to the driving semantic decision, and the driving speed of the target vehicle is adjusted according to the speed planning decision. Thus, a speed planning solution of the target vehicle in the conflict zone is generated, and the target vehicle completes the rushing / yielding processing of all obstacles, thereby controlling the self-vehicle and the obstacle vehicle to not appear in the conflict zone at the same time, so that the self-vehicle has the ability to predict and handle conflicts, so as to avoid collisions between the self-vehicle and the obstacle vehicle in the conflict zone, thereby improving the safety of vehicle driving.

[0036] In addition, in the technical solutions involved in the present disclosure, the acquisition, storage, use, processing, transportation, provision and disclosure of the vehicle speed, trajectory information, etc. are in compliance with the relevant laws and regulations and do not violate public order and good morals.

[0037] Continue to refer Figure 3 , Figure 3 A process 300 of a second embodiment of a vehicle speed planning method according to the present disclosure is shown. The vehicle speed planning method comprises the following steps: Step 301 : determining a conflict area where the planned trajectory and the predicted trajectory overlap based on the planned trajectory of the target vehicle and the predicted trajectory of the obstacle.

[0038] Step 301 is basically the same as step 101 of the aforementioned embodiment. The specific implementation method can refer to the aforementioned description of step 101, which will not be repeated here.

[0039] Step 302 , in response to determining that there are conflict zones between the target vehicle and multiple obstacles and that there are intersection areas between the multiple conflict zones, determine an initial decision result set of the target vehicle in the multiple conflict zones.

[0040] In this embodiment, the execution subject of the vehicle speed planning method, such as a server or a terminal device (such as a vehicle-mounted terminal), determines whether there is an intersection area between the vehicle (target vehicle) and multiple obstacles, that is, when there are multiple conflict areas. For example, the conflict area between the vehicle and obstacle A is area 1, and the conflict area between the vehicle and obstacle B is area 2. It is determined whether there is an intersection area between area 1 and area 2. If there is an intersection area between multiple conflict areas, an initial decision result set of the target vehicle in multiple conflict areas is generated, and the initial decision result of each conflict area includes grabbing and giving way. The initial decision results of multiple conflict areas are combined to obtain an initial decision result set.

[0041] As an example, the conflict zone between the vehicle and obstacle A is area 1, and the conflict zone between the vehicle and obstacle B is area 2, and there is an intersection area between area 1 and area 2. The initial decision result of the vehicle in area 1 can be overtaking and giving way, and the initial decision result of the vehicle in area 2 can also be overtaking and giving way. Therefore, the initial decision result set for the vehicle in area 1 and area 2 includes: overtaking and overtaking, overtaking and giving way, giving way and giving way, and giving way and overtaking.

[0042] Step 303, determining whether the initial decision result satisfies preset constraints based on the driving distance and driving time of the target vehicle in the process of executing the initial decision result.

[0043] In this embodiment, the execution subject will determine whether the initial decision result meets the preset constraint conditions according to the driving distance and driving time of the target vehicle in the process of executing the initial decision result. The constraint conditions here refer to whether the driving distance (s) and driving time (t) conflict. If not, the constraint conditions are met. It should be noted that here, it will be judged whether each initial decision result (such as the four initial decision results of rushing and rushing, rushing and giving way, giving way and giving way, giving way and rushing in the previous example) meets the constraint conditions.

[0044] As an example, further reference Figure 4-1 , Figure 4-1 The figure shows the decision results of near-end rushing and far-end yielding in the case of conflict zone intersection. Near-end rushing and far-end yielding means that the vehicle rushes in the near-end conflict zone and yields in the far-end conflict zone. The rushing is successful only when it passes the rear boundary, and the yielding is successful only when it passes the front boundary or before. Therefore, in this case, the near-end decision conflict boundary is the rear boundary, and the far-end decision conflict boundary is the front boundary. The execution process has information conflicts, which need special processing.

[0045] In this case, the front and rear intersecting conflicting areas are merged, and the rear boundary of the near-end conflicting area is moved forward to the position of the front boundary of the far-end conflicting area, that is, =

[0046] This process has risks. After the ego vehicle enters the near-end conflict area, it occupies the space area. Some people think that the overtaking is successful. The process of overtaking->yielding is as follows:

[0047] In the rough solution, if there is a margin on t, that is, there is a time difference between grabbing first and giving way later:

[0048] If the decision sequence is feasible, then the decision sequence is considered feasible, otherwise the sequence execution has no solution. That is, if there is a time difference between grabbing first and letting go later, the constraint condition is met, otherwise it is not met.

[0049] As another example, further reference Figure 4-2 , Figure 4-2 The figure shows the results of the decision of giving way near and rushing far in the case of intersection of conflict zones. Giving way near and rushing far means that the vehicle has to give way in the near-end conflict zone and rush in the far-end conflict zone. In this case, the near-end decision conflict boundary is the front boundary, and the far-end decision conflict boundary is the rear boundary. The execution process st information does not conflict, and it can be executed in sequence, that is, the constraints are met.

[0050] As another example, further reference Figure 4-3 , Figure 4-3 The figure shows the decision results of near-end rushing and far-end rushing in the case of intersection of conflict zones. Near-end rushing and far-end rushing means that the vehicle has to rush in the near-end conflict zone and also has to rush in the far-end conflict zone. At this time, the near-end decision conflict boundary is the rear boundary, and the far-end decision conflict boundary is the rear boundary. The execution process st information does not conflict, and it can be executed in sequence, that is, the constraints are met.

[0051] As another example, further reference Figure 4-4 , Figure 4-4 The figure shows the results of the near-give way and far-give way decision in the case of intersection of conflict zones. The near-give way and far-give way means that the vehicle has to give way in the near-end conflict zone and also in the far-end conflict zone. At this time, the near-end decision conflict boundary is the front boundary, and the far-end decision conflict boundary is the front boundary. The st information of the execution process does not conflict, and they can be executed in sequence, that is, the constraints are met.

[0052] In addition, when the front and back boundaries of a conflict zone (zone 1) contain the front and back boundaries of another conflict zone (zone 2), the processing of each decision result is the same as before ( Figure 4-1 , Figure 4-2 , Figure 4-3 , Figure 4-4 ) are the same and will not be repeated here. Figure 5-1 , Figure 5-1 The schematic diagram shows the decision results of the close-in grab and far-out decision-making when the conflict zone is included. The handling method of this situation is the same as Figure 4-1 The case shown is handled in the same way. Further references Figure 5-2 , Figure 5-2 The schematic diagram shows the decision results of the near-give-up and far-grab decision-making in the case of conflict zone inclusion. The handling method of this situation is the same as Figure 4-2 The case shown is handled in the same way. Further references Figure 5-3 , Figure 5-3 The schematic diagram shows the decision results of the near-seize and far-seize situations when the conflict zone is included. The handling method of this situation is the same as Figure 4-3 The case shown is handled in the same way. Further references Figure 5-4 , Figure 5-4 The schematic diagram shows the decision results of the near-give-way and far-give-way decision-making in the case of conflict zone inclusion. The handling method of this situation is the same as Figure 4-4 The situation shown is handled in the same way.

[0053] Step 304, in response to determining that the initial decision result meets the constraint condition, the initial decision result is determined to be a candidate decision result, and a set of candidate decision results is obtained.

[0054] In this embodiment, if it is determined that the initial decision result meets the constraint condition, the execution subject will determine the initial decision result as a candidate decision result, thereby obtaining a candidate decision result set. The st information in the execution process of the initial decision result is used as a constraint condition, and the decision results that do not meet the constraint condition are deleted, so as to obtain a candidate decision result set including all decision results that meet the constraint condition.

[0055] Step 305: construct a driving semantic decision tree based on the candidate decision result set.

[0056] In this embodiment, the execution subject constructs a driving semantic decision tree based on the candidate decision results in the candidate decision result set. The semantic decision tree constructed based on the candidate decision results in the candidate decision result set is a full binary tree, and the action of each layer of the driving semantic decision tree is the semantics of rushing or yielding. When there are multiple conflict zones, each branch of the semantic decision tree represents each conflict zone in the multiple conflict zones.

[0057] Step 306 , judging whether the candidate decision result of the target vehicle in the conflict zone satisfies the timing constraint and / or the speed limit constraint according to the distance between the obstacle and the conflict zone and the speed information of the obstacle.

[0058] In this embodiment, the execution subject will determine whether the candidate decision result meets the timing constraint and / or speed limit constraint based on the distance between the obstacle and the conflict zone and the speed information of the obstacle. Here, the timing constraint refers to the constraint on the order of execution time, and the speed limit constraint refers to the speed constraint on the vehicle. The timing constraint and speed limit constraint can be constructed in advance according to the actual situation.

[0059] Step 307 , in response to determining that the candidate decision result does not satisfy the timing constraint and / or the speed limit constraint, pruning the candidate decision result in the driving semantics decision tree.

[0060] In this embodiment, if it is determined that the candidate decision result does not meet the timing constraint and / or the speed limit constraint, the above-mentioned execution subject will prune the candidate decision result in the driving semantic decision tree. That is, if the candidate decision result does not meet at least one of the timing constraint and the speed limit constraint, it will be pruned, and the semantic decision sequence will be obtained according to the pruned semantic decision tree. According to the pruning operation, the unexecutable decision results are filtered out, and the speed of solving the speed planning solution is improved.

[0061] In one example, since there are timing constraints between the previous and subsequent semantic decisions in the semantic decision sequence corresponding to the driving semantic decision, pruning is performed if the timing constraints are obviously violated.

[0062] For example, first calculate the decision time of each interactive (cut-in) obstacle separately. For a specific obstacle A, the rush planning time ,

[0063] in, and are the distances from obstacle A to the front and rear boundaries of the conflict zone, respectively. is the speed of obstacle A.

[0064] Assume there is a decision sequence {B:yield, C:yield, D:rush}, calculate the planning time of each decision , and ,like: or

[0065] This means that after the vehicle has given way to obstacles B and C in sequence, it no longer has the time conditions to overtake obstacle D, and pruning should be performed at this time.

[0066] In one example, the semantic decision sequence that is obviously unexecutable under the speed limit constraint should be pruned.

[0067] Assuming a speed limit constraint , there is a decision sequence {B: rush, C: yield, D: rush}, and the conflict boundaries corresponding to the BC line grabbing semantic decisions are and , the corresponding time is and , then in and The maximum distance that the vehicle can reach is and :

[0068] in, To specify a series of specific types of speed limit values, is the ideal driving distance of the vehicle within the next t time under speed limit a.

[0069] if, < or < If any of the conditions is met, the vehicle still does not meet the conditions for overtaking under ideal conditions, and pruning should be performed.

[0070] Step 308: Determine a speed planning decision of the target vehicle relative to all obstacles according to the driving semantic decision, and adjust the driving speed of the target vehicle according to the speed planning decision.

[0071] Step 308 is basically the same as step 104 in the aforementioned embodiment. The specific implementation method can refer to the aforementioned description of step 104, which will not be repeated here.

[0072] from Figure 3 It can be seen that Figure 1 Compared with the corresponding embodiments, the vehicle speed planning method in this embodiment highlights the steps of constructing a driving semantic decision tree and pruning, that is, first judging whether the initial decision result satisfies the constraint conditions, so as to obtain a set of candidate decision results that satisfy the constraint conditions, and constructing a driving semantic decision tree based on the candidate decision result set, and pruning the candidate decision results in the driving semantic decision tree according to the timing constraints and speed limit constraints, thereby filtering out unexecutable decision results and improving the speed of solving the speed planning problem.

[0073] Continue to refer Figure 6 , Figure 6 A process 600 of a third embodiment of a vehicle speed planning method according to the present disclosure is shown. The vehicle speed planning method comprises the following steps: Step 601, according to the planned trajectory of the target vehicle and the predicted trajectory of the obstacle, determining a conflict area where the planned trajectory and the predicted trajectory overlap.

[0074] Step 601 is basically the same as step 101 of the aforementioned embodiment. The specific implementation method can refer to the aforementioned description of step 101, which will not be repeated here.

[0075] Step 602 , in response to determining that a conflict zone exists and the obstacle is in front of the current position of the target vehicle, determining the type of the obstacle is a front obstacle.

[0076] In this embodiment, the execution subject of the vehicle speed planning method, such as a server or terminal device (such as a vehicle-mounted terminal), after determining the conflict zone between the vehicle and the obstacle, further determines the position of the obstacle relative to the vehicle. If the obstacle is located in front of the current position of the vehicle, it is determined as the front obstacle (also called the path front following obstacle). That is, if the proximal front boundary of the conflict zone between the vehicle and the obstacle 0 and the far rear boundary For larger value , then the obstacle is defined as the obstacle following the path (referred to as the front obstacle), and the condition is expressed in the following form: &&

[0077] For such obstacles, the vehicle should follow the vehicle.

[0078] Step 603 , in response to determining that the type of the obstacle is a front obstacle and there are multiple front obstacles, determine a set of obstacles to be followed from the multiple front obstacles according to the distance between the target vehicle and the front obstacle and the distance between the multiple front obstacles.

[0079] In this embodiment, if the obstacle is determined to be a front obstacle and there are multiple front obstacles, the above-mentioned execution body will determine a set of obstacles to be followed from the multiple front obstacles according to the distance between the vehicle and the front obstacle and the distance between the multiple front obstacles.

[0080] Specifically, the execution subject will first sort all the front obstacles according to the distance between each front obstacle and the vehicle, for example, in ascending order, so as to obtain a sorted front obstacle set. Then, the sorted front obstacle set is clustered according to the distance between each front obstacle, so as to obtain multiple clustered obstacle clusters. Finally, the obstacle cluster closest to the vehicle is selected from the multiple clustered obstacle clusters, and the front obstacles in the obstacle cluster are used as the obstacle set V to be followed. Compared with selecting a single vehicle as the vehicle to be followed, the method of selecting the obstacle set to be followed takes into account the randomness of the movement of the vehicle in front, so as to effectively avoid the rear-end collision problem caused by the untimely switching of the front following vehicle.

[0081] Step 604 , in response to determining that a conflict zone exists and the obstacle is behind the current position of the target vehicle, determining the type of the obstacle is a rear obstacle.

[0082] In this embodiment, after determining that there is a conflict zone between the ego vehicle and the obstacle, the above-mentioned execution subject will further determine the position of the obstacle relative to the ego vehicle. If the obstacle is located behind the current position of the ego vehicle, it will be determined as a rear obstacle (also called a path rear following obstacle). That is, when the obstacle is located behind the current position of the ego vehicle, and the obstacle's trajectory and the ego vehicle's historical planning trajectory have a conflict zone, the obstacle is defined as a rear obstacle. The conditions can be expressed as follows:

[0083] in, Represents the intersection of the obstacle's trajectory and the vehicle's trajectory.

[0084] For such obstacles, appropriate protection should be provided to prevent rear-end collisions, taking into account the following situation.

[0085] Step 605 , in response to determining that the obstacle type is a rear obstacle and there are multiple rear obstacles, determine the maximum braking deceleration of the target vehicle according to the distance between the target vehicle and the rear obstacle and the speed of the target vehicle.

[0086] In this embodiment, if the obstacle is determined to be a rear obstacle and there are multiple rear obstacles, the above-mentioned execution subject will determine the maximum braking deceleration of the target vehicle according to the distance between the target vehicle and the rear obstacle and the speed of the target vehicle. Specifically, the maximum braking deceleration of the ego vehicle (target vehicle) estimated based on the counterfactual inference method can be expressed as:

[0087] in, To counterfactually infer the maximum braking deceleration of the vehicle, is the speed of the ego vehicle (target vehicle), is the minimum safe distance, is the speed of the backward obstacle, is the maximum braking deceleration of the rear obstacle, is the distance between the vehicle and the rear obstacle at the current moment.

[0088] Considering the rear obstacle protection strategy, the vehicle to be protected behind the path must meet the general principle: there is a possibility of collision between the rear obstacle vehicle and the vehicle. Specifically: First, define the set open_set, sort multiple rear obstacles in ascending order according to the distance between the rear obstacles and the vehicle, and put the sorted rear obstacles into open_set; then, define the set close_set, put the first rear obstacle in open_set into close_set, traverse open_set, and determine whether the elements in open_set have no horizontal overlap with all elements in close_set. If so, put the element into close_set; otherwise, remove it from open_set; finally, traverse close_set and calculate , take all The maximum value in is used as the lower limit of the maximum braking deceleration of the vehicle. Compared with selecting a single obstacle as the protection vehicle, the advantage of this method is that it can effectively avoid the problem of information feature loss caused by selecting a single vehicle and only considering the distance / speed factors, thereby avoiding the occurrence of rear-end collisions with the following vehicles.

[0089] In one example, when the proximal front boundary of the collision zone between the ego vehicle and the obstacle is greater than a smaller threshold If the far rear boundary is smaller than the larger value of the rear end, the obstacle is defined as a lateral cut-in obstacle. The condition can be expressed as: &&

[0090] For such obstacles, the decision of overtaking / yielding should be considered comprehensively and then the response trajectory should be planned.

[0091] In one example, when the proximal front boundary of the collision zone between the ego vehicle and the obstacle is greater than a smaller threshold and the distal rear boundary is a larger value, the obstacle is defined as a sideways cut-in obstacle. The condition can be expressed as: &&

[0092] For this type of obstacle, special treatment should be given. This type of obstacle should have two states: a. Maintain the initial conflict area information; b. Correct the conflict area information. After correcting the conflict area of ​​the vehicle, the boundary is a finite value. The conflict area information is corrected to .

[0093] In one example, when the semantic decision of the obstacle cut-in is to rush in the decision sequence, the conflict area information is modified. ; When the semantic decision of the obstacle cut-in is to yield in the decision sequence, after the ego vehicle executes the yield decision, the distance of the obstacle in front of the ego vehicle path in the worst case is , the distance can be used as the current relative distance, and the cut-in obstacle can be used as the obstacle in front of the path for following the vehicle. By performing special processing on the cut-in obstacle, the problem of solution failure caused by insufficient yield topological space in the prior art is solved, and the success rate of the solution is improved.

[0094] Step 606 , constructing a driving semantic decision tree based on the candidate decision results of the target vehicle in the conflict zone.

[0095] Step 607: prune the driving semantics decision tree according to a predetermined pruning condition, and generate a driving semantics decision for the target vehicle according to the pruned decision tree.

[0096] Steps 606-607 are basically consistent with steps 102-103 of the aforementioned embodiment. For specific implementation methods, reference may be made to the aforementioned description of steps 102-103, which will not be repeated here.

[0097] Step 608 , according to the semantic decision sequence corresponding to the driving semantic decision, a rough solution to the quadratic speed planning problem is determined by solving the optimal boundary value problem.

[0098] In this embodiment, the above-mentioned execution subject generates a semantic decision sequence corresponding to the driving semantic decision, and determines the rough solution of the secondary speed planning problem by solving the optimal boundary value problem (OBVP) according to the semantic decision sequence. The optimal boundary value problem can also be called the two-point boundary value optimal control problem, which is a motion planning algorithm under dynamic constraints. The algorithm solves the optimal expression by giving the initial state and the terminal state. When solving, this embodiment selects a spline curve as the state transfer function, and the number of spline curve connection segments is determined according to the length of the semantic decision sequence.

[0099] That is, by giving the input of the optimal boundary value problem: the starting point state, the ending point state and the state transfer equation, the output of the optimal boundary value problem can be obtained by solving it: the state expression with the minimum cost function that conforms to the transfer equation.

[0100] In some optional implementations of the present embodiment, step 608 includes: solving the secondary velocity planning problem according to the distance between the current position of the target vehicle and each conflict zone, the speed and acceleration of the target vehicle at the proximal front boundary of each conflict zone, and the speed and acceleration of the target vehicle at the distal rear boundary of each conflict zone to obtain multiple initial solutions, wherein the number of segments of the initial solution is obtained according to the length of the semantic decision sequence; and splicing the multiple initial solutions to obtain a rough solution.

[0101] Specifically, assuming that the length of the semantic decision sequence is n, then the number of spline curve connection segments is n+1, and the definition is: Segment start status for:

[0102] Segment end status :for:

[0103] Joint Status for:

[0104] in, , and They are the planned forward distance of the vehicle in the initial state (i.e. the forward distance from the initial state of the vehicle to the current position), speed and acceleration, , and They are the planned forward distance of the terminal state vehicle (i.e. the forward distance from the terminal state of the vehicle to the current position), speed and acceleration,

[0105] Define the transfer matrix for:

[0106] in, Plan the length of time for this segment.

[0107] Spline parameters for:

[0108] There is an initial solution:

[0109] Finally, the initial solutions of each segment are connected end to end to form a rough solution, specifically: The length of planning time for each segment The definition is as follows:

[0110] in, is the distance between the k-segment obstacles and the boundary after the conflict, is the distance between k obstacles and the boundary before the conflict, v is the obstacle speed, and D is the semantic decision of the ego vehicle.

[0111] For the first paragraph: The starting state is the current initial state of the vehicle for:

[0112] Terminal state:

[0113] Therefore:

[0114] For a certain section in the middle: The starting state is the ending state of the previous segment:

[0115] Terminal state:

[0116] Therefore:

[0117] For the end segment: The starting state is the ending state of the previous segment:

[0118] The generation of the end segment solution can be generated by a simple IDM (Intelligent Driver Model) follow-up.

[0119] Since the initial solution calculation processes obstacles one by one in time sequence, they need to be processed one by one and then pieced together in time sequence to obtain a rough solution.

[0120] Step 609, optimizing the rough solution according to the planning period of the target vehicle, using the obtained optimized solution as the speed planning decision, and adjusting the driving speed of the target vehicle according to the speed planning decision.

[0121] In this embodiment, the above-mentioned execution subject will optimize the rough solution according to the planning cycle of the target vehicle to obtain the optimized solution, and use the optimized solution as the speed planning decision. It should be noted that an optimized solution can be obtained by optimizing a rough solution, and when there are multiple rough solutions, multiple optimized solutions can be obtained through multiple optimizations. Then, the most suitable optimized solution is determined from all the optimized solutions as the final optimized solution, for example, the optimized solution with the smallest objective function is selected as the final optimized solution. Finally, the driving speed of the target vehicle is adjusted according to the determined optimized solution, so as to deal with conflicts with other vehicles, avoid collisions with other vehicles, and improve the safety of vehicle driving.

[0122] In some optional implementations of this embodiment, step 609 includes: generating an equality constraint in the time domain according to the planning cycle of the target vehicle, specifically: Assuming that the minimum cycle of vehicle planning is Δt, finite Taylor expansion, we have:

[0123] Likewise, assuming is a fixed constant, we have:

[0124] make:

[0125] have:

[0126] In the optimization time domain, there are equality constraints:

[0127] Among them, the status , for:

[0128] Step 609 also includes: constructing inequality constraints, wherein the inequality constraints include: boundary constraints of the target vehicle in the conflict zone, speed limit constraints obtained according to the maximum braking deceleration, and / or following constraints for the set of obstacles to be followed.

[0129] The inequality constraints here include: first-order inequality constraints, second-order inequality constraints and third-order inequality constraints. The first-order inequality constraints include prohibition of reversing constraints, boundary constraints in the conflict zone, and following constraints (for the set of obstacles to be followed). The second-order inequality constraints include speed limit constraints. The third-order inequality constraints include vehicle motion constraints (greater than the maximum braking deceleration and less than the maximum executable acceleration). Specifically: (1) First-order inequality constraints: First-order inequality constraints mainly refer to the s-boundary constraints and the prohibition of reversing constraints in all conflicting areas of the full plane, as follows: A. Reverse prohibition Driving plan prohibits reversing when:

[0130] B. Conflict Area Boundary Constraints

[0131] After a decision sequence is given, each decision moment must satisfy the boundary s constraint. For example, given the following decision sequence and its corresponding boundary constraint:

[0132] For the s boundary constraint, the ego vehicle is , , ...., The time should be:

[0133] In general, speed constraints need to be introduced. For example, the speed of the vehicle should be higher than the speed of the obstacle in the overtaking state, and lower than the speed of the obstacle in the yielding state. However, these constraints are not added in this embodiment because: (1) the conflict area ensures spatiotemporal safety, and the s boundary constraint can represent this point; (2) overtaking considers relative distance and relative speed, and constraining only the speed is too strong.

[0134] C. Following Constraints

[0135] For the obstacles to be followed on the path, predict their future driving trajectories and generate s boundary constraints, which are:

[0136] (2) Second-order inequality constraints: Second-order inequality constraints mainly refer to road environment speed limits and other speed limit constraints. For example, suppose there is a speed limit constraint that the road speed limit is ,have:

[0137] (3) Third-order inequality constraints: Third-order inequality constraints mainly refer to vehicle motion constraints. Assume that the maximum executable deceleration of the vehicle is -6 , the maximum executable acceleration is 3 ,have:

[0138] In addition, an objective function, also known as a cost function, is constructed. The cost function considers three categories: comfort cost; rear protection cost; efficiency cost; A. Comfort cost The comfort cost takes into account the acceleration cost and the jerk cost (the cost caused by the rate of change of vehicle acceleration), which is:

[0139] B. Efficiency cost

[0140] The efficiency cost takes into account the current road recommended speed. Assume that the current road recommended speed is ,have:

[0141] C. Backward protection cost

[0142] The rearward protection cost protects the rearward vehicle within a limited frame to prevent rear-end collision. Assume that the maximum deceleration of the rearward protection is ,have:

[0143] in, , , They are acceleration cost, jerk cost, recommended speed cost and backward protection cost weights respectively, and K is the number of frames in which backward protection takes effect.

[0144] Step 609 also includes: optimizing the rough solution according to the constructed equality constraints, inequality constraints and objective function to obtain an optimized solution. That is, the rough solution is optimized by the above-constructed constraint conditions and objective function to obtain a final optimized solution, and the driving speed of the target vehicle is adjusted according to the optimized solution, thereby improving the safety of vehicle driving.

[0145] from Figure 6 It can be seen that Figure 3 Compared with the corresponding embodiments, the vehicle speed planning method in this embodiment processes obstacles differently according to their different types, and adopts a sampling form of semantic decision-making, thereby improving the success rate of the solution, thereby avoiding collisions between the vehicle and obstacle vehicles in the conflict area, and improving the safety of vehicle driving.

[0146] Further references Figure 7 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a vehicle speed planning device, and the device embodiment is Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0147] like Figure 7As shown, the vehicle speed planning device 700 of this embodiment includes: a determination module 701, a construction module 702, a pruning module 703 and a planning module 704. The determination module 701 is configured to determine the conflict area where the planned trajectory and the predicted trajectory overlap according to the planned trajectory of the target vehicle and the predicted trajectory of the obstacle; the construction module 702 is configured to construct a driving semantic decision tree based on the candidate decision results of the target vehicle in the conflict area; the pruning module 703 is configured to prune the driving semantic decision tree according to a predetermined pruning condition, and generate a driving semantic decision for the target vehicle according to the pruned decision tree; the planning module 704 is configured to determine the speed planning decision of the target vehicle relative to all obstacles according to the driving semantic decision, and adjust the driving speed of the target vehicle according to the speed planning decision.

[0148] In this embodiment, the specific processing of the determination module 701, the construction module 702, the pruning module 703 and the planning module 704 in the vehicle speed planning device 700 and the technical effects thereof can be referred to respectively. Figure 1 The relevant descriptions of steps 101 - 104 in the corresponding embodiment are not repeated here.

[0149] In some optional implementations of the present embodiment, the vehicle speed planning device 700 also includes: a decision module, configured to determine a set of initial decision results of the target vehicle in multiple conflict zones in response to determining that a conflict zone exists between the target vehicle and multiple obstacles and that multiple conflict zones exist in an intersection area, wherein the initial decision results in the initial decision result set are to cut in or give way; a constraint module, configured to determine whether the initial decision result meets a preset constraint condition based on the driving distance and driving time of the target vehicle in the process of executing the initial decision result; a candidate module, configured to determine that the initial decision result is a candidate decision result in response to determining that the initial decision result meets the constraint condition, and obtain a set of candidate decision results; and a construction module is further configured to: construct a driving semantic decision tree based on the set of candidate decision results.

[0150] In some optional implementations of this embodiment, the pruning module is further configured to: determine whether the candidate decision results of the target vehicle in the conflict zone meet the timing constraints and / or speed limit constraints based on the distance between the obstacle and the conflict zone and the speed information of the obstacle; in response to determining that the candidate decision results do not meet the timing constraints and / or speed limit constraints, prune the candidate decision results in the driving semantic decision tree.

[0151] In some optional implementations of this embodiment, the planning module includes: a rough solution sub-module, configured to determine a rough solution to the secondary speed planning problem by solving an optimal boundary value problem according to a semantic decision sequence corresponding to the driving semantic decision; an optimized solution sub-module, configured to optimize the rough solution according to a planning cycle of the target vehicle, and use the obtained optimized solution as the speed planning decision.

[0152] In some optional implementations of the present embodiment, the rough solution submodule is further configured to: solve the quadratic velocity planning problem according to the distance between the current position of the target vehicle and each conflict zone, the speed and acceleration of the target vehicle at the proximal front boundary of each conflict zone, and the speed and acceleration of the target vehicle at the distal rear boundary of each conflict zone to obtain multiple segments of initial solutions, wherein the number of segments of the initial solution is obtained according to the length of the semantic decision sequence; and splice the multiple segments of the initial solution to obtain a rough solution.

[0153] In some optional implementations of this embodiment, the optimization solution submodule is further configured to: generate equality constraints in the time domain according to the planning cycle of the target vehicle; construct inequality constraints, wherein the inequality constraints include: boundary constraints of the target vehicle in the conflict zone, speed limit constraints obtained according to the maximum braking deceleration and / or following constraints for the set of obstacles to be followed; optimize the rough solution according to the equality constraints, inequality constraints and the objective function to obtain an optimized solution.

[0154] In some optional implementations of this embodiment, the vehicle speed planning device 700 also includes: a to-be-followed obstacle determination module, configured to, in response to determining that there is a conflict zone and the obstacle is in front of the current position of the target vehicle, determine the type of the obstacle as a front obstacle; in response to determining that the type of the obstacle is a front obstacle and there are multiple front obstacles, determine a set of obstacles to be followed from multiple front obstacles based on the distance between the target vehicle and the front obstacle and the distance between the multiple front obstacles.

[0155] In some optional implementations of this embodiment, the vehicle speed planning device 700 also includes: a deceleration determination module, configured to determine that the type of obstacle is a rear obstacle in response to determining that there is a conflict zone and the obstacle is behind the current position of the target vehicle; in response to determining that the obstacle type is a rear obstacle and there are multiple rear obstacles, determine the maximum braking deceleration of the target vehicle based on the distance between the target vehicle and the rear obstacle and the speed of the target vehicle.

[0156] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, a computer program product and an autonomous driving vehicle.

[0157] Figure 8A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers and other suitable devices with computing functions. The electronic device can also represent various forms of mobile devices suitable for performing calculations. In particular, the electronic device can also be an electronic device integrated in a vehicle, such as a vehicle computer.

[0158] The components shown herein, their connections and relationships, and their functions, are intended only as examples, and are not meant to limit implementations of the disclosure described and / or claimed herein.

[0159] like Figure 8 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 to a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0160] Multiple components in the electronic device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc. It should be understood that the input and output units listed here are only examples that exist in some special scenarios. In some other application scenarios, the input and output units can be in other forms. For example, when the device is a car device, the input unit can be a touch screen, a rotary button, etc.

[0161] The communication unit 809 , such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0162] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as the speed planning method of the vehicle. For example, in some embodiments, the speed planning method of the vehicle may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the speed planning method of the vehicle described above may be executed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the speed planning method of the vehicle in any other appropriate manner (e.g., by means of firmware).

[0163] The autonomous driving vehicle provided by the present disclosure may include: Figure 8 The electronic device shown above can implement the vehicle speed planning method described in any of the above embodiments when executed by its processor.

[0164] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0165] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0166] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0167] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0168] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0169] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0170] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0171] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A vehicle speed planning method, comprising: According to the planned trajectory of the target vehicle and the predicted trajectory of the obstacle, determining a conflict area where the planned trajectory and the predicted trajectory overlap; Building a driving semantic decision tree based on candidate decision results of the target vehicle in the conflict zone; Pruning the driving semantics decision tree according to a predetermined pruning condition, and generating a driving semantics decision for the target vehicle according to the pruned decision tree; A speed planning decision of the target vehicle relative to all the obstacles is determined according to the driving semantic decision, and a driving speed of the target vehicle is adjusted according to the speed planning decision.

2. The method according to claim 1, wherein: The method further comprises: In response to determining that there are conflict zones between the target vehicle and multiple obstacles and that there are intersection zones between the multiple conflict zones, determining an initial decision result set for the target vehicle in the multiple conflict zones, wherein an initial decision result in the initial decision result set is to cut in or give way; Determining whether the initial decision result satisfies a preset constraint condition according to the driving distance and driving time of the target vehicle in the process of executing the initial decision result; In response to determining that the initial decision result meets the constraint condition, determining the initial decision result as a candidate decision result, and obtaining a set of candidate decision results; and The step of constructing a driving semantic decision tree based on candidate decision results of the target vehicle in the conflict zone includes: The driving semantics decision tree is constructed based on the candidate decision result set.

3. The method according to claim 1 or 2, wherein: The step of pruning the driving semantics decision tree according to a predetermined pruning condition includes: Determining whether a candidate decision result of the target vehicle in the conflict zone satisfies a timing constraint and / or a speed limit constraint according to the distance between the obstacle and the conflict zone and the speed information of the obstacle; In response to determining that the candidate decision result does not satisfy the timing constraint and / or the speed limit constraint, the candidate decision result is pruned in the driving semantics decision tree.

4. The method according to claim 1, wherein: Determining the speed planning decision of the target vehicle relative to all the obstacles according to the driving semantic decision includes: Determining a rough solution to the quadratic speed planning problem by solving an optimal boundary value problem according to a semantic decision sequence corresponding to the driving semantic decision; The rough solution is optimized according to the planning period of the target vehicle, and the obtained optimized solution is used as the speed planning decision.

5. The method according to claim 4, wherein: The determining of a rough solution to the secondary speed planning problem by solving an optimal boundary value problem according to the semantic decision sequence corresponding to the driving semantic decision includes: According to the distance between the current position of the target vehicle and each conflict zone, the speed and acceleration of the target vehicle at the proximal front boundary of each conflict zone, and the speed and acceleration of the target vehicle at the distal rear boundary of each conflict zone, the secondary speed planning problem is solved to obtain multiple segments of initial solutions, wherein the number of segments of the initial solution is obtained according to the length of the semantic decision sequence; The multiple segments of initial solutions are spliced ​​together to obtain the rough solution.

6. The method according to claim 4 or 5, wherein: The optimizing the rough solution according to the planning period of the target vehicle includes: Generate an equality constraint in the time domain according to the planning cycle of the target vehicle; Constructing inequality constraints, wherein the inequality constraints include: a boundary constraint of the target vehicle in the conflict zone, a speed limit constraint obtained according to a maximum braking deceleration, and / or a following constraint for a set of obstacles to be followed; The rough solution is optimized according to the equality constraint, the inequality constraint and the objective function to obtain an optimized solution.

7. The method according to claim 6, wherein: The method further comprises: In response to determining that the conflict zone exists and the obstacle is in front of the current position of the target vehicle, determining that the type of the obstacle is a front obstacle; In response to determining that the type of the obstacle is the front obstacle and there are multiple front obstacles, the set of obstacles to be followed is determined from the multiple front obstacles according to the distance between the target vehicle and the front obstacle and the distances between the multiple front obstacles.

8. The method according to claim 6, wherein: The method further comprises: In response to determining that the conflict zone exists and the obstacle is behind the current position of the target vehicle, determining that the type of the obstacle is a rear obstacle; In response to determining that the obstacle type is the rear obstacle and there are a plurality of rear obstacles, the maximum braking deceleration of the target vehicle is determined according to the distance between the target vehicle and the rear obstacle and the speed of the target vehicle.

9. A vehicle speed planning device, comprising: A determination module is configured to determine, based on the planned trajectory of the target vehicle and the predicted trajectory of the obstacle, a conflict area where the planned trajectory and the predicted trajectory overlap; A building module is configured to build a driving semantic decision tree based on candidate decision results of the target vehicle in the conflict zone; A pruning module is configured to prune the driving semantics decision tree according to a predetermined pruning condition, and generate a driving semantics decision for the target vehicle according to the pruned decision tree; A planning module is configured to determine a speed planning decision of the target vehicle relative to all the obstacles according to the driving semantic decision, and adjust the driving speed of the target vehicle according to the speed planning decision.

10. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

11. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 8.

12. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 8.

13. An autonomous driving vehicle comprising the electronic device as claimed in claim 10.

Images