Trajectory planning method, device and electronic equipment

Abstract

The present disclosure provides a trajectory planning method, device, and electronic device, which relate to the field of data processing technology, and more specifically, to the field of autonomous driving technology. A specific implementation scheme is as follows: when an interaction between a vehicle and a first obstacle is detected, a first state at a first moment and M first behavior combinations within a first time period are obtained; based on the first state and the M first behavior combinations, M second states at a second moment at the end of the first time period are determined; based on the first state and the M second states, a first game tree is constructed, wherein the first state is the state of the first node of the first game tree, the second state is the state of the second node of the first game tree, and the second node is a child node of the first node; and when the interaction between the vehicle and the first obstacle is detected to have ended, a driving trajectory of the vehicle is planned based on the first game tree.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, in particular to the field of autonomous driving technology, and specifically to a trajectory planning method, device, and electronic device. Background Art

[0002] Vehicles, such as autonomous vehicles, need to plan safe and reasonable driving trajectories while interacting with surrounding traffic participants, which is very important in the field of autonomous driving.

[0003] Currently, the trajectory planning method for autonomous vehicles usually uses the predicted trajectories of surrounding traffic participants to plan the vehicle's driving trajectory. Summary of the Invention

[0004] The present disclosure provides a trajectory planning method, device, and electronic device.

[0005] According to a first aspect of the present disclosure, a trajectory planning method is provided, comprising:

[0006] When an interaction between the vehicle and the first obstacle is detected, a first state at a first moment and M first behavior combinations within a first time period are obtained, where the first state includes: driving states of the vehicle and the first obstacle at the first moment, respectively; the first behavior combinations include: driving behaviors of the vehicle and the first obstacle within the first time period, respectively; the first time period is a time period starting from the first moment and having a preset duration, where M is a positive integer;

[0007] Determining, based on the first state and the M first behavior combinations, M second states at a second moment at the end of the first time period, the second states comprising: simulated driving states of the vehicle and the first obstacle after each of them performs the driving behaviors according to the first behavior combinations;

[0008] Constructing a first game tree based on the first state and the M second states, where the first state is a state of a first node of the first game tree, the second state is a state of a second node of the first game tree, and the second node is a child node of the first node;

[0009] When it is detected that the interaction between the vehicle and the first obstacle ends, a driving trajectory of the vehicle is planned based on the first game tree.

[0010] According to a second aspect of the present disclosure, a trajectory planning device is provided, comprising:

[0011] A first acquisition module is configured to, upon detecting interaction between the vehicle and the first obstacle, acquire a first state at a first moment and M first behavior combinations within a first time period, wherein the first state includes: driving states of the vehicle and the first obstacle, respectively, at the first moment; and the first behavior combinations include: driving behaviors of the vehicle and the first obstacle, respectively, within the first time period, wherein the first time period is a time period starting from the first moment and having a preset duration, and M is a positive integer;

[0012] a determination module configured to determine, based on the first state and the M first behavior combinations, M second states at a second moment at the end of the first time period, the second states comprising simulated driving states of the vehicle and the first obstacle after each of the vehicle and the first obstacle performs the driving behaviors according to the first behavior combinations;

[0013] A first construction module is configured to construct a first game tree based on the first state and the M second states, wherein the first state is a state of a first node of the first game tree, the second state is a state of a second node of the first game tree, and the second node is a child node of the first node;

[0014] A trajectory planning module is used to plan the driving trajectory of the vehicle based on the first game tree when it is detected that the interaction between the vehicle and the first obstacle ends.

[0015] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0016] at least one processor; and

[0017] a memory communicatively connected to at least one processor; wherein,

[0018] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform any one of the methods in the first aspect.

[0019] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute any one of the methods in the first aspect.

[0020] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, which implements any one of the methods in the first aspect when executed by a processor.

[0021] According to a sixth aspect of the present disclosure, an autonomous driving vehicle is provided, comprising the electronic device as described in the third aspect.

[0022] The technology disclosed in the present invention solves the problem of relatively low accuracy in trajectory planning for autonomous vehicles and improves the accuracy of trajectory planning for autonomous vehicles.

[0023] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0025] Figure 1 is a flow chart of a trajectory planning method according to the first embodiment of the present disclosure;

[0026] Figure 2 This is a schematic diagram of the structure of the first game tree;

[0027] Figure 3 is a structural diagram of a trajectory planning device according to a second embodiment of the present disclosure;

[0028] Figure 4 is a schematic block diagram of an example electronic device for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize 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.

[0030] First embodiment

[0031] like Figure 1 As shown, the present disclosure provides a trajectory planning method, comprising the following steps:

[0032] Step S101: When interaction between a vehicle and a first obstacle is detected, a first state at a first moment and M first behavior combinations within a first time period are obtained, where the first state includes: driving states of the vehicle and the first obstacle, respectively, at the first moment; and the first behavior combinations include: driving behaviors of the vehicle and the first obstacle, respectively, within the first time period, where the first time period is a time period starting from the first moment and lasting a preset length of time.

[0033] Step S102: Based on the first state and the M first behavior combinations, determining M second states at a second moment at the end of the first time period, wherein the second states include simulated driving states of the vehicle and the first obstacle after each of the vehicle and the first obstacle performs the driving behaviors of the first behavior combinations.

[0034] Step S103: constructing a first game tree based on the first state and the M second states, where the first state is the state of the first node of the first game tree, the second state is the state of the second node of the first game tree, and the second node is a child node of the first node;

[0035] Step S104: When it is detected that the interaction between the vehicle and the first obstacle ends, a driving trajectory of the vehicle is planned based on the first game tree.

[0036] Wherein, M is a positive integer.

[0037] In this embodiment, the trajectory planning method relates to the field of data processing technology, and in particular to the field of autonomous driving technology, and can be widely applied in autonomous driving scenarios. The trajectory planning method of the disclosed embodiment can be executed by the trajectory planning device of the disclosed embodiment. The trajectory planning device of the disclosed embodiment can be configured in any electronic device to execute the trajectory planning method of the disclosed embodiment. The electronic device can be deployed in an autonomous driving vehicle to perform trajectory planning for the autonomous driving vehicle.

[0038] In step S101, the vehicle may be an autonomous driving vehicle, which may be referred to as a master vehicle, and the first obstacle may be an obstacle around the master vehicle, which may be a motor vehicle, which may be referred to as a slave vehicle.

[0039] The trajectory planning device can detect whether there are any slave vehicles interacting with the master vehicle. If so, the device can plan the master vehicle's trajectory for safe driving. Specifically, the trajectory planning device can determine whether the master vehicle is interacting with any of the surrounding slave vehicles by detecting their positions, driving status, and other information. For example, if the two vehicles are detected to be relatively close, or if a slave vehicle's acceleration is relatively high, then interaction can be determined.

[0040] When interaction between the vehicle and the first obstacle is detected, a first state at a first moment and M first behavior combinations within a first time period can be obtained, where the first moment can be the moment t0 when the interaction between the vehicle and the first obstacle begins, or can be a moment during the interaction between the vehicle and the first obstacle.

[0041] In an alternative embodiment, the first time t1 may be t0 + L * step length T, where L is a positive integer. When the first time is t0, the first state at the first time can be referred to as the initial state, which includes the driving state of the host vehicle and the first obstacle at time t0, and may also include the positions of the host vehicle and the first obstacle at time t0. The driving state may include speed, acceleration, angle, angular velocity, etc.

[0042] When interaction between the host vehicle and the first obstacle is detected, a first game tree for the interaction between the host vehicle and the first obstacle can be constructed, and the initial state is used as the node state of the root node of the first game tree. The number of layers in the first game tree is determined based on the interaction time between the host vehicle and the first obstacle. The longer the interaction time, the more layers there are. The number of nodes in each layer is determined by the number of first behavior combinations (M) consisting of the host vehicle's driving behavior at the first moment and the first obstacle's driving behavior at the first moment.

[0043] Different first moments correspond to different levels of the first game tree. For example, when the first moment is t0, it corresponds to the root node, and the node state of the root node is the initial state of the main vehicle and the first obstacle at t0. When the first moment is (t0 + step length T), it corresponds to the first-level node in the first game tree, and the node state of the node is the state of the main vehicle and the first obstacle at (t0 + step length T), and so on.

[0044] The trajectory planning device can obtain the first states of the host vehicle and the first obstacle at the first moment respectively through an existing or new detection method.

[0045] The first time period may be a time period starting from the first moment and lasting for a preset time period, where the preset time period may be a step length T. The first time period may be different depending on the first moment. For example, if the first moment is t0, the first time period may be a time period between t0 and (t0 + step length T).

[0046] The M first behavior combinations can be combinations of the driving behaviors of the host vehicle and the first obstacle, respectively, within a first time period. At least one possible driving behavior of the host vehicle and at least one possible driving behavior of the first obstacle can be obtained for the driving scenario corresponding to the first moment. The at least one possible driving behavior of the host vehicle and the at least one possible driving behavior of the first obstacle are combined to obtain M first behavior combinations. Each first behavior combination includes a driving behavior determined by the host vehicle and a driving behavior determined by the first obstacle. The driving behaviors may include, for example, longitudinal acceleration and lateral angular velocity of the vehicle's head.

[0047] For example, at least one driving behavior that the main vehicle may decide includes driving behavior A1 and driving behavior A2, and at least one driving behavior that the first obstacle may decide includes driving behavior B1 and driving behavior B2. Then the M first behavior combinations include (A1, B1), (A1, B2), (A2, B1) and (A2, B2).

[0048] Different first moments may correspond to different driving scenarios. For example, when the first moment is t0, the corresponding scenario is a straight-ahead scenario, while when the first moment is (t0 + step length T), the corresponding driving scenario is an intersection scenario. Accordingly, the first behavior combinations may be different, and the number of first behavior combinations, M, may also be different.

[0049] In step S102, the second time t2 may be the time at the end of the first time period, that is, time (t1 + step length T). For each first behavior combination, the driving state of the host vehicle at time t1 may be used to simulate the host vehicle driving under the determined driving behavior, and the driving state of the host vehicle at the second time after step length T may be calculated. Furthermore, the driving state of the first obstacle at time t1 may be used to simulate the first obstacle driving under the determined driving behavior, and the driving state of the first obstacle at the second time after step length T may be calculated. Accordingly, a second state corresponding to the first behavior combination may be obtained, thereby obtaining M second states.

[0050] In step S103, the first state can be used as the node state of the first node of the first game tree, and the second state can be used as the node state of the second node of the first game tree. The second node can be a child node of the first node, that is, the first node is the parent node of the second node, and the number of child nodes of the first node can be M.

[0051] It should be noted that step S101, step S102 and step S103 are the process of constructing a group of parent-child nodes in the first game tree. All parent-child nodes in the first game tree can be constructed in the above manner until it is detected that the interaction between the main vehicle and the first obstacle is completed, and the first game tree for the interaction between the main vehicle and the first obstacle can be obtained accordingly.

[0052] Figure 2 This is a structural diagram of the first game tree, such as Figure 2 As shown, the relationship between the root node of the first game tree and the first-layer nodes can be a set of parent-child nodes. The node state of the root node can be represented by S0, and the node state of the first-layer nodes can be represented by Indicates that j can be the label of the child node. For each node in the first layer, the nodes connected to it in the second layer can also be a set of parent and child nodes. The node status of the second layer node can be expressed as It indicates that as the interaction between the main vehicle and the first obstacle proceeds, the above process of constructing the parent-child node is repeated until the interaction between the main vehicle and the first obstacle ends.

[0053] In step S104, the trajectory planning device can determine whether the interaction between the main vehicle and the first obstacle is completed by detecting the positions of the main vehicle and the slave vehicle, the driving status of the main vehicle and the slave vehicle, and other information. When it is detected that the interaction between the vehicle and the first obstacle is completed, the driving trajectory of the main vehicle can be planned based on the constructed first game tree.

[0054] Since the first game tree reflects the driving behavior and driving status of the host vehicle and the first obstacle during the interactive simulation process, the interaction between the host vehicle and the obstacle can be fully considered during the trajectory planning of the host vehicle based on the first game tree, so that a safe and reasonable driving trajectory can be planned for the host vehicle, thereby improving the accuracy of trajectory planning for the autonomous driving vehicle.

[0055] Optionally, step S104 specifically includes:

[0056] When it is detected that the interaction between the vehicle and the first obstacle ends, determining a target leaf node from the first game tree;

[0057] Determine a first node set, where the first node set includes nodes arranged along a path from a root node to the target leaf node in the first game tree;

[0058] A target driving trajectory of the vehicle is determined based on the driving status of the vehicle corresponding to the first node set at each moment and the driving behavior of the vehicle under the path corresponding to the first node set.

[0059] In this embodiment, upon detecting that the interaction between the host vehicle and the first obstacle has ended, a target leaf node can be determined from the first game tree based solely on the node status of the leaf node in the first game tree. The leaf node can be a node at the last level of the first game tree. Alternatively, the target leaf node can be determined from the first game tree based on at least one of the driving status, position, and driving behavior of the vehicle and the first obstacle along the first path. The first path can be the path from the root node to the leaf node.

[0060] All leaf results simulated in the first game tree can be scored, and the scoring criteria can take into account interaction safety, interaction sensation, traffic rules, etc., so that the higher the scoring value of the leaf node, the better the safety of the main vehicle and the first obstacle at the end of the interaction or during the interaction, the better the interaction sensation, and both comply with traffic rules; the lower the scoring value of the leaf node, the worse the safety of the main vehicle and the first obstacle at the end of the interaction or during the interaction, the worse the interaction sensation, and both may violate traffic rules.

[0061] The leaf node with the highest score value may be determined as the target leaf node, or a leaf node may be selected from the candidate leaf nodes ranked first in score value as the target leaf node, which is not specifically limited here.

[0062] After determining the target leaf node, we can trace back from the target leaf node to the root node to obtain the nodes arranged along the path from the root node to the target leaf node in the first game tree, thereby obtaining the first node set.

[0063] By recording the driving behavior of the main vehicle along the path from the root node to the target leaf node in the first game tree and the driving status of the vehicles corresponding to the first node set at each moment in the order of the path, the target driving trajectory of the vehicle can be obtained. The target driving trajectory may include information such as angle, angular velocity, position, acceleration, and speed.

[0064] In this embodiment, upon detecting that the interaction between the vehicle and the first obstacle has ended, a target leaf node is determined from the first game tree; a first node set is determined, comprising the nodes arranged along the path from the root node of the first game tree to the target leaf node; and a target driving trajectory of the vehicle is determined based on the driving state of the vehicle at each moment corresponding to the first node set and the driving behavior of the vehicle along the path corresponding to the first node set. In this way, the target driving trajectory of the host vehicle can be planned based on the first game tree.

[0065] Optionally, determining a target leaf node from the first game tree includes:

[0066] Based on the target information, scoring each leaf node in the first game tree according to a preset standard to obtain a score value of the leaf node, wherein the preset standard includes at least one of interaction safety, interaction sensation, and traffic rules;

[0067] Select the leaf node with the highest score from the first game tree to obtain the target leaf node;

[0068] The target information includes at least one of the following:

[0069] driving behaviors of the vehicle and the first obstacle along a first path, where the first path is a path from the root node to the leaf node;

[0070] driving states of the vehicle and the first obstacle on the first path;

[0071] The positions of the vehicle and the first obstacle on the first path.

[0072] In this embodiment, the first path is the path from the root node to the leaf node. The first path may include nodes and edges. Each leaf node in the first game tree may be scored based on relevant information about the interaction between the host vehicle and the first obstacle along the first path, taking into account information such as interaction safety, interaction perception, and traffic regulations. The relevant information about the interaction between the host vehicle and the first obstacle may include the host vehicle's driving behavior corresponding to the edges along the first path, and the host vehicle's driving status and position corresponding to the nodes along the first path.

[0073] Based on the scoring of each leaf node, the leaf node with the highest score in the first game tree can be determined as the target leaf node. In this way, based on the relevant information about the interaction between the host vehicle and the first obstacle on the first path, each leaf node is scored according to preset criteria. This improves the accuracy and rationality of the leaf node scoring, thereby further improving the accuracy of vehicle trajectory planning.

[0074] Optionally, before detecting that the interaction between the vehicle and the first obstacle ends, the method further includes:

[0075] When it is detected that the vehicle interacts with the second obstacle, a second game tree is constructed based on a third state and N fourth states, where the third state is the state of the third node of the second game tree, the fourth state is the state of the fourth node of the second game tree, and the fourth node is a child node of the third node; the third state includes the driving states of the vehicle and the second obstacle at the start of the interaction, and the fourth state includes: simulating the driving states of the vehicle and the second obstacle after driving according to the second behavior combination of N second behavior combinations within a second time period, the second behavior combination including: the driving behaviors of the vehicle and the second obstacle within the second time period, the second time period being the time period from the start of the interaction between the vehicle and the second obstacle to a third moment, the third moment matching the moment corresponding to the node state in the first game tree, and N is a positive integer;

[0076] Obtain a second node set in the second game tree, the second node set including: nodes whose time corresponding to the node state in the second game tree matches the time corresponding to the leaf node state in the first game tree;

[0077] The determining of the target leaf node from the first game tree includes:

[0078] Select K candidate leaf nodes from the first game tree, where the K candidate leaf nodes are leaf nodes whose score values ​​are ranked in the top K, and K is a positive integer;

[0079] Based on the second node set, the target leaf node is determined from the K candidate leaf nodes.

[0080] In this embodiment, during the simulation of the interaction between the main vehicle and the first obstacle, it is possible to detect whether there is a second obstacle around the main vehicle that interacts with it. If it is detected that the main vehicle interacts with the second obstacle, a second game tree for the interaction between the main vehicle and the second obstacle can be constructed.

[0081] The third state can be used as the node state of the root node in the second game tree. The third state can be the driving state of the main vehicle and the second obstacle at the start of the interaction, and the fourth state can be used as the node state of the child node of the root node in the second game tree. The second state can be the driving state after the main vehicle and the second obstacle are simulated to drive according to the second behavior combination of N second behavior combinations within the second time period. The second time period can be the time period from the start of the interaction between the main vehicle and the second obstacle to the third moment.

[0082] The third moment matches the moment corresponding to the node state in the first game tree. For example, the moment corresponding to the node state in the first game tree is t0 + L*step length T. If the detected start time of the interaction between the host vehicle and the second obstacle is between two adjacent moments corresponding to the node states in the first game tree, in order to align the moment corresponding to the node state in the second game tree with the moment corresponding to the node state in the first game tree and more accurately simulate the interactive impact of the same driving behavior of the host vehicle on the first and second obstacles, only the driving states of the host vehicle and the second obstacle after each of the N second behavior combinations within the second time period can be simulated, and child nodes of the root node can be constructed based on these driving states. The duration of the second time period is less than step length T, so that the node state corresponding moments of the child nodes of the root node in the second game tree are aligned with the node state corresponding moments in the first game tree. That is, the third moment can be a moment within t0 + L*step length T, such as (t0 + 3*step length T).

[0083] The second behavior combination may include the driving behaviors of the main vehicle and the second obstacle in the second time period respectively. At least one driving behavior that may be decided by the main vehicle in the second time period can be combined with at least one driving behavior that may be decided by the second obstacle in the second time period to obtain N second behavior combinations.

[0084] Then, based on the third moment and the corresponding fourth state, the driving state of the host vehicle and the second obstacle at each moment can be inferred based on the step length T. Based on this driving state, the remaining nodes of the second obstacle are constructed until the interaction between the host vehicle and the first obstacle ends. The process of constructing the remaining nodes of the second obstacle can be the same as that of constructing the first game tree, and will not be further described here.

[0085] The leaf nodes in the first game tree can be matched with the nodes in the second game tree according to the time corresponding to the node state to obtain a second node set in the second game tree at the time corresponding to the node state of the leaf node in the first game tree. For example, if the node state of the leaf node in the first game tree corresponds to the time (t0+10*step length T), then the nodes constructed based on the state at the time (t0+10*step length T) in the second game tree are obtained to obtain the second node set.

[0086] Afterwards, when it is detected that the interaction between the main vehicle and the first obstacle has ended, K candidate leaf nodes with the highest score values ​​can be selected from the leaf nodes of the first game tree, and the final target leaf node can be selected from the K candidate leaf nodes based on the second node set.

[0087] In an optional embodiment, for each candidate leaf node, it can be determined whether there is an intersection between the first driving behavior set of the main vehicle under the path corresponding to each node in the second node set and the second driving behavior set of the main vehicle under the path from the root node to the candidate leaf node in the first game tree. If there is an intersection, it is determined that the main vehicle has the same driving behavior under the two paths, and this same driving behavior can simultaneously act on the interaction between the first obstacle and the second obstacle.

[0088] A node in the second game tree corresponding to the path corresponding to the candidate leaf node in the first game tree and having the same driving behavior can be selected from the second node set. The score of the node and the score of the candidate leaf node are weighted to obtain a target score. The scoring method for the nodes in the second game tree can be similar to the scoring method for the leaf nodes in the first game tree and will not be further described here.

[0089] Accordingly, the candidate leaf node with the highest target score can be selected from the K candidate leaf nodes as the target leaf node. In this way, the driving trajectory of the host vehicle can be planned by considering the interactive effects of the same driving behavior on the first obstacle and the second obstacle. This allows for accurate trajectory planning when the host vehicle interacts with multiple obstacles simultaneously.

[0090] Optionally, determining the target driving trajectory of the vehicle based on the driving state of the vehicle corresponding to the first node set at each moment and the driving behavior of the vehicle under the path corresponding to the first node set includes:

[0091] determining an initial driving trajectory of the vehicle based on the driving state of the vehicle corresponding to the first node set at each moment and the driving behavior of the vehicle under the path corresponding to the first node set;

[0092] The initial driving trajectory is smoothed to obtain a target driving trajectory of the vehicle.

[0093] In this embodiment, the driving behavior of the main vehicle along the path from the root node to the target leaf node in the first game tree and the driving status of the vehicles corresponding to the first node set at each moment can be recorded in the order of the path, and the initial driving trajectory of the vehicle can be obtained. The initial driving trajectory may include information such as angle, angular velocity, position, acceleration, and speed.

[0094] Then, using this initial trajectory as a constraint, a quadratic programming method is used to output a smooth planned trajectory, resulting in the target trajectory. This target trajectory can then be output to the control module for execution, enabling autonomous driving and improving the user experience.

[0095] Second embodiment

[0096] like Figure 3 As shown, the present disclosure provides a trajectory planning device 300, comprising:

[0097] A first acquisition module 301 is configured to, upon detecting interaction between the vehicle and a first obstacle, acquire a first state at a first moment and M first behavior combinations within a first time period, wherein the first state includes: driving states of the vehicle and the first obstacle at the first moment, respectively; and the first behavior combinations include: driving behaviors of the vehicle and the first obstacle within the first time period, respectively. The first time period is a time period starting from the first moment and having a preset duration, where M is a positive integer.

[0098] a determination module 302 configured to determine, based on the first state and the M first behavior combinations, M second states at a second moment at the end of the first time period, the second states comprising simulated driving states of the vehicle and the first obstacle after each of the vehicle and the first obstacle performs the driving behaviors of the first behavior combinations;

[0099] A first construction module 303 is configured to construct a first game tree based on the first state and the M second states, where the first state is the state of a first node of the first game tree, the second state is the state of a second node of the first game tree, and the second node is a child node of the first node;

[0100] The trajectory planning module 304 is configured to plan a driving trajectory of the vehicle based on the first game tree when it is detected that the interaction between the vehicle and the first obstacle ends.

[0101] Optionally, the trajectory planning module 304 includes:

[0102] A first determining unit is configured to determine a target leaf node from the first game tree when detecting that the interaction between the vehicle and the first obstacle ends;

[0103] A second determining unit is configured to determine a first node set, where the first node set includes nodes arranged along a path from a root node to the target leaf node in the first game tree;

[0104] The third determining unit is configured to determine a target driving trajectory of the vehicle based on the driving status of the vehicle corresponding to the first node set at each moment and the driving behavior of the vehicle under the path corresponding to the first node set.

[0105] Optionally, the first determining unit is specifically configured to:

[0106] Based on the target information, scoring each leaf node in the first game tree according to a preset standard to obtain a score value of the leaf node, wherein the preset standard includes at least one of interaction safety, interaction sensation, and traffic rules;

[0107] Select the leaf node with the highest score from the first game tree to obtain the target leaf node;

[0108] The target information includes at least one of the following:

[0109] driving behaviors of the vehicle and the first obstacle along a first path, where the first path is a path from the root node to the leaf node;

[0110] driving states of the vehicle and the first obstacle on the first path;

[0111] The positions of the vehicle and the first obstacle on the first path.

[0112] Optionally, also include:

[0113] a second construction module, configured to construct a second game tree based on a third state and N fourth states when an interaction is detected between the vehicle and the second obstacle, wherein the third state is the state of the third node of the second game tree, the fourth state is the state of the fourth node of the second game tree, and the fourth node is a child node of the third node; the third state includes the driving states of the vehicle and the second obstacle at the start of the interaction, and the fourth state includes: simulating the driving states of the vehicle and the second obstacle after driving according to the second behavior combination of N second behavior combinations within a second time period, the second behavior combination including: the driving behaviors of the vehicle and the second obstacle within the second time period, the second time period being the time period from the start of the interaction between the vehicle and the second obstacle to a third moment, the third moment matching the moment corresponding to the node state in the first game tree, and N being a positive integer;

[0114] A second acquisition module is configured to acquire a second node set in the second game tree, the second node set including nodes whose time corresponding to the node state in the second game tree matches the time corresponding to the leaf node state in the first game tree;

[0115] The first determining unit is specifically configured to:

[0116] Select K candidate leaf nodes from the first game tree, where the K candidate leaf nodes are leaf nodes whose score values ​​are ranked in the top K, and K is a positive integer;

[0117] Based on the second node set, the target leaf node is determined from the K candidate leaf nodes.

[0118] Optionally, the third determining unit is specifically configured to:

[0119] determining an initial driving trajectory of the vehicle based on the driving state of the vehicle corresponding to the first node set at each moment and the driving behavior of the vehicle under the path corresponding to the first node set;

[0120] The initial driving trajectory is smoothed to obtain a target driving trajectory of the vehicle.

[0121] The trajectory planning device 300 provided in the present disclosure can implement each process implemented in the trajectory planning method embodiment and can achieve the same beneficial effects. To avoid repetition, it will not be described here.

[0122] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0123] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0124] Figure 4 A schematic block diagram of an example electronic device 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, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0125] like Figure 4 As shown, the device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. Various programs and data required for the operation of the device 400 can also be stored in the RAM 403. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0126] Various components in device 400 are connected to I / O interface 405, including an input unit 406, such as a keyboard, mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a magnetic disk, optical disk, etc.; and a communication unit 409, such as a network card, modem, wireless communication transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0127] The computing unit 401 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 401 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 that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as the trajectory planning method. For example, in some embodiments, the trajectory planning method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the trajectory planning method described above can be performed. Alternatively, in other embodiments, the computing unit 401 can be configured to perform the trajectory planning method by any other appropriate means (e.g., by means of firmware).

[0128] Various embodiments of the systems and techniques described 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), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes 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.

[0129] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0130] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can 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.

[0131] 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).

[0132] The systems and techniques described herein can 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 having 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 can 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.

[0133] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0134] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0135] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A trajectory planning method, comprising: When an interaction between the vehicle and the first obstacle is detected, a first state at a first moment and M first behavior combinations within a first time period are obtained, where the first state includes: driving states of the vehicle and the first obstacle at the first moment, respectively; the first behavior combinations include: driving behaviors of the vehicle and the first obstacle within the first time period, respectively; the first time period is a time period starting from the first moment and having a preset duration, where M is a positive integer; Determining, based on the first state and the M first behavior combinations, M second states at a second moment at the end of the first time period, the second states comprising: simulated driving states of the vehicle and the first obstacle after each of them performs the driving behaviors according to the first behavior combinations; Constructing a first game tree based on the first state and the M second states, where the first state is a state of a first node of the first game tree, the second state is a state of a second node of the first game tree, and the second node is a child node of the first node; When it is detected that the interaction between the vehicle and the first obstacle ends, a driving trajectory of the vehicle is planned based on the first game tree.

2. The method according to claim 1, wherein When it is detected that the interaction between the vehicle and the first obstacle ends, planning the driving trajectory of the vehicle based on the first game tree includes: When it is detected that the interaction between the vehicle and the first obstacle ends, determining a target leaf node from the first game tree; Determine a first node set, where the first node set includes nodes arranged along a path from a root node to the target leaf node in the first game tree; A target driving trajectory of the vehicle is determined based on the driving status of the vehicle corresponding to the first node set at each moment and the driving behavior of the vehicle under the path corresponding to the first node set.

3. The method according to claim 2, wherein: The determining of the target leaf node from the first game tree includes: Based on the target information, scoring each leaf node in the first game tree according to a preset standard to obtain a score value of the leaf node, wherein the preset standard includes at least one of interaction safety, interaction sensation, and traffic rules; Select the leaf node with the highest score from the first game tree to obtain the target leaf node; The target information includes at least one of the following: driving behaviors of the vehicle and the first obstacle along a first path, where the first path is a path from the root node to the leaf node; driving states of the vehicle and the first obstacle on the first path; The positions of the vehicle and the first obstacle along the first path.

4. The method according to claim 2, before detecting that the interaction between the vehicle and the first obstacle ends, the method further comprises: When it is detected that the vehicle interacts with the second obstacle, constructing a second game tree based on the third state and N fourth states, where the third state is the state of the third node of the second game tree, the fourth state is the state of the fourth node of the second game tree, and the fourth node is a child node of the third node; The third state includes the driving states of the vehicle and the second obstacle at the start of the interaction, and the fourth state includes: a driving state after simulating the vehicle and the second obstacle driving according to the driving behaviors of the second behavior combination in N second behavior combinations within a second time period, the second behavior combination including: the driving behaviors of the vehicle and the second obstacle within the second time period, the second time period being the time period from the start of the interaction between the vehicle and the second obstacle to a third moment, the third moment matching the moment corresponding to the node state in the first game tree, and N being a positive integer; Obtain a second node set in the second game tree, the second node set including: nodes whose time corresponding to the node state in the second game tree matches the time corresponding to the leaf node state in the first game tree; The determining of the target leaf node from the first game tree includes: Select K candidate leaf nodes from the first game tree, where the K candidate leaf nodes are leaf nodes whose score values ​​are ranked in the top K, and K is a positive integer; Based on the second node set, the target leaf node is determined from the K candidate leaf nodes.

5. The method according to claim 2, wherein: The determining the target driving trajectory of the vehicle based on the driving state of the vehicle at each moment corresponding to the first node set and the driving behavior of the vehicle under the path corresponding to the first node set includes: Determining an initial driving trajectory of the vehicle based on the driving state of the vehicle corresponding to the first node set at each moment and the driving behavior of the vehicle under the path corresponding to the first node set; The initial driving trajectory is smoothed to obtain a target driving trajectory of the vehicle.

6. A trajectory planning device comprising: A first acquisition module is configured to, upon detecting interaction between the vehicle and the first obstacle, acquire a first state at a first moment and M first behavior combinations within a first time period, wherein the first state includes: driving states of the vehicle and the first obstacle, respectively, at the first moment; and the first behavior combinations include: driving behaviors of the vehicle and the first obstacle, respectively, within the first time period, wherein the first time period is a time period starting from the first moment and having a preset duration, and M is a positive integer; a determination module, configured to determine, based on the first state and the M first behavior combinations, M second states at a second moment at the end of the first time period, the second states comprising: simulated driving states of the vehicle and the first obstacle after each of them performs the driving behaviors according to the first behavior combinations; A first construction module is configured to construct a first game tree based on the first state and the M second states, wherein the first state is a state of a first node of the first game tree, the second state is a state of a second node of the first game tree, and the second node is a child node of the first node; A trajectory planning module is used to plan the driving trajectory of the vehicle based on the first game tree when it is detected that the interaction between the vehicle and the first obstacle ends.

7. The device according to claim 6, wherein The trajectory planning module includes: A first determining unit is configured to determine a target leaf node from the first game tree when detecting that the interaction between the vehicle and the first obstacle ends; A second determining unit is configured to determine a first node set, where the first node set includes nodes arranged along a path from a root node to the target leaf node in the first game tree; The third determining unit is configured to determine a target driving trajectory of the vehicle based on the driving status of the vehicle corresponding to the first node set at each moment and the driving behavior of the vehicle under the path corresponding to the first node set.

8. The device according to claim 7, wherein The first determining unit is specifically configured to: Based on the target information, scoring each leaf node in the first game tree according to a preset standard to obtain a score value of the leaf node, wherein the preset standard includes at least one of interaction safety, interaction sensation, and traffic rules; Select the leaf node with the highest score from the first game tree to obtain the target leaf node; The target information includes at least one of the following: driving behaviors of the vehicle and the first obstacle along a first path, where the first path is a path from the root node to the leaf node; driving states of the vehicle and the first obstacle on the first path; The positions of the vehicle and the first obstacle along the first path.

9. The apparatus according to claim 7, further comprising: a second construction module, configured to construct, when detecting that the vehicle interacts with a second obstacle, a second game tree based on a third state and N fourth states, wherein the third state is a state of a third node of the second game tree, the fourth state is a state of a fourth node of the second game tree, and the fourth node is a child node of the third node; The third state includes the driving states of the vehicle and the second obstacle at the start of the interaction, and the fourth state includes: a driving state after simulating the vehicle and the second obstacle driving according to the driving behaviors of the second behavior combination in N second behavior combinations within a second time period, the second behavior combination including: the driving behaviors of the vehicle and the second obstacle within the second time period, the second time period being the time period from the start of the interaction between the vehicle and the second obstacle to a third moment, the third moment matching the moment corresponding to the node state in the first game tree, and N being a positive integer; A second acquisition module is configured to acquire a second node set in the second game tree, the second node set including nodes whose time corresponding to the node state in the second game tree matches the time corresponding to the leaf node state in the first game tree; The first determining unit is specifically configured to: Select K candidate leaf nodes from the first game tree, where the K candidate leaf nodes are leaf nodes whose score values ​​are ranked in the top K, and K is a positive integer; Based on the second node set, the target leaf node is determined from the K candidate leaf nodes.

10. The device according to claim 7, wherein The third determining unit is specifically configured to: Determining an initial driving trajectory of the vehicle based on the driving state of the vehicle corresponding to the first node set at each moment and the driving behavior of the vehicle under the path corresponding to the first node set; The initial driving trajectory is smoothed to obtain a target driving trajectory of the vehicle.

11. 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 that can be executed 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 5.

12. 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 5.

13. 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 5.

14. An autonomous driving vehicle comprising the electronic device according to claim 11.

Images