Driving track determination method and device, terminal and storage medium

Abstract

The invention provides a driving track determination method and device, a terminal and a storage medium, and belongs to the technical field of vehicles. The method comprises the following steps: acquiring state data of a target vehicle; creating an initial behavior decision tree based on the state data; based on at least one of a first heuristic rule and a second heuristic rule, pruning the initial behavior decision tree to obtain a target behavior decision tree, the first heuristic rule being used for representing that the number of behavior changes of the target vehicle in the future time period does not exceed a preset number of times, and the second heuristic rule being used for representing that the number of behavior changes of the target vehicle in the future time period does not exceed a preset number of times; the second heuristic rule is used for representing that the target vehicle meets a lane changing condition; and for each behavior sequence in the target behavior decision tree, based on a plurality of behaviors in the behavior sequence and the state data, fitting the moment in the future time period and the vehicle position to obtain a driving track corresponding to the behavior sequence. According to the technical scheme, the driving track of the target vehicle can be quickly determined.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a method, device, terminal and storage medium for determining a vehicle trajectory. Background Art

[0002] With the continuous development of vehicle technology, smart cars that can achieve autonomous driving have emerged. In the process of autonomous driving, how to plan a reasonable driving trajectory for smart cars so that they can drive safely is the focus of research in this field.

[0003] At present, there have been some studies on trajectory planning methods for smart cars. For example, the patent application number is CN202010763228.1, and the patent name is "A global path planning method for smart cars based on improved A-star algorithm". It records that by dividing a specific outdoor area into grids and using the center of each grid as a control point, the driving trajectory of the smart car is determined according to the improved A-star algorithm.

[0004] However, the above technical solution requires multiple iterations and a lot of computing power to determine the driving trajectory of the smart car, which is inefficient and cannot determine the driving trajectory for the smart car in real time according to the current state of the smart car. Summary of the invention

[0005] The embodiment of the present application provides a method, device, terminal and storage medium for determining a driving trajectory, which can quickly determine the driving trajectory of a target vehicle. The technical solution is as follows:

[0006] In one aspect, a method for determining a driving trajectory is provided, the method comprising:

[0007] Acquire state data of a target vehicle, wherein the state data is used to represent the state of the target vehicle at a current moment;

[0008] Based on the state data, an initial behavior decision tree is created, wherein a root node in the initial behavior decision tree is used to represent the behavior performed by the target vehicle at the current moment, and other nodes in the initial behavior decision tree except the root node are used to represent the behaviors that the target vehicle can perform in a future time period, and the behaviors that the target vehicle can perform include three categories: changing lanes to the left, keeping the original lane, and changing lanes to the right;

[0009] Based on at least one of a first heuristic rule and a second heuristic rule, pruning the initial behavior decision tree to obtain a target behavior decision tree, wherein the first heuristic rule is used to indicate that the number of behavior changes of the target vehicle in the future time period does not exceed a preset number, and the second heuristic rule is used to indicate that the target vehicle meets the lane change condition;

[0010] For each behavior sequence in the target behavior decision tree, based on multiple behaviors in the behavior sequence and the state data, the moments in the future time period are fitted with the vehicle positions to obtain a driving trajectory corresponding to the behavior sequence.

[0011] On the other hand, a device for determining a driving trajectory is provided, the device comprising:

[0012] An acquisition module, used for acquiring status data of a target vehicle, wherein the status data is used for indicating the status of the target vehicle at a current moment;

[0013] A creation module, used for creating an initial behavior decision tree based on the state data, wherein the root node in the initial behavior decision tree is used to represent the behavior performed by the target vehicle at the current moment, and other nodes in the initial behavior decision tree except the root node are used to represent the behaviors that the target vehicle can perform in a future time period, and the behaviors that the target vehicle can perform include three categories: changing lanes to the left, keeping the original lane, and changing lanes to the right;

[0014] a first processing module, configured to prune the initial behavior decision tree based on at least one of a first heuristic rule and a second heuristic rule to obtain a target behavior decision tree, wherein the first heuristic rule is used to indicate that the number of behavior changes of the target vehicle in the future time period does not exceed a preset number, and the second heuristic rule is used to indicate that the target vehicle meets the lane change condition;

[0015] The second processing module is used to fit the moments in the future time period with the vehicle positions for each behavior sequence in the target behavior decision tree based on multiple behaviors in the behavior sequence and the state data to obtain a driving trajectory corresponding to the behavior sequence.

[0016] In some embodiments, the creation module is used to:

[0017] Determine the behavior of the target vehicle at the current moment based on the longitudinal position, lateral position, first speed, second speed, yaw angle and yaw angular velocity of the target vehicle in the state data, wherein the first speed is the speed along the direction of the vehicle body, and the second speed is the speed perpendicular to the direction of the vehicle body;

[0018] Based on the behavior performed by the target vehicle at the current moment, creating a root node of the initial behavior decision tree;

[0019] Based on the behavior collection, on the basis of the root node, creating other nodes in the initial behavior decision tree except the root node, wherein the behavior collection includes three types of behaviors that the target vehicle can perform;

[0020] Among them, any node other than the sub-node in the initial behavior decision tree corresponds to three sub-nodes, and the three sub-nodes of each node are respectively used to represent changing lanes to the left, keeping the original lane, and changing lanes to the right.

[0021] In some embodiments, the first processing module is used to:

[0022] Based on the first heuristic rule, a plurality of first nodes are determined from the initial behavior decision tree, the number of target node pairs between each first node and the root node is equal to the preset number, a parent-child relationship exists between two nodes in the target node pair, and the behaviors represented by the two nodes are different;

[0023] For any first node among the multiple first nodes, remove the second node corresponding to the first node and all nodes after the second node from the initial behavior decision tree, where the second node is a child node of the first node and the behavior represented by the second node is different from the behavior represented by the first node.

[0024] In some embodiments, the first processing module is used to:

[0025] Based on the second heuristic rule, a first warning distance, a first lane-changing gap, a second warning distance, and a second lane-changing gap of the target vehicle at the current moment are obtained, wherein the first warning distance is the minimum safe distance between the target vehicle and surrounding vehicles when changing lanes to the left, the first lane-changing gap is the distance between surrounding vehicles when the target vehicle changes lanes to the left, the second warning distance is the minimum safe distance between the target vehicle and surrounding vehicles when changing lanes to the right, and the second lane-changing gap is the distance between surrounding vehicles when the target vehicle changes lanes to the right;

[0026] Based on the first warning distance, the first lane changing gap, the second warning distance and the second lane changing gap, nodes corresponding to a target behavior sequence are removed from the initial behavior decision tree to obtain the target behavior decision tree, wherein the target behavior sequence includes a target lane changing behavior, and the warning distance corresponding to the target lane changing behavior is less than the corresponding lane changing gap.

[0027] In some embodiments, the first processing module is used to:

[0028] Based on the first heuristic rule, the initial behavior decision tree is pruned for the first time to obtain a first intermediate behavior decision tree;

[0029] Based on the second heuristic rule, the intermediate behavior decision tree is pruned for the second time to obtain the target behavior decision tree.

[0030] In some embodiments, the apparatus further comprises:

[0031] A third processing module is used to determine a plurality of third nodes from the initial behavior decision tree, wherein the behavior represented by each third node is opposite to the behavior represented by the parent node of the third node; and remove the plurality of third nodes and all nodes after the third node from the initial behavior decision tree to obtain a second intermediate behavior decision tree;

[0032] The first processing module is used to prune the second intermediate behavior decision tree based on at least one of the first heuristic rule and the second heuristic rule to obtain a target behavior decision tree.

[0033] In some embodiments, the second processing module includes:

[0034] A simulation unit, for performing a dynamic simulation on the target vehicle for each behavior sequence in the target behavior decision tree based on a plurality of behaviors in the behavior sequence and the state data, to determine a terminal position of the target vehicle after the future time period;

[0035] a processing unit, configured to perform polynomial fitting based on the lateral starting position of the target vehicle at the current moment and the lateral end position of the end position with the moment in the future time period, so as to obtain a lateral trajectory of the target vehicle, wherein the lateral trajectory is used to represent a change in the lateral position of the target vehicle in the future time period;

[0036] A determination unit is used to adopt a longitudinal following model to determine the acceleration at multiple moments in the future time period, and determine the longitudinal trajectory of the target vehicle based on the acceleration at the multiple moments and the longitudinal starting position of the target vehicle at the current moment, wherein the longitudinal trajectory is used to represent the change in the longitudinal position of the target vehicle in the future time period.

[0037] In some embodiments, the simulation unit is used to:

[0038] For each behavior sequence in the target behavior decision tree, based on the behaviors to be executed at multiple moments in the behavior sequence and the state data, a dynamic simulation is performed on the target vehicle to obtain the state data of the target vehicle at the multiple moments, wherein the state data corresponding to each moment includes the longitudinal position, road adhesion coefficient and vehicle speed of the target vehicle at the moment;

[0039] Clustering the state data at the multiple moments to obtain multiple groups of state data;

[0040] For any group of status data among the multiple groups of status data, averaging multiple status data in the group of status data to obtain central status data corresponding to the group of status data;

[0041] Based on the central state data, a dynamic simulation is performed on the target vehicle to obtain a terminal position of the target vehicle after the future time period.

[0042] On the other hand, a computer device is provided, which includes a processor and a memory, wherein the memory is used to store at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the method for determining the driving trajectory in the embodiment of the present application.

[0043] On the other hand, a computer-readable storage medium is provided, in which at least one computer program is stored. The at least one computer program is loaded and executed by a processor to implement a method for determining a driving trajectory as in an embodiment of the present application.

[0044] On the other hand, a computer program product is provided, including a computer program, which is stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device executes the method for determining the driving trajectory provided in the above-mentioned various aspects or various optional implementations of various aspects.

[0045] The embodiment of the present application provides a method for determining a driving trajectory, which can generate an initial behavior decision tree in real time according to the behavior of the target vehicle at the current moment, and can design behavior change restrictions and first heuristic rules that mainly focus on the vehicle based on human driving habits, and preliminarily prune the initial behavior decision tree. Secondly, or alternatively, a humanoid lane change warning model that considers vehicle heterogeneity and driver heterogeneity can be established to perform secondary pruning on the behavior decision tree from a safety perspective. Finally, according to the state corresponding to the vehicle behavior in each decision cycle in the target behavior decision tree, a driving trajectory corresponding to each behavior sequence in the target behavior decision tree is generated to provide it to the target vehicle for selection, thereby reducing the complexity of the decision algorithm, improving the efficiency of determining the driving trajectory, and at the same time helping to ensure the robustness of the subsequently determined driving trajectory, and having stronger practicality. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 It is a schematic diagram of an implementation environment of a method for determining a driving trajectory provided in an embodiment of the present application;

[0048] Figure 2 is a flow chart of a method for determining a driving trajectory provided according to an embodiment of the present application;

[0049] Figure 3 is a schematic diagram of an initial behavior decision tree provided according to an embodiment of the present application;

[0050] Figure 4 is a schematic diagram of an initial behavior decision tree after pruning provided in an embodiment of the present application;

[0051] Figure 5 is a block diagram of a vehicle trajectory determination device provided according to an embodiment of the present application;

[0052] Figure 6 It is a structural schematic diagram of a vehicle controller of a target vehicle provided according to an embodiment of the present application;

[0053] Figure 7 It is a structural diagram of a server provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0055] In this application, the terms "first", "second", etc. are used to distinguish identical or similar items with basically the same effects and functions. It should be understood that there is no logical or temporal dependency between "first", "second", and "nth", nor is there any limitation on quantity and execution order.

[0056] In the present application, the term "at least one" means one or more, and the term "plurality" means two or more.

[0057] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions. For example, the status data of the target vehicle and the status data of surrounding vehicles involved in this application are all obtained with full authorization.

[0058] The method for determining the driving trajectory provided in the embodiment of the present application can be executed by a computer device. In some embodiments, the computer device is a terminal or a server. The following first takes the computer device as an example to introduce the implementation environment of the method for determining the driving trajectory provided in the embodiment of the present application. Figure 1 Schematic diagram of an implementation environment of a method for determining a vehicle trajectory provided in an embodiment of the present application. Figure 1 , the implementation environment includes a smart car 101 and a server 102. The smart car 101 and the server 102 can be directly or indirectly connected via wired or wireless communication, which is not limited in this application.

[0059] In some embodiments, the smart car 101 can be a new energy vehicle, such as a pure electric vehicle, a plug-in hybrid electric vehicle, a fuel cell electric vehicle, etc., which is not limited in the embodiments of the present application. The smart car 101 is equipped with a vehicle controller, an on-board charger, a power battery, and a battery management system for managing the power battery. Among them, the vehicle controller can communicate with the server 102 via the CAN (Controller Area Network) bus. Accordingly, the vehicle controller of the smart car 101 can obtain its own driving trajectory from the server 102 through the network, and control the driving of the smart car 101 based on the driving trajectory.

[0060] In some embodiments, server 102 is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), big data and artificial intelligence platforms. Server 102 is used to provide background services to support smart cars. In some embodiments, server 102 undertakes the main computing work and terminal 101 undertakes the secondary computing work; or, server 102 undertakes the secondary computing work and terminal 101 undertakes the main computing work; or, server 102 and terminal 101 use a distributed computing architecture for collaborative computing.

[0061] Figure 2 is a flow chart of a method for determining a driving trajectory provided in accordance with an embodiment of the present application, see Figure 2 In the present application, the method for determining the vehicle trajectory includes the following steps:

[0062] 201. The server obtains status data of a target vehicle, where the status data is used to indicate the status of the target vehicle at the current moment.

[0063] In the embodiment of the present application, the target vehicle is a smart car that supports automatic driving technology. During the automatic driving process of the target vehicle, the target vehicle can collect its own status data through millimeter wave radar, laser radar, camera, IMU (Inertial Measurement Unit), navigation system and vehicle speed sensor, and upload the status data to the server.

[0064] Among them, the state data of the target vehicle may include the position, speed, acceleration, yaw angle, yaw angular velocity, etc. of the target vehicle at the current moment, and the embodiments of the present disclosure are not limited to this. Among them, the position of the target vehicle includes the longitudinal position and the lateral position. The longitudinal position refers to the position of the target vehicle along the road direction. The lateral position refers to the position of the target vehicle in the direction perpendicular to the road. The speed of the target vehicle includes the longitudinal speed and the lateral speed. The longitudinal speed refers to the speed along the direction of the vehicle body. The lateral speed refers to the speed perpendicular to the direction of the vehicle body. The acceleration of the target vehicle includes the longitudinal acceleration and the lateral acceleration. The longitudinal acceleration refers to the acceleration along the direction of the vehicle body. The lateral acceleration refers to the acceleration perpendicular to the direction of the vehicle body. The yaw angle of the target vehicle refers to the angle of change of the vehicle body posture of the target vehicle during driving. The yaw angular velocity of the target vehicle refers to the rate at which the vehicle body posture of the target vehicle changes, that is, the rate of change of the yaw angle.

[0065] 202. The server creates an initial behavior decision tree based on the state data. The root node in the initial behavior decision tree is used to represent the behavior performed by the target vehicle at the current moment. The other nodes in the initial behavior decision tree except the root node are used to represent the behaviors that the target vehicle can perform in the future time period. The behaviors that the target vehicle can perform include three categories: changing lanes to the left, keeping the original lane, and changing lanes to the right.

[0066] In the embodiment of the present application, the server determines the behavior of the target vehicle at the current moment based on the longitudinal position, lateral position, first speed, second speed, yaw angle and yaw angular velocity of the target vehicle in the state data. The first speed is the speed along the direction of the vehicle body. The second speed is the speed perpendicular to the direction of the vehicle body. The behavior of the target vehicle at the current moment can be any one of changing lanes to the left, keeping the original lane, and changing lanes to the right, which is not limited in the embodiment of the present application.

[0067] Then, the server creates the root node of the initial behavior decision tree based on the behavior performed by the target vehicle at the current moment. Based on the behavior collection, the server creates other nodes in the initial behavior decision tree except the root node. The behavior collection includes three types of behaviors that the target vehicle can perform. The three types of behaviors include changing lanes to the left, keeping the original lane, and changing lanes to the right. Correspondingly, any node other than the leaf node in the initial behavior decision tree corresponds to three child nodes, and the three child nodes of each node are used to represent changing lanes to the left, keeping the original lane, and changing lanes to the right.

[0068] Among them, the initial behavior decision tree is used to represent the behavior of the target vehicle in the future time period. The depth of the initial behavior decision tree is used to represent the number of times the behavior is determined in the future time period. That is, the future time period is a decision cycle, and each decision cycle contains multiple decision moments for determining the behavior. The server can discretize the decision cycle into multiple decision moments according to the number of decisions. For any decision moment, the server must determine the behavior of the target vehicle once. That is, for any decision moment, the server can create a new layer of nodes based on the collection of behaviors to construct a behavior decision tree. Correspondingly, each layer in the initial behavior decision tree corresponds one-to-one to a decision moment, and the nodes in each layer are used to represent the possible behavior of the target vehicle at the corresponding decision moment.

[0069] The solution provided in the embodiment of the present application determines the current behavior of the target vehicle based on the state data of the target vehicle at the current moment, and constructs an initial behavior decision tree based on the behavior collection based on the current behavior. Since the behavior collection contains all types of behaviors that the target vehicle can perform, the constructed initial behavior decision tree contains all behavior changes of the target vehicle in the future time period, ensuring that the subsequently determined driving trajectory is determined on the basis of all behavior changes, that is, ensuring the diversity and accuracy of the driving trajectory.

[0070] For example, the current state data of the target vehicle is Among them, x k is the longitudinal position of the target vehicle, y k is the lateral position of the target vehicle, v uk is the speed of the target vehicle along the body direction, v vk is the speed of the target vehicle perpendicular to the direction of the vehicle body, is the yaw angle of the target vehicle, r kis the yaw rate of the target vehicle. The behavior set in the target vehicle behavior decision process is A = {LLC, LK, RLC}, where LLC means changing lanes to the left, LK means keeping the original lane, and RLC means changing lanes to the right. The server constructs an initial behavior decision tree for the target vehicle based on the state data and behavior set of the target vehicle at the current moment. Assuming that the behavior of the target vehicle at the current moment is to keep the original lane, the initial behavior decision tree is created by keeping the original lane as the initial behavior of the target vehicle. In the process of constructing the initial behavior decision tree, the server can S , the decision cycle T P Discretized into multiple decision moments, namely t0 to t4. For each decision moment, the server creates a new layer of nodes based on the latest layer of nodes that have been created. Figure 3 , Figure 3 It is a schematic diagram of an initial behavior decision tree provided according to an embodiment of the present application. Figure 3 The L, K, and R behaviors in represent LLc (changing lanes to the left), LK (staying in the original lane), and RLC (changing lanes to the right), respectively. Figure 3 It can be seen that each layer in the initial behavior decision tree corresponds to a decision moment one by one, and the nodes in each layer are used to represent the possible behaviors of the target vehicle at the corresponding decision moment.

[0071] 203. The server prunes the initial behavior decision tree based on at least one of the first heuristic rule and the second heuristic rule to obtain a target behavior decision tree, wherein the first heuristic rule is used to indicate that the number of behavior changes of the target vehicle in a future time period does not exceed a preset number, and the second heuristic rule is used to indicate that the target vehicle meets the lane change condition.

[0072] In the embodiment of the present application, considering human driving habits and vehicle driving stability, human drivers will not frequently change the behavior of the vehicle in a short period of time, and a first heuristic rule can be set to constrain the number of behavior changes of the target vehicle in the future time period to not exceed a preset number. Considering that the lane changing conditions need to be met when the vehicle changes lanes, a second heuristic rule can be set to constrain the lane changing behavior that can be achieved in the future time period. Then, the server can prune the initial behavior decision tree based on at least one of the first heuristic rule and the second heuristic rule to obtain the target behavior decision tree.

[0073] That is, the server can prune the initial behavior decision tree based on the first heuristic rule to remove behaviors in the initial behavior decision tree whose behavior changes more than a preset number of times. The embodiment of the present application does not limit the preset number of times. For example, the preset number of times can be positively correlated with a future time period (i.e., a decision cycle). Alternatively, the server can also prune the initial behavior decision tree based on the second heuristic rule to remove lane-changing behaviors that cannot be realized in the initial behavior decision tree. Alternatively, the server can also prune the initial behavior decision tree based on the first heuristic rule and the second heuristic rule to remove behaviors in the initial behavior decision tree whose behavior changes more than a preset number of times and lane-changing behaviors that cannot be realized. The above-mentioned multiple pruning methods are introduced below.

[0074] In the first pruning method, the server prunes the initial behavior decision tree based on the first heuristic rule. Accordingly, the process of the server pruning the initial behavior decision tree includes: the server determines multiple first nodes from the initial behavior decision tree based on the first heuristic rule. The number of target node pairs between each first node and the root node is equal to the preset number of times. There is a parent-child relationship between the two nodes in the target node pair, and the behaviors represented by the two nodes are different. That is, each target node pair can represent a change in the behavior of the target vehicle. The number of target node pairs in each link (behavior sequence) in the initial behavior decision tree is used to represent the number of changes in the behavior of the target vehicle when it travels along the behavior in the link. That is, the server traverses from the root node in the initial behavior decision tree to find the first node when the number of behavior changes reaches the preset number of times.

[0075] Then, for any first node among the multiple first nodes, the server removes the second node corresponding to the first node and all nodes after the second node from the initial behavior decision tree. The second node is a child node of the first node. The behavior represented by the second node is different from the behavior represented by the first node. That is, the server removes all nodes in the initial behavior decision tree that are located after the first node and have different behaviors from those represented by the first node. In other words, the server removes the node when the number of behavior changes exceeds a preset number and all nodes after the node from the initial behavior decision tree.

[0076] The embodiment of the present application provides a solution for pruning the initial behavior decision tree based on the first heuristic rule, so that the number of behavior changes of the target vehicle in the future time period does not exceed a preset number. This can not only directly reduce the number of driving trajectories to be determined subsequently, effectively reduce the complexity of determining the driving trajectory, thereby obtaining the driving trajectory more quickly and improving the efficiency of determining the driving trajectory, but also help to ensure the driving stability of the target vehicle in the future time period, that is, it is conducive to ensuring the robustness of the driving trajectory determined subsequently, and has stronger practicality.

[0077] In the second pruning method, the server prunes the initial behavior decision tree based on the second heuristic rule. Accordingly, the process of the server pruning the initial behavior decision tree includes: the server obtains the first warning distance, the first lane change gap, the second warning distance, and the second lane change gap of the target vehicle at the current moment based on the second heuristic rule. The first warning distance is the minimum safe distance between the target vehicle and the surrounding vehicles when changing lanes to the left. The first lane change gap is the distance between the surrounding vehicles when the target vehicle changes lanes to the left. The second warning distance is the minimum safe distance between the target vehicle and the surrounding vehicles when changing lanes to the right. The second lane change gap is the distance between the surrounding vehicles when the target vehicle changes lanes to the right. Based on the first warning distance, the first lane change gap, the second warning distance, and the second lane change gap, the server removes the nodes corresponding to the target behavior sequence from the initial behavior decision tree to obtain the target behavior decision tree. The target behavior sequence includes the target lane change behavior. The warning distance corresponding to the target lane change behavior is less than the corresponding lane change gap. If the warning distance is less than the corresponding lane change gap, the target vehicle cannot change lanes, that is, the target lane change behavior is a lane change behavior that the target vehicle cannot achieve.

[0078] In other words, when the target vehicle changes lanes to the left, it will check whether there is a safe lane-changing gap in the lane adjacent to the left of the target vehicle's current lane. If the distance between the front and rear vehicles in the lane adjacent to the left of the target vehicle's current lane is greater than the warning distance, the target vehicle can safely change lanes to the left. When the target vehicle changes lanes to the right, it will check whether there is a safe lane-changing gap in the lane adjacent to the right of the target vehicle's current lane. If the distance between the front and rear vehicles in the lane adjacent to the right of the target vehicle's current lane is greater than the warning distance, the target vehicle can safely change lanes to the right.

[0079] The above-mentioned first warning distance and second warning distance can be determined using the following formula 1.

[0080] Formula 1:

[0081]

[0082] Among them, S wd Indicates the overall warning distance corresponding to any lane change behavior, which can be the first warning distance or the second warning distance; Indicates the warning distance between the target vehicle and the preceding vehicle. The preceding vehicle refers to the vehicle in front of the target vehicle in the lane to which the target vehicle is changing. For example, when changing lanes to the left, the preceding vehicle is the vehicle in front of the target vehicle in the lane adjacent to the left of the target vehicle's current lane. Indicates the warning distance between the target vehicle and the following vehicle. The leading vehicle refers to the vehicle behind the target vehicle in the lane to which the target vehicle is changing. For example, when changing lanes to the left, the following vehicle is the vehicle behind the target vehicle in the lane adjacent to the left of the target vehicle's current lane.

[0083] Above It can be determined by the following formula 2.

[0084] Formula 2:

[0085]

[0086] Among them, v k represents the speed of the target vehicle at the current time k; τ1 represents the reaction time of the target vehicle to delay deceleration; t′1 represents the braking time of the target vehicle at a larger deceleration; a max,brake represents the maximum deceleration of the target vehicle; t″1 represents the duration of the target vehicle braking at a comfortable braking deceleration; a comfort,brake Indicates the target vehicle's comfortable braking deceleration; It represents the speed of the vehicle preceding the target vehicle at the current time k.

[0087] Above It can be determined by the following formula 3.

[0088] Formula 3:

[0089]

[0090] in, represents the speed of the vehicle behind the target vehicle at the current time k; τ2 represents the reaction time of the delayed deceleration of the vehicle behind the target vehicle; t′2 represents the braking time of the vehicle behind the target vehicle with a large deceleration; Indicates the maximum deceleration of the following vehicle; t″2 indicates the duration of braking of the following vehicle at the comfortable braking deceleration; Indicates the comfortable braking deceleration of the rear vehicle; v k represents the speed of the target vehicle at the current time k.

[0091] The above τ1 and τ2 can reflect the duration of different vehicles' perception of the impending danger. When τ1 and τ2 are large, it can be reflected that the vehicle's response to the dangerous situation is slow; when τ1 and τ2 are small, it can be reflected that the vehicle's response to the dangerous situation is more sensitive. comfort,brake and This can reflect the adaptability of the vehicle to different drivers. That is, different drivers have different strengths in braking control of the vehicle, resulting in different comfortable braking decelerations of the vehicle. In other words, the calculation method of the above warning distance takes into account the influence of different vehicles and different drivers, which is equivalent to a human-like lane change warning model.

[0092] Then, all the behavior sequences of left and right lane changes in the initial behavior decision tree are screened through the above-mentioned humanoid warning model, and it is checked whether the target vehicle has a safe lane change gap in the target lane when changing lanes, so as to realize the screening of the behavior sequence, and eliminate the behavior sequence without a safe lane change gap to ensure the safety of lane changing. For example, if the behavior sequence is a left lane change, the humanoid warning model is used to check whether there is a safe lane change gap in the left adjacent lane. If not, the left lane change behavior sequence is deleted; if the behavior sequence is a right lane change, check whether there is a safe lane change gap in the right adjacent lane. If not, the right lane change behavior sequence is deleted. That is, the server removes the behavior sequences that do not meet the safety requirements. Specifically, the warning distance and lane change gap corresponding to the lane change behavior should meet the conditions expressed by the following formula 4 to be retained in the behavior decision tree.

[0093] Formula 4:

[0094]

[0095] in, represents the longitudinal position of the preceding vehicle in the adjacent lane of the current lane of the target vehicle at the current time k; l f Indicates the length of the vehicle in front of the target vehicle in the adjacent lane of the current lane; x k represents the longitudinal position of the target vehicle at the current time k; l represents the length of the target vehicle; Indicates the warning distance between the target vehicle and the vehicle ahead; represents the longitudinal position of the vehicle behind the target vehicle in the adjacent lane of the target vehicle's current lane at the current time k; l r Indicates the length of the vehicle behind in the adjacent lane of the current lane of the target vehicle; Indicates the warning distance between the target vehicle and the following vehicle; S wd Indicates the overall warning distance.

[0096] It can be seen from the above formula 4 that the lane change gap between the target vehicle and the preceding vehicle is greater than or equal to The lane change gap between the target vehicle and the following vehicle is greater than or equal to The distance between the preceding vehicle and the following vehicle (i.e., the overall lane-changing gap) is greater than or equal to S wd Only when the condition in formula 4 is met can it be indicated that the target vehicle has a safe lane-changing gap, and then the server retains the behavior sequence corresponding to the lane-changing behavior. Otherwise, if the condition in formula 4 is not met, the target vehicle does not have a safe lane-changing gap, and the server deletes the behavior sequence corresponding to the lane-changing behavior.

[0097] The solution provided in the embodiment of the present application prunes the initial behavior decision tree based on the second heuristic rule, takes into account the heterogeneity of vehicles and drivers, proposes humanized parameters related to the vehicle delayed reaction deceleration time and vehicle comfort, improves the adaptability of the target vehicle to different vehicles and passengers, makes the generation of subsequent driving trajectories more humanized, and at the same time can screen out behavior sequences that can drive safely to calculate the driving trajectory, thereby ensuring the safety of the target vehicle's driving; and, through pruning, the number of driving trajectories to be determined subsequently can be directly reduced, effectively reducing the complexity of determining the driving trajectory, thereby obtaining the driving trajectory faster and improving the efficiency of determining the driving trajectory.

[0098] In the third pruning method, the server prunes the initial behavior decision tree based on the first heuristic rule and the second heuristic rule. Accordingly, the process of the server pruning the initial behavior decision tree includes: the server performs a first pruning on the initial behavior decision tree based on the first heuristic rule to obtain a first intermediate behavior decision tree. Then, the server performs a second pruning on the intermediate behavior decision tree based on the second heuristic rule to obtain a target behavior decision tree. That is, the server can use the first pruning method mentioned above to perform preliminary pruning on the initial behavior decision tree to obtain a first intermediate behavior decision tree, and then use the second pruning method mentioned above to prune the first intermediate behavior decision tree obtained by preliminary pruning again to obtain a target behavior decision tree, which will not be repeated here.

[0099] In some embodiments, considering that after the target vehicle changes lanes in a certain direction, it usually travels along the vehicle after the lane change or continues to change lanes in the same direction, and it is unlikely to change lanes in the opposite direction again in a short time, that is, it is unlikely to perform the opposite behavior in a short time. Accordingly, in addition to adopting the above-mentioned pruning method, the server can also remove nodes that perform opposite behaviors in a short time from the initial behavior decision tree. Accordingly, the server determines multiple third nodes from the initial behavior decision tree. The behavior represented by each third node is opposite to the behavior represented by the parent node of the third node. Then, the server removes multiple third nodes and all nodes after the third node from the initial behavior decision tree to obtain a second intermediate behavior decision tree. Then, the server can prune the second intermediate behavior decision tree based on at least one of the first heuristic rule and the second heuristic rule to obtain the target behavior decision tree. Alternatively, the server can also first use at least one of the first heuristic rule and the second heuristic rule to perform preliminary pruning on the initial behavior decision tree, and then remove nodes that perform opposite behaviors in a short time from the intermediate behavior decision tree obtained by preliminary pruning, etc. The embodiment of the present application does not limit the order of pruning.

[0100] The solution provided in the embodiment of the present application removes the lane changing behavior in the opposite direction to the previous lane changing behavior in the behavior decision tree, so that the behavior changes of the target vehicle in the future time period are consistent with human habits. This can not only directly reduce the number of driving trajectories to be determined subsequently, effectively reduce the complexity of determining the driving trajectory, thereby obtaining the driving trajectory more quickly and improving the efficiency of determining the driving trajectory, but also help to ensure the driving stability of the target vehicle in the future time period, that is, it is conducive to ensuring the robustness of the driving trajectory determined subsequently, and has stronger practicality.

[0101] For example, the preset number of times corresponding to the first heuristic rule is 1, that is, the target vehicle can only change its behavior once in the future time period. Figure 3 The initial behavior decision tree shown is pruned to obtain Figure 4 The target behavior decision tree shown in Figure . Figure 3 and Figure 4 It can be seen that the server removes all unreasonable behavior sequences in the initial behavior decision tree (including decision sequences with simultaneous left and right lane changes and two or more changes in vehicle behavior). Figure 4 In (a), if the target vehicle's initial behavior is to stay in the original lane K, then it can change its behavior once to change lanes to the left L or right R in the entire future time period (decision cycle). Figure 4 In (b), if the target vehicle's initial behavior is to change lanes to the right R, then in the entire future time period (decision cycle), it is only allowed to change its behavior once to stay in the original lane K, and it is not allowed to change lanes to the right and then to the left in a short period of time. In other words, while ensuring that the number of behavior changes does not exceed the preset number, the lane change behavior in the opposite direction of the previous lane change behavior can also be removed.

[0102] 204. For each behavior sequence in the target behavior decision tree, the server fits the time and vehicle position in the future time period based on multiple behaviors and state data in the behavior sequence to obtain a driving trajectory corresponding to the behavior sequence.

[0103] In an embodiment of the present application, the behavior sequence in the target behavior decision tree includes the behaviors represented by each node on the link from the root node to any leaf node, which is used to represent multiple behaviors that the target vehicle performs in sequence in the future time period. The number of behavior sequences in the target behavior decision tree is equal to the number of leaf nodes. For any behavior sequence in the target behavior decision tree, the server can fit the moment and vehicle position in the future time period based on the multiple behaviors in the behavior sequence and the state data of the target vehicle at the current moment, so as to determine the position of the target vehicle at each moment in the future time period, that is, to obtain the corresponding driving trajectory when driving according to the behaviors in the behavior sequence.

[0104] In the process of determining the driving trajectory corresponding to each behavior sequence, for each behavior sequence in the target behavior decision tree, the server performs dynamic simulation on the target vehicle based on multiple behaviors and state data in the behavior sequence to determine the terminal position of the target vehicle after the future time period. Then, the server performs polynomial fitting based on the lateral starting position and the lateral terminal position of the target vehicle at the current moment and the moment in the future time period to obtain the lateral trajectory of the target vehicle. The lateral trajectory is used to represent the change in the lateral position of the target vehicle in the future time period. The server uses a longitudinal following model to determine the acceleration at multiple moments in the future time period, and determines the longitudinal trajectory of the target vehicle based on the acceleration at multiple moments and the longitudinal starting position of the target vehicle at the current moment. The longitudinal trajectory is used to represent the change in the longitudinal position of the target vehicle in the future time period.

[0105] That is, the server can establish an adaptive horizontal k-order polynomial mathematical model based on the state data of the target vehicle at the current moment, and P The corresponding local trajectory of the behavior in the future (i.e., the future time period) is polynomially fitted at the starting position and the constraints of the starting position, and then the lateral trajectory of the target vehicle in one decision cycle is obtained. In addition, the server can establish a longitudinal following model, obtain a discrete acceleration sequence, and obtain the longitudinal trajectory of the target vehicle in one decision cycle through the kinematic formula. Then, the server takes the state of the target vehicle after one decision cycle as the current state, and repeats the above operation 4 times to generate the lateral trajectory and longitudinal trajectory of the target vehicle in 5 decision cycles of the behavior decision tree after pruning.

[0106] Specifically, in the process of determining the terminal position of the target vehicle after the future time period, the server performs a dynamic simulation on the target vehicle for each behavior sequence in the target behavior decision tree based on the behaviors and state data to be executed at multiple moments in the behavior sequence, and obtains the state data of the target vehicle at multiple moments. The state data corresponding to each moment includes the longitudinal position of the target vehicle at the moment, the road adhesion coefficient, and the vehicle speed. Then, the server clusters the state data at multiple moments to obtain multiple groups of state data. For any group of state data in the multiple groups of state data, the server averages the multiple state data in the group state data to obtain the central state data corresponding to the group state data. Then, based on the central state data, the server performs a dynamic simulation on the target vehicle to obtain the terminal position of the target vehicle after the future time period.

[0107] For example, the current state data of the target vehicle is Among them, x k is the longitudinal position of the target vehicle; y k is the lateral position of the target vehicle; is the speed of the target vehicle along the body direction, that is, the longitudinal speed; v vk is the speed of the target vehicle perpendicular to the direction of the vehicle body, that is, the lateral speed; is the acceleration of the target vehicle along the body direction, that is, the longitudinal acceleration; is the acceleration of the target vehicle perpendicular to the body direction, that is, the lateral acceleration. The target vehicle has a decision cycle T P The state after Among them, the target vehicle goes through a decision cycle T P Lateral position The lateral position of the target vehicle in this decision cycle is the target vehicle in a decision cycle T P Lateral velocity after time and lateral acceleration Both are 0.

[0108] The server can calculate the longitudinal position x of the target vehicle at time k by performing dynamic simulation on the target vehicle. k , road adhesion coefficient β k and the target vehicle’s velocity v k The server can then create a dataset D containing all data points, where each data point is represented by m k =(x k ,β k ,v j ). The server can then normalize the dataset D to ensure that all features in the dataset D have similar ranges.

[0109] The server can then cluster the data points in the dataset D into j clusters. k Belongs to a cluster C i , where i = 1, 2, ..., j, for each cluster C i , the server calculates the average value of its feature vector as the center point of the cluster. The center point can be expressed as: in The clustering algorithm may be a k-means clustering algorithm, which is not limited in the present embodiment.

[0110] For each cluster C i , the server can be based on the center point of the cluster Perform dynamic simulation on the target vehicle to obtain the target vehicle's final position after a future time period. Then, the server can make a decision based on the target vehicle's lateral starting position and decision period T at the current moment. PThe lateral end position of the target vehicle is then used as a constraint for the following adaptive lateral k-order polynomial (Formula 5) to determine the fitting parameter a η , thus obtaining the lateral trajectory of the target vehicle within a decision cycle.

[0111] Formula 5:

[0112]

[0113] Among them, y(k) represents the lateral position of the target vehicle at time k, a η represents the fitting parameter, k i Represents the i-th discrete time point in a decision cycle (i.e., the i-th decision moment).

[0114] The solution provided in the embodiment of the present application adopts an adaptive lateral k-order polynomial mathematical model to fit the lateral candidate trajectory of the vehicle, thereby improving the adaptability of the generated lateral candidate trajectory to different road surfaces.

[0115] The specific method of calculating the acceleration of the target vehicle in the above longitudinal following model can be found in the following formula 6.

[0116] Formula 6:

[0117]

[0118] Among them, a k represents the optimal acceleration of the target vehicle at time k; a represents the maximum deceleration of the target vehicle; b represents the comfortable deceleration of the target vehicle; v k represents the speed of the target vehicle at time k; Indicates the speed of the vehicle in front of the target vehicle in the current lane at time k; Δs k represents the relative distance between the target vehicle and the preceding vehicle at time k; v l represents the road speed limit; δ represents the acceleration exponential factor; s0 represents the minimum distance between vehicles at rest; T h Indicates the expected headway.

[0119] Then, the server determines the longitudinal trajectory of the target vehicle based on the accelerations at multiple moments calculated in the above manner and the longitudinal starting position of the target vehicle at the current moment, as shown in the following formula 7.

[0120] Formula 7:

[0121]

[0122] Where x(k) represents the longitudinal position of the target vehicle at time k; x k Represents the decision cycle T P The vertical starting position of represents the longitudinal velocity of the target vehicle at time k; T S Represents the decision cycle T P discrete time interval within a k represents the optimal acceleration of the target vehicle at time k.

[0123] In the embodiment of the present application, there are multiple behavior sequences in the target behavior decision tree. For each behavior sequence, the server can use the above method to calculate the driving trajectory (including lateral trajectory and longitudinal trajectory) corresponding to the behavior sequence. Correspondingly, for the target behavior decision tree, the server can determine multiple driving trajectories for the target vehicle as candidate trajectories of the target vehicle, so that the subsequent target vehicle can determine a driving trajectory from multiple driving trajectories to travel. The embodiment of the present application does not limit the selection method of the trajectory.

[0124] The embodiment of the present application provides a method for determining a driving trajectory, which can generate an initial behavior decision tree in real time according to the behavior of the target vehicle at the current moment, and can design behavior change restrictions and first heuristic rules that mainly focus on the vehicle based on human driving habits, and preliminarily prune the initial behavior decision tree. Secondly, or alternatively, a humanoid lane change warning model that considers vehicle heterogeneity and driver heterogeneity can be established to perform secondary pruning on the behavior decision tree from a safety perspective. Finally, according to the state corresponding to the vehicle behavior in each decision cycle in the target behavior decision tree, a driving trajectory corresponding to each behavior sequence in the target behavior decision tree is generated to provide it to the target vehicle for selection, thereby reducing the complexity of the decision algorithm, improving the efficiency of determining the driving trajectory, and at the same time helping to ensure the robustness of the subsequently determined driving trajectory, and having stronger practicality.

[0125] Figure 5 is a block diagram of a vehicle trajectory determination device provided according to an embodiment of the present application. The vehicle trajectory determination device is used to execute the steps of the vehicle trajectory determination method described above, see Figure 5 , the device comprises:

[0126] An acquisition module 501 is used to acquire the state data of the target vehicle, where the state data is used to represent the state of the target vehicle at the current moment;

[0127] A creation module 502 is used to create an initial behavior decision tree based on the state data. The root node in the initial behavior decision tree is used to represent the behavior performed by the target vehicle at the current moment. The other nodes in the initial behavior decision tree except the root node are used to represent the behaviors that the target vehicle can perform in the future time period. The behaviors that the target vehicle can perform include three categories: changing lanes to the left, keeping the original lane, and changing lanes to the right.

[0128] A first processing module 503 is used to prune the initial behavior decision tree based on at least one of a first heuristic rule and a second heuristic rule to obtain a target behavior decision tree, wherein the first heuristic rule is used to indicate that the number of behavior changes of the target vehicle in a future time period does not exceed a preset number, and the second heuristic rule is used to indicate that the target vehicle meets the lane change condition;

[0129] The second processing module 504 is used to fit the time and vehicle position in the future time period for each behavior sequence in the target behavior decision tree based on multiple behaviors and state data in the behavior sequence to obtain a driving trajectory corresponding to the behavior sequence.

[0130] In some embodiments, a creation module 502 is configured to:

[0131] Determine the behavior of the target vehicle at the current moment based on the longitudinal position, lateral position, first speed, second speed, yaw angle and yaw angular velocity of the target vehicle in the state data, where the first speed is the speed along the direction of the vehicle body and the second speed is the speed perpendicular to the direction of the vehicle body;

[0132] Based on the behavior performed by the target vehicle at the current moment, create the root node of the initial behavior decision tree;

[0133] Based on the behavior collection, on the basis of the root node, other nodes in the initial behavior decision tree except the root node are created. The behavior collection includes three types of behaviors that the target vehicle can perform;

[0134] Among them, any node other than the child node in the initial behavior decision tree corresponds to three child nodes, and the three child nodes of each node are used to represent changing lanes to the left, keeping the original lane, and changing lanes to the right.

[0135] In some embodiments, the first processing module 503 is used to:

[0136] Based on the first heuristic rule, multiple first nodes are determined from the initial behavior decision tree, the number of target node pairs between each first node and the root node is equal to a preset number, there is a parent-child relationship between two nodes in the target node pair, and the behaviors represented by the two nodes are different;

[0137] For any first node among the multiple first nodes, remove the second node corresponding to the first node and all nodes after the second node from the initial behavior decision tree, the second node is a child node of the first node, and the behavior represented by the second node is different from the behavior represented by the first node.

[0138] In some embodiments, the first processing module 503 is used to:

[0139] Based on the second heuristic rule, the first warning distance, the first lane-changing gap, the second warning distance, and the second lane-changing gap of the target vehicle at the current moment are obtained. The first warning distance is the minimum safe distance between the target vehicle and surrounding vehicles when changing lanes to the left. The first lane-changing gap is the distance between surrounding vehicles when the target vehicle changes lanes to the left. The second warning distance is the minimum safe distance between the target vehicle and surrounding vehicles when changing lanes to the right. The second lane-changing gap is the distance between surrounding vehicles when the target vehicle changes lanes to the right.

[0140] Based on the first warning distance, the first lane changing gap, the second warning distance and the second lane changing gap, nodes corresponding to the target behavior sequence are removed from the initial behavior decision tree to obtain a target behavior decision tree, where the target behavior sequence includes a target lane changing behavior, and the warning distance corresponding to the target lane changing behavior is less than the corresponding lane changing gap.

[0141] In some embodiments, the first processing module 503 is used to:

[0142] Based on the first heuristic rule, the initial behavior decision tree is pruned for the first time to obtain the first intermediate behavior decision tree;

[0143] Based on the second heuristic rule, the intermediate behavior decision tree is pruned for the second time to obtain the target behavior decision tree.

[0144] In some embodiments, the apparatus further comprises:

[0145] A third processing module is used to determine a plurality of third nodes from the initial behavior decision tree, wherein the behavior represented by each third node is opposite to the behavior represented by the parent node of the third node; and remove the plurality of third nodes and all nodes after the third node from the initial behavior decision tree to obtain a second intermediate behavior decision tree;

[0146] The first processing module 503 is used to prune the second intermediate behavior decision tree based on at least one of the first heuristic rule and the second heuristic rule to obtain a target behavior decision tree.

[0147] In some embodiments, the second processing module 504 includes:

[0148] A simulation unit, for performing a dynamic simulation on a target vehicle for each behavior sequence in the target behavior decision tree based on a plurality of behaviors and state data in the behavior sequence, and determining a terminal position of the target vehicle after a future time period;

[0149] A processing unit, configured to perform polynomial fitting based on the lateral starting position and the lateral end position of the target vehicle at the current moment and the moment in the future time period to obtain a lateral trajectory of the target vehicle, wherein the lateral trajectory is used to represent a change in the lateral position of the target vehicle in the future time period;

[0150] The determination unit is used to adopt a longitudinal following model to determine the acceleration at multiple moments in a future time period, and determine the longitudinal trajectory of the target vehicle based on the acceleration at multiple moments and the longitudinal starting position of the target vehicle at the current moment. The longitudinal trajectory is used to represent the change of the longitudinal position of the target vehicle in the future time period.

[0151] In some embodiments, the simulation unit is used to:

[0152] For each behavior sequence in the target behavior decision tree, based on the behaviors to be executed and the state data at multiple moments in the behavior sequence, a dynamic simulation is performed on the target vehicle to obtain the state data of the target vehicle at multiple moments, and the state data corresponding to each moment includes the longitudinal position of the target vehicle at the moment, the road adhesion coefficient, and the vehicle speed;

[0153] Clustering the state data at multiple moments to obtain multiple groups of state data;

[0154] For any group of state data among the multiple groups of state data, averaging multiple state data in the group state data to obtain central state data corresponding to the group state data;

[0155] Based on the center state data, the target vehicle is dynamically simulated to obtain the target vehicle's final position after a future time period.

[0156] The embodiment of the present application provides a device for determining a driving trajectory, which can generate an initial behavior decision tree in real time according to the behavior of the target vehicle at the current moment, and can design behavior change restrictions and first heuristic rules that mainly focus on the vehicle based on human driving habits, and preliminarily prune the initial behavior decision tree. Secondly, or it can also establish a human-like lane change warning model that considers vehicle heterogeneity and driver heterogeneity, and perform secondary pruning on the behavior decision tree from a safety perspective. Finally, according to the state corresponding to the vehicle behavior in each decision cycle in the target behavior decision tree, a driving trajectory corresponding to each behavior sequence in the target behavior decision tree is generated to provide it to the target vehicle for selection, thereby reducing the complexity of the decision algorithm, improving the efficiency of determining the driving trajectory, and at the same time helping to ensure the robustness of the subsequently determined driving trajectory, and having stronger practicality.

[0157] It should be noted that: the driving trajectory determination device provided in the above embodiment only uses the division of the above functional modules as an example when calculating the driving trajectory of the target vehicle in the future time period. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the driving trajectory determination device provided in the above embodiment and the driving trajectory determination method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0158] In the embodiments of the present application, the computer device can be configured as a terminal (such as the target vehicle itself) or a server. When the computer device is configured as a terminal, the terminal can be used as the execution subject to implement the technical solution provided in the embodiments of the present application. When the computer device is configured as a server, the server can be used as the execution subject to implement the technical solution provided in the embodiments of the present application. The technical solution provided in the present application can also be implemented through interaction between the terminal and the server. The embodiments of the present application are not limited to this.

[0159] Figure 6 It is a structural schematic diagram of a vehicle controller of a target vehicle provided according to an embodiment of the present application.

[0160] Typically, the vehicle controller 600 includes: a main control module 601, a CAN interface 602, a hard-wire input interface 603, and a hard-wire output interface 604. The main control module 601 is connected to the CAN interface 602, the hard-wire input interface 603, and the hard-wire output interface 604, respectively.

[0161] The main control module 601 generally includes a processor and a memory. Among them, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the vehicle display screen. In some embodiments, the processor may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning. The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include a high-speed random access memory and a non-volatile memory, such as one or more disk storage devices and flash storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory is used to store at least one computer program, and the at least one computer program is used to be executed by the processor to implement the method for determining the driving trajectory provided in the method embodiment of the present application.

[0162] The CAN interface 602 may include a power CAN interface, a motor CAN interface, and a diagnostic CAN interface, wherein the power CAN interface is used to communicate with a power system module of the vehicle, the motor CAN interface is used to communicate with a motor controller of the vehicle, and the diagnostic CAN interface is used to communicate with a diagnostic device.

[0163] The hard-wire input interface 603 is used to receive hard-wire control signals. The hard-wire output interface 604 is used to send control instructions to the electronic control components of the vehicle so that the electronic control components of the vehicle perform corresponding actions. The electronic control components of the vehicle include a power management system, a motor controller, an on-board charger, a body control system, etc.

[0164] The main control module 601 can communicate with the vehicle's power system module, motor controller and diagnostic equipment through the CAN interface 602, and generate control instructions based on the hard-wired control signal received by the hard-wired input interface 603 to send control instructions to the vehicle's electronic control components through the hard-wired output interface 604.

[0165] Those skilled in the art will understand that Figure 6 The structure shown in the figure does not constitute a limitation on the vehicle controller 600, and may include more or fewer components than shown in the figure, or combine certain components, or adopt a different component arrangement.

[0166] Figure 7 It is a structural diagram of a server provided according to an embodiment of the present application. The server 700 may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 701 and one or more memories 702, wherein the memory 702 stores at least one computer program, and the at least one computer program is loaded and executed by the processor 701 to implement the driving trajectory determination method provided by the above-mentioned various method embodiments. Of course, the server may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output. The server may also include other components for implementing device functions, which will not be described in detail here.

[0167] The embodiment of the present application also provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is loaded and executed by a processor of a computer device to implement the operation performed by the computer device in the method for determining the driving trajectory of the above embodiment. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device.

[0168] In some embodiments, the computer program involved in the embodiments of the present application may be deployed and executed on a computer device, or on multiple computer devices located at one location, or on multiple computer devices distributed at multiple locations and interconnected by a communication network. Multiple computer devices distributed at multiple locations and interconnected by a communication network may constitute a blockchain system.

[0169] The embodiment of the present application also provides a computer program product, including a computer program, which is stored in a computer-readable storage medium. The processor of the computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device executes the method for determining the driving trajectory provided in the above various optional implementations.

[0170] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0171] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining a driving trajectory, characterized in that: The method comprises: Acquire state data of a target vehicle, wherein the state data is used to represent the state of the target vehicle at a current moment; Based on the state data, an initial behavior decision tree is created, wherein a root node in the initial behavior decision tree is used to represent the behavior performed by the target vehicle at the current moment, and other nodes in the initial behavior decision tree except the root node are used to represent the behaviors that the target vehicle can perform in a future time period, and the behaviors that the target vehicle can perform include three categories: changing lanes to the left, keeping the original lane, and changing lanes to the right; Based on at least one of a first heuristic rule and a second heuristic rule, pruning the initial behavior decision tree to obtain a target behavior decision tree, wherein the first heuristic rule is used to indicate that the number of behavior changes of the target vehicle in the future time period does not exceed a preset number, and the second heuristic rule is used to indicate that the target vehicle meets the lane change condition; For each behavior sequence in the target behavior decision tree, based on multiple behaviors in the behavior sequence and the state data, the moments in the future time period are fitted with the vehicle positions to obtain a driving trajectory corresponding to the behavior sequence.

2. The method for determining a driving trajectory according to claim 1, characterized in that: The step of creating an initial behavior decision tree based on the state data comprises: Determine the behavior of the target vehicle at the current moment based on the longitudinal position, lateral position, first speed, second speed, yaw angle and yaw angular velocity of the target vehicle in the state data, wherein the first speed is the speed along the direction of the vehicle body, and the second speed is the speed perpendicular to the direction of the vehicle body; Based on the behavior performed by the target vehicle at the current moment, creating a root node of the initial behavior decision tree; Based on the behavior collection, on the basis of the root node, creating other nodes in the initial behavior decision tree except the root node, wherein the behavior collection includes three types of behaviors that the target vehicle can perform; Among them, any node other than the sub-node in the initial behavior decision tree corresponds to three sub-nodes, and the three sub-nodes of each node are respectively used to represent changing lanes to the left, keeping the original lane, and changing lanes to the right.

3. The method for determining a driving trajectory according to claim 1, characterized in that: The pruning of the initial behavior decision tree based on at least one of the first heuristic rule and the second heuristic rule to obtain a target behavior decision tree includes: Based on the first heuristic rule, a plurality of first nodes are determined from the initial behavior decision tree, the number of target node pairs between each first node and the root node is equal to the preset number, a parent-child relationship exists between two nodes in the target node pair, and the behaviors represented by the two nodes are different; For any first node among the multiple first nodes, remove the second node corresponding to the first node and all nodes after the second node from the initial behavior decision tree, where the second node is a child node of the first node and the behavior represented by the second node is different from the behavior represented by the first node.

4. The method for determining a vehicle trajectory according to claim 1, characterized in that: The pruning of the initial behavior decision tree based on at least one of the first heuristic rule and the second heuristic rule to obtain a target behavior decision tree includes: Based on the second heuristic rule, a first warning distance, a first lane-changing gap, a second warning distance, and a second lane-changing gap of the target vehicle at the current moment are obtained, wherein the first warning distance is the minimum safe distance between the target vehicle and surrounding vehicles when changing lanes to the left, the first lane-changing gap is the distance between surrounding vehicles when the target vehicle changes lanes to the left, the second warning distance is the minimum safe distance between the target vehicle and surrounding vehicles when changing lanes to the right, and the second lane-changing gap is the distance between surrounding vehicles when the target vehicle changes lanes to the right; Based on the first warning distance, the first lane changing gap, the second warning distance and the second lane changing gap, nodes corresponding to a target behavior sequence are removed from the initial behavior decision tree to obtain the target behavior decision tree, wherein the target behavior sequence includes a target lane changing behavior, and the warning distance corresponding to the target lane changing behavior is less than the corresponding lane changing gap.

5. The method for determining a driving trajectory according to claim 1, characterized in that: The pruning of the initial behavior decision tree based on at least one of the first heuristic rule and the second heuristic rule to obtain a target behavior decision tree includes: Based on the first heuristic rule, pruning the initial behavior decision tree for the first time to obtain a first intermediate behavior decision tree; Based on the second heuristic rule, the intermediate behavior decision tree is pruned for the second time to obtain the target behavior decision tree.

6. The method for determining a vehicle trajectory according to claim 1, characterized in that: The method further comprises: Determine a plurality of third nodes from the initial behavior decision tree, wherein the behavior represented by each third node is opposite to the behavior represented by the parent node of the third node; Remove the plurality of third nodes and all nodes after the third nodes from the initial behavior decision tree to obtain a second intermediate behavior decision tree; The pruning of the initial behavior decision tree based on at least one of the first heuristic rule and the second heuristic rule to obtain a target behavior decision tree includes: Based on at least one of the first heuristic rule and the second heuristic rule, the second intermediate behavior decision tree is pruned to obtain a target behavior decision tree.

7. The method for determining a vehicle's driving trajectory according to claim 1, characterized in that: For each behavior sequence in the target behavior decision tree, based on multiple behaviors in the behavior sequence and the state data, fitting the time in the future time period with the vehicle position to obtain the driving trajectory corresponding to the behavior sequence includes: For each behavior sequence in the target behavior decision tree, based on a plurality of behaviors in the behavior sequence and the state data, a dynamic simulation is performed on the target vehicle to determine a terminal position of the target vehicle after the future time period; Based on the lateral starting position of the target vehicle at the current moment and the lateral ending position of the starting position, a polynomial fitting is performed with the moments in the future time period to obtain a lateral trajectory of the target vehicle, wherein the lateral trajectory is used to represent the change of the lateral position of the target vehicle in the future time period; A longitudinal following model is used to determine the acceleration at multiple moments in the future time period, and based on the acceleration at the multiple moments and the longitudinal starting position of the target vehicle at the current moment, the longitudinal trajectory of the target vehicle is determined, and the longitudinal trajectory is used to represent the change in the longitudinal position of the target vehicle in the future time period.

8. The method for determining a vehicle's driving trajectory according to claim 7, characterized in that: For each behavior sequence in the target behavior decision tree, based on a plurality of behaviors in the behavior sequence and the state data, performing dynamic simulation on the target vehicle to determine the terminal position of the target vehicle after the future time period includes: For each behavior sequence in the target behavior decision tree, based on the behaviors to be executed at multiple moments in the behavior sequence and the state data, a dynamic simulation is performed on the target vehicle to obtain the state data of the target vehicle at the multiple moments, wherein the state data corresponding to each moment includes the longitudinal position, road adhesion coefficient and vehicle speed of the target vehicle at the moment; Clustering the state data at the multiple moments to obtain multiple groups of state data; For any group of status data among the multiple groups of status data, averaging multiple status data in the group of status data to obtain central status data corresponding to the group of status data; Based on the central state data, a dynamic simulation is performed on the target vehicle to obtain a terminal position of the target vehicle after the future time period.

9. A device for determining a vehicle trajectory, characterized in that: The device comprises: An acquisition module, used for acquiring status data of a target vehicle, wherein the status data is used for indicating the status of the target vehicle at a current moment; A creation module, used for creating an initial behavior decision tree based on the state data, wherein the root node in the initial behavior decision tree is used to represent the behavior performed by the target vehicle at the current moment, and other nodes in the initial behavior decision tree except the root node are used to represent the behaviors that the target vehicle can perform in a future time period, and the behaviors that the target vehicle can perform include three categories: changing lanes to the left, keeping the original lane, and changing lanes to the right; a first processing module, configured to prune the initial behavior decision tree based on at least one of a first heuristic rule and a second heuristic rule to obtain a target behavior decision tree, wherein the first heuristic rule is used to indicate that the number of behavior changes of the target vehicle in the future time period does not exceed a preset number, and the second heuristic rule is used to indicate that the target vehicle meets the lane change condition; The second processing module is used to fit the moments in the future time period with the vehicle positions for each behavior sequence in the target behavior decision tree based on multiple behaviors in the behavior sequence and the state data to obtain a driving trajectory corresponding to the behavior sequence.

10. A computer device, characterized in that: The computer device includes a processor and a memory, the memory is used to store at least one computer program, and the at least one computer program is loaded by the processor and executes the method for determining the vehicle trajectory according to any one of claims 1 to 8.

Images