Automatic driving decision-making method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to an automatic driving decision-making method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring environment information of an environment where a target object is located and a plurality of first candidate paths of the target object; determining a plurality of first prediction trajectories corresponding to each traffic participant in the current environment and first importance weights corresponding to the first prediction trajectories according to a trajectory prediction model and the environment information; the trajectory prediction model is trained through a decision cost function; and determining a decision cost corresponding to each first candidate path based on the first candidate paths, the first prediction trajectory, the first importance weight and a decision cost function, and determining a target path in the first candidate paths according to the decision cost. By adopting the method, the safety of automatic driving can be improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to an autonomous driving decision-making method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] Autonomous driving vehicles will face more dangerous environmental conditions and more complex decision-making behaviors in complex traffic environments. The safe driving of autonomous driving vehicles requires accurate and reliable decision-making methods.

[0003] In traditional technology, the vehicle-computer system of an autonomous driving vehicle includes a prediction module and a planning module. The prediction module predicts the future trajectory of traffic participants by sensing environmental information and information about traffic participants. The planning module combines environmental information and the future trajectory of traffic participants to determine a target path that does not overlap with or is a certain distance away from the future trajectory.

[0004] However, in traditional methods, the planning module has a poor utilization rate of the output results of the prediction module, and the effects of the prediction module and the planning module on information decision-making are independent of each other, which leads to poor safety of autonomous driving. Summary of the invention

[0005] Based on this, it is necessary to provide an autonomous driving decision-making method, device, computer equipment, computer-readable storage medium and computer program product to address the above-mentioned technical problems.

[0006] In a first aspect, the present application provides an autonomous driving decision-making method, comprising:

[0007] Acquire environmental information of an environment in which a target object is located and a plurality of first candidate paths of the target object;

[0008] Determine, according to the trajectory prediction model and the environmental information, a plurality of first predicted trajectories corresponding to each traffic participant in the current environment and a first importance weight corresponding to each of the first predicted trajectories; the trajectory prediction model is trained by a decision cost function;

[0009] Based on the first candidate paths, the first predicted trajectory, the first importance weight, and the decision cost function, a decision cost corresponding to each of the first candidate paths is determined, and a target path is determined among the first candidate paths according to the decision cost.

[0010] In one of the embodiments, before acquiring the environment information of the environment in which the target object is located and the plurality of first candidate paths of the target object, the method further includes:

[0011] Obtaining a sample data set and a trajectory label and a path selection label corresponding to each sample data in the sample data set;

[0012] Performing prediction processing on each of the sample data according to the trajectory prediction model to be trained, to obtain a second predicted trajectory and a second importance weight corresponding to each of the second predicted trajectories;

[0013] determining an accuracy prediction loss based on the trajectory label and the second predicted trajectory, and determining a path planning loss based on the second importance weight, the decision cost function, and the path selection label;

[0014] The model parameters of the trajectory prediction model to be trained are updated through back propagation until the accuracy prediction loss and the path planning loss meet a preset loss threshold, thereby obtaining a trained trajectory prediction model.

[0015] In one embodiment, determining the path planning loss based on the second importance weight, the decision cost function and the path selection label includes:

[0016] Constructing a historical sampling space according to the sample data set; the historical sampling space includes a plurality of historical candidate paths determined based on the sample data;

[0017] Among the historical candidate paths, determining the historical candidate path with the smallest distance to the path selection label as the expert trajectory;

[0018] A path planning loss is determined based on the expert trajectory and the decision cost function.

[0019] In one embodiment, before determining the decision cost corresponding to each of the first candidate paths based on the first candidate paths, the first predicted trajectory, the first importance weight and the decision cost function, the method further includes:

[0020] Acquire initial candidate paths, and screen the initial candidate paths according to a preset dynamic constraint sub-model to obtain preliminary screening candidate paths;

[0021] The initially screened candidate paths are screened a second time according to a preset collision safety constraint sub-model to obtain a first candidate path.

[0022] In one embodiment, the decision cost function includes a decision safety cost function, a decision efficiency cost function and a decision comfort cost function; the decision cost includes a decision safety cost, a decision efficiency cost and a decision comfort cost;

[0023] The determining, based on the first candidate paths, the first predicted trajectories, the first importance weights, and the decision cost function, a decision cost corresponding to each of the first candidate paths includes:

[0024] Determining the decision safety cost based on the initial candidate path, the first predicted trajectory, the first importance weight, and the decision safety cost function;

[0025] Determining the decision efficiency cost based on the initial candidate path, the destination coordinates and a decision efficiency cost function;

[0026] The decision comfort cost is determined based on the initial candidate path and a decision comfort cost function.

[0027] In one embodiment, obtaining the initial candidate path includes:

[0028] Get the preset path starting point and path end point;

[0029] generating a global path based on the path starting point and the path end point;

[0030] A plurality of initial candidate paths for the target object are generated according to preset lateral and longitudinal offset distances and the global path.

[0031] In a second aspect, the present application also provides an automatic driving decision-making device, comprising:

[0032] A first acquisition module, used to acquire environmental information of an environment where a target object is located and a plurality of first candidate paths of the target object;

[0033] A first prediction module, used to determine a plurality of first predicted trajectories corresponding to each traffic participant in the current environment and a first importance weight corresponding to each of the first predicted trajectories according to a trajectory prediction model and the environmental information; the trajectory prediction model is trained by a decision cost function;

[0034] A planning module is used to determine the decision cost corresponding to each of the first candidate paths based on the first candidate paths, the first predicted trajectory, the first importance weight and the decision cost function, and determine the target path among the first candidate paths according to the decision cost.

[0035] In one embodiment, the device further comprises:

[0036] A second acquisition module is used to acquire a sample data set and a trajectory label and a path selection label corresponding to each sample data in the sample data set;

[0037] A second prediction module, used to perform prediction processing on each of the sample data according to the trajectory prediction model to be trained, to obtain a second predicted trajectory and a second importance weight corresponding to each of the second predicted trajectories;

[0038] a loss calculation module, configured to determine an accuracy prediction loss based on the trajectory label and the second predicted trajectory, and to determine a path planning loss based on the second importance weight, the decision cost function and the path selection label;

[0039] The training module is used to update the model parameters of the trajectory prediction model to be trained through back propagation until the accuracy prediction loss and the path planning loss meet a preset loss threshold, thereby obtaining a trained trajectory prediction model.

[0040] In one of the embodiments, the loss calculation module is specifically used to construct a historical sampling space according to the sample data set; the historical sampling space includes a plurality of historical candidate paths determined based on the sample data;

[0041] Among the historical candidate paths, determining the historical candidate path with the smallest distance to the path selection label as the expert trajectory;

[0042] A path planning loss is determined based on the expert trajectory and the decision cost function.

[0043] In one embodiment, the device further comprises:

[0044] A first screening module is used to obtain initial candidate paths, and screen the initial candidate paths according to a preset dynamic constraint sub-model to obtain a preliminary screening candidate path;

[0045] The second screening module is used to perform a secondary screening on the initially screened candidate paths according to a preset collision safety constraint sub-model to obtain a first candidate path.

[0046] In one embodiment, the decision cost function includes a decision safety cost function, a decision efficiency cost function and a decision comfort cost function; the decision cost includes a decision safety cost, a decision efficiency cost and a decision comfort cost;

[0047] The planning module is specifically used to determine the decision safety cost based on the initial candidate path, the first predicted trajectory, the first importance weight and the decision safety cost function;

[0048] Determining the decision efficiency cost based on the initial candidate path, the destination coordinates and a decision efficiency cost function;

[0049] The decision comfort cost is determined based on the initial candidate path and a decision comfort cost function.

[0050] In one of the embodiments, the planning module is specifically used to obtain a preset path starting point and a path end point;

[0051] generating a global path based on the path starting point and the path end point;

[0052] A plurality of initial candidate paths for the target object are generated according to preset lateral and longitudinal offset distances and the global path.

[0053] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0054] Acquire environmental information of an environment in which a target object is located and a plurality of first candidate paths of the target object;

[0055] Determine, according to the trajectory prediction model and the environmental information, a plurality of first predicted trajectories corresponding to each traffic participant in the current environment and a first importance weight corresponding to each of the first predicted trajectories; the trajectory prediction model is trained by a decision cost function;

[0056] Based on the first candidate paths, the first predicted trajectory, the first importance weight, and the decision cost function, a decision cost corresponding to each of the first candidate paths is determined, and a target path is determined among the first candidate paths according to the decision cost.

[0057] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0058] Acquire environmental information of an environment in which a target object is located and a plurality of first candidate paths of the target object;

[0059] Determine, according to the trajectory prediction model and the environmental information, a plurality of first predicted trajectories corresponding to each traffic participant in the current environment and a first importance weight corresponding to each of the first predicted trajectories; the trajectory prediction model is trained by a decision cost function;

[0060] Based on the first candidate paths, the first predicted trajectory, the first importance weight, and the decision cost function, a decision cost corresponding to each of the first candidate paths is determined, and a target path is determined among the first candidate paths according to the decision cost.

[0061] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0062] Acquire environmental information of an environment in which a target object is located and a plurality of first candidate paths of the target object;

[0063] Determine, according to the trajectory prediction model and the environmental information, a plurality of first predicted trajectories corresponding to each traffic participant in the current environment and a first importance weight corresponding to each of the first predicted trajectories; the trajectory prediction model is trained by a decision cost function;

[0064] Based on the first candidate paths, the first predicted trajectory, the first importance weight, and the decision cost function, a decision cost corresponding to each of the first candidate paths is determined, and a target path is determined among the first candidate paths according to the decision cost.

[0065] The above-mentioned autonomous driving decision-making method, device, computer equipment, computer-readable storage medium and computer program product analyze environmental information through a trajectory prediction model trained by a quantitative evaluation of safety reflected by a decision cost function to obtain multiple first predicted trajectories of each traffic participant and a first importance weight of each first predicted trajectory. At the same time, the planning of the target path is also obtained by screening each first candidate path based on the constraints of the decision cost function and the first predicted trajectory and the first importance weight, so that the decision cost function is introduced into the prediction and path planning of autonomous driving at the same time, and the first importance weight is transmitted as safety information in the two stages of trajectory prediction and path planning, thereby strengthening the connection between trajectory prediction and path planning, and improving the utilization rate of the output results of the trajectory prediction model in the path planning stage, thereby improving the accuracy of path planning guided by safety, and further improving the safety of autonomous driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions 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 related drawings can be obtained based on these drawings without paying creative work.

[0067] Figure 1 A diagram of an application environment of an autonomous driving decision-making method in an embodiment;

[0068] Figure 2 is a schematic diagram of a decision cost function in one embodiment;

[0069] Figure 3 A schematic diagram of a process for training a trajectory prediction model in one embodiment;

[0070] Figure 4 A schematic diagram of a flow chart of an example of training a trajectory prediction model in one embodiment;

[0071] Figure 5 A schematic diagram of a process for determining a path planning loss in one embodiment;

[0072] Figure 6 A schematic diagram of a process of determining a first candidate path through path screening in one embodiment;

[0073] Figure 7 A schematic diagram of a process for calculating a decision cost according to a decision cost function in one embodiment;

[0074] Figure 8 A schematic diagram of a process for generating an initial candidate path in one embodiment;

[0075] Fig. 9 is a structural block diagram of an automatic driving decision-making device in an embodiment;

[0076] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0077] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0078] In one embodiment, Figure 1 As shown, an automatic driving decision method is provided. This embodiment takes the method applied to a terminal as an example. The terminal may be a vehicle-mounted terminal of an automatic driving vehicle. It is understandable that the method may also be applied to a server, or to a system including a terminal and a server, and implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0079] Step 102: Acquire environmental information of the environment where the target object is located and a plurality of first candidate paths of the target object.

[0080] In the embodiments of the present application, the autonomous driving vehicle is used as the target object for explanation. The safe driving of the autonomous driving vehicle requires accurate and reliable decision-making to determine the control of the autonomous driving vehicle. The terminal selects the target path of the autonomous driving vehicle in the future time step based on the environmental information transmitted from the upstream, including the information of the traffic participants, to achieve autonomous driving. Therefore, the structure used for autonomous driving decision-making in the terminal can be divided into a trajectory prediction model and a planning model. The trajectory prediction model is used to predict the possible trajectories of other traffic participants in the current environment in the future; the planning model is used to select the target path in combination with the prediction results output by the trajectory prediction model.

[0081] First, the terminal collects environmental information around the vehicle by using sensors (e.g., cameras, lidar, millimeter-wave radar, etc.). Environmental information may include information about traffic participants, road structure information, and obstacle information. Among them, information about traffic participants includes the current position and speed of traffic participants such as vehicles, pedestrians, and bicycles; road structure information includes road structure, such as lane lines, traffic signs, and traffic lights; obstacle information includes buildings, roadblocks, etc. Then, the terminal processes and fuses the sensor data to generate a comprehensive understanding of the current environment. At the same time, the terminal pre-generates multiple first candidate paths based on environmental information to cover different driving strategies. For example, different first candidate paths represent paths such as lane keeping, lane changing, and deceleration.

[0082] Step 104 , determining a plurality of first predicted trajectories corresponding to each traffic participant in the current environment and a first importance weight corresponding to each first predicted trajectory according to the trajectory prediction model and the environmental information.

[0083] Among them, the trajectory prediction model is trained through the decision cost function.

[0084] The first predicted trajectory and the first importance weight are output results of the trajectory prediction model in the application phase.

[0085] In the embodiment of the present application, the terminal constructs and trains the trajectory prediction model .in, For environmental data, is the decision cost function. For high-density traffic and high-risk scenarios such as intersections and highways, the terminal builds a trajectory prediction model based on a deep neural network. The trajectory prediction model is based on environmental data. As input, environmental data The features include: historical trajectories of traffic participants, interaction status of traffic participants, historical trajectories of the ego vehicle and future plans.

[0086] The terminal inputs the environmental information including the road environment data into the trajectory prediction model, and obtains the multiple possible first predicted trajectories of each traffic participant in the current environment within a certain time step in the future and the first importance weight corresponding to each first predicted trajectory within the time step through the mapping relationship between the pre-trained environmental information in the trajectory prediction model and the first predicted trajectory and the first importance weight corresponding to each first predicted trajectory in the time step, so as to characterize the risk and importance of the first predicted trajectory in the target path decision. Among them, the trajectory prediction model is composed of a historical trajectory encoder, an ego vehicle state information encoder, an interactive feature encoder, a predicted trajectory decoder, and a planning importance perception module decoder.

[0087] Among them, the interactive feature encoder adopts a graph neural network structure, the historical trajectory encoder and the self-vehicle state information encoder adopt a network structure based on long short-term memory (LSTM), and the predicted trajectory decoder and the planning perception decoder uniformly adopt a network structure based on the gated recurrent unit (GRU).

[0088] The interactive feature encoder is used to encode the spatial interactive features between the ego vehicle and traffic participants, or between multiple traffic participants. In autonomous driving scenarios, the interactive relationships between traffic participants (e.g., vehicles, pedestrians, bicycles, etc.) are very complex. Using graph neural networks as interactive feature encoders can effectively model the fine spatial and topological relationships between the ego vehicle and traffic participants, as well as between each traffic participant. At the same time, at each time step, the position and state of traffic participants are dynamically changing. The use of graph neural networks can adapt to scenarios where the states of traffic participants are constantly changing. In addition, the topological invariance of graph neural networks makes graph neural networks insensitive to the connection mode of nodes, and can better handle the changes in the relationship between nodes (traffic participants) in complex traffic scenarios. Therefore, graph neural networks are more suitable for processing the interactive features between traffic participants and ego vehicles in dynamic environments.

[0089] In the interactive feature encoder, traffic participants are regarded as nodes of the graph, and the interactions between nodes (e.g., distance, speed, etc.) are represented as edges. The graph neural network aggregates the information of adjacent nodes through the message passing mechanism. Each node updates its own state according to the state (features) of its adjacent nodes. This message passing process enables the interactive feature encoder to capture the mutual influence between traffic participants, learn complex interaction patterns, and dynamically adjust the edges of the graph according to the current environmental conditions, so as to achieve flexible response to dynamic interactions and obtain the interactive features of each traffic participant.

[0090] For the historical trajectory encoder and the self-vehicle state information encoder, the long short-term memory structure can capture the time dependency between the historical trajectory and the self-vehicle state. The LSTM structure effectively solves the gradient vanishing and explosion problems in long sequence training by introducing a gating mechanism (input gate, forget gate, and output gate), so that the LSTM structure can effectively capture information in a long time range, retain and update the state within several time steps, and is suitable for processing complex historical trajectory sequences. Therefore, the historical trajectory encoder and the self-vehicle state information encoder adopt a long short-term memory structure. The LSTM structure controls the flow of information through a gating structure, determines the extent to which each input affects the current hidden state and output, stores long-term dependent information through memory units, and selectively deletes unnecessary information through forget gates. At each time step, the LSTM structure updates its internal state and generates output in combination with the current input, thereby encoding the time series of information and obtaining the characteristics between the historical trajectory and the self-state.

[0091] The trajectory prediction and importance weights in the prediction trajectory decoder and planning importance perception module decoder both involve processing time series data. In the autonomous driving scenario, the future position of each traffic participant is closely related to the current and past position states. The gating mechanism of the GRU structure enables it to adapt to this dynamic time dependency and effectively learn trends and patterns in time series data. The prediction trajectory decoder and planning perception decoder need to gradually generate prediction targets under the current state. Therefore, in autonomous driving, the trajectory and state information change rapidly and variably, and the GRU structure enables the trajectory prediction model to show strong adaptability when dealing with rapidly changing environments.

[0092] Step 106, based on the first candidate paths, the first predicted trajectory, the first importance weight and the decision cost function, determine the decision cost corresponding to each first candidate path, and determine the target path from the first candidate paths according to the decision cost.

[0093] In the embodiment of the present application, a decision cost function is pre-set in the planning model of the terminal, such as Figure 2 As shown in the figure, for driving risk scenarios and common planning task problems in autonomous driving, such as turning, going straight, etc., a decision cost function based on driving needs is constructed The decision cost function mainly includes the decision safety cost function, the decision efficiency cost function and the decision comfort cost function. The unified decision cost function is based on the idea of ​​minimizing the optimal planning. The form of is the linear weighting of the above decision safety cost function, decision efficiency cost function and decision comfort cost function:

[0094]

[0095] in, represents the weight coefficient, ,Right now .

[0096] The terminal calculates the multiple first predicted trajectories corresponding to each traffic participant output by the trajectory prediction model and the first importance weight corresponding to each first predicted trajectory in combination with the decision cost function and the first candidate path to obtain the decision cost of each first candidate path. The decision cost evaluates the safety, efficiency and comfort of each first candidate path, and selects the first candidate path with the lowest decision cost as the optimal path, that is, as the target path.

[0097] Among them, the target path is a part of the global path, that is, after obtaining the only optimal trajectory as the target path, the ego vehicle will move forward along the target path for one time step at this moment, and at the next time step, the process from step 102 to step 106 will be repeated until the terminal determines that the ego vehicle has reached the end of the global path, and then the execution of all processes is terminated. In use, the decision frequency is set to 10Hz, the prediction history time domain and future time domain are set to 6 frames and 20 frames respectively, and the decision future time domain is set to 20 frames.

[0098] In the above-mentioned autonomous driving decision-making method, the trajectory prediction model trained by the quantitative evaluation of safety reflected by the decision cost function analyzes the environmental information to obtain multiple first predicted trajectories of each traffic participant and the first importance weight of each first predicted trajectory. At the same time, the planning of the target path is also obtained by screening each first candidate path through the constraints of the decision cost function and combining the first predicted trajectory and the first importance weight, so that the decision cost function is introduced into the prediction and path planning of autonomous driving at the same time, and the first importance weight is transmitted as safety information in the two stages of trajectory prediction and path planning, thereby strengthening the connection between trajectory prediction and path planning, and improving the utilization rate of the output results of the trajectory prediction model in the path planning stage, thereby improving the accuracy of path planning guided by safety, and then improving the safety of autonomous driving.

[0099] In an exemplary embodiment, Figure 3 As shown, before step 102, the trajectory prediction model needs to be trained first, and the method also includes steps 302 to 308. Among them:

[0100] Step 302: Obtain a sample data set and a trajectory label and a path selection label corresponding to each sample data in the sample data set.

[0101] In an embodiment of the present application, the terminal uses historical data in high-density vehicle scenarios such as intersections and highways as sample data to construct a sample data set. The sample data includes the historical trajectory of each traffic participant in a preset scenario, the interaction characteristics between each traffic participant and the self-vehicle and between each traffic participant, and the historical trajectory and future path of the self-vehicle. Specifically, the terminal can obtain a random number in advance based on a random number seed, and randomly initialize the model parameters of the trajectory prediction model to be trained based on the random number, and divide it into a training set and a validation set according to the date and time corresponding to the sample data to obtain a sample data set. Among them, the trajectory label reflects the actual path that other traffic participants should take in a specific environment, and is used to guide the training to generate predicted trajectories; the path selection label represents the path selected by the planning model under the state of the sample data, and is used to guide the generation of importance weights.

[0102] Step 304 , performing prediction processing on each sample data according to the trajectory prediction model to be trained, and obtaining a second predicted trajectory and a second importance weight corresponding to each second predicted trajectory.

[0103] The second predicted trajectory and the second importance weight are output results of the trajectory prediction model in the training phase.

[0104] In an embodiment of the present application, the terminal inputs the training set in the sample data set into the trajectory prediction model to be trained, and generates and outputs the prediction results for each sample data through the trajectory prediction model to be trained, including the second predicted trajectory corresponding to each traffic participant contained in the sample data and the second importance weight corresponding to each second predicted trajectory. The second predicted trajectory output by the current trajectory prediction model to be trained may be different from the trajectory label. At the same time, the second importance weight based on the current prediction output may cause the subsequent planning model to select other paths other than the path selection label as the target path. Therefore, it is necessary to adjust the model parameters to optimize the accuracy of the output results of the model trajectory prediction model to be trained.

[0105] Step 306 , determining the accuracy prediction loss based on the trajectory label and the second predicted trajectory, and determining the path planning loss based on the second importance weight, the decision cost function and the path selection label.

[0106] In the embodiment of the present application, for the trajectory prediction model to be trained The training process, in which is the historical trajectory of environmental objects in the sample data, is the policy cost function, is the second predicted trajectory output by the trajectory prediction model to be trained, It is the second importance weight output by the trajectory prediction model to be trained.

[0107] The terminal calculates the accuracy loss of the trajectory prediction model to be trained by comparing the second predicted trajectory with the actual trajectory label. Specifically, the predicted trajectory accuracy Calculate the accuracy prediction loss through the Evidence Lower Bound (ELBO) principle To constrain:

[0108]

[0109] Among them, X is the historical trajectory of the environment object, E is the target path of the self-vehicle, Y is the second predicted trajectory, and Z is the intermediate variable of the auxiliary ELBO loss. and The two distributions of the intermediate variable Z are obtained, where For the training process, For inference, these two distributions are fitted during training. For the decoder, Characterize the calculation of KL divergence, characterize so that and distribution as close as possible. is the mathematical expectation, representing the training process from Z-pair decoder for distributed sampling The impact of output.

[0110] For path planning loss, the terminal uses the second importance weight, decision cost function and path selection label to comprehensively calculate the loss. The decision cost function is used to consider the actual cost of path selection and is combined with the path selection label to evaluate the performance of the trajectory prediction model to be trained in path selection.

[0111] Step 308, updating the model parameters of the trajectory prediction model to be trained by back propagation until the accuracy prediction loss and the path planning loss meet the preset loss conditions, thereby obtaining a trained trajectory prediction model.

[0112] In an embodiment of the present application, the training process of the trajectory prediction model to be trained updates the model parameters through back propagation, and verifies the path selection under the second predicted trajectory and the second importance weight through the verification set. If the accuracy prediction loss and the path planning loss still do not meet the preset loss conditions, the model parameters of the trajectory prediction model to be trained continue to be adjusted until the accuracy prediction loss and the path planning loss meet the preset loss conditions. The trajectory prediction model to be trained is considered to be within an acceptable accuracy range, and a trained trajectory prediction model is obtained.

[0113] In this embodiment, the loss of the trajectory prediction model to be trained is calculated based on the prediction results through sample data and corresponding trajectory labels and path selection labels, and the model parameters of the trajectory prediction model are continuously iterated and updated to obtain a high-performance trajectory prediction model. In the autonomous driving vehicle, the training mechanism enables the trajectory prediction model to be trained to better understand the environment and the impact of different predicted trajectories on decision-making.

[0114] In a specific embodiment, Figure 4 As shown, an example of training a trajectory prediction model is provided, including:

[0115] Step 401, the trajectory prediction model to be trained is randomly initialized;

[0116] Step 402, dividing the sample data set into a training set and a validation set, and randomly shuffling the data arrangement;

[0117] Step 403 , the prediction capability of the trajectory prediction model to be trained is evaluated according to the scene trajectory true value in the validation set, and the decision capability is evaluated according to the scene trajectory true value and the decision cost function, so as to complete the training of the trajectory prediction model to be trained.

[0118] In an exemplary embodiment, Figure 5 As shown, step 306 includes steps 502 to 506. Among them:

[0119] Step 502: construct a historical sampling space according to the sample data set.

[0120] The historical sampling space includes a plurality of historical candidate paths determined based on sample data.

[0121] In the embodiment of the present application, the sample data includes the starting point and the end point of the ego vehicle. When the terminal is training the trajectory prediction model to be trained, a plurality of historical candidate paths are constructed according to the same principle as step 102 to constitute a historical sampling space of the training process. That is, in the training process of the trajectory prediction model to be trained, it is necessary to guide the generation of importance weights in the selection of a plurality of historical candidate paths.

[0122] Step 504 : among the historical candidate paths, determine the historical candidate path with the smallest distance to the path selection label as the expert trajectory.

[0123] In the embodiment of the present application, the importance of the predicted trajectory to the future of the ego vehicle (the second importance weight) Constraints are implemented through planning perception. The specific training process is as follows: First, a historical sampling space is constructed based on the sample data set. , including candidate planning paths for the vehicle in different scenarios , is the number of candidate paths. The terminal uses the path selection label in the historical sampling space as the real future planning behavior of humans, and selects the path with the closest L2 distance to the path selection label in the historical sampling space as the security expert trajectory. :

[0124]

[0125] in, Characterizing candidate planning paths exist The location at the moment, Indicates the path corresponding to the path selection label.

[0126] Step 506 , determining the path planning loss based on the expert trajectory and the decision cost function.

[0127] In the embodiment of the present application, the terminal uses the expert trajectory as the label trajectory to guide the second predicted trajectory generated by the trajectory prediction model to be trained. and the second importance weight Generate a decision cost function Select the label trajectory, that is, supervise the planning model to maximize the probability of selecting the label trajectory, thereby obtaining the planning-related path planning loss :

[0128]

[0129]

[0130] In the formula, Refers to calculating the decision cost function Extensive information on the scene required.

[0131] At this point, the training of the trajectory prediction model is completed. On the one hand, the task of predicting trajectory accuracy is supervised. On the other hand, from the perspective of planning, the important modes of the trajectory are self-selected and importance weights are generated in a data-driven way.

[0132] In this embodiment, by referring to the historical candidate paths corresponding to the sample data set and quantitatively evaluating the decision costs, the trajectory prediction model can be improved to generate importance weights that are more suitable for each predicted trajectory through more accurate decision selection, so that the predicted trajectory and importance weights generated by it can better guide the decision-making process of the planning model.

[0133] In an exemplary embodiment, Figure 6 As shown, before step 106, the method further includes steps 602 to 604. Among them:

[0134] Step 602, obtaining initial candidate paths, screening the initial candidate paths according to a preset dynamic constraint sub-model, and obtaining pre-screened candidate paths.

[0135] In the embodiment of the present application, the planning model includes a collision safety constraint sub-model, a dynamic constraint sub-model and a global path sub-model. The global path sub-model is used to generate an initial candidate path, and the terminal is pre-set with a preset collision safety constraint sub-model, which is based on road environment information, such as the shape, position, and road edge line of traffic participants, considering driving safety issues, setting the minimum safe distance for object interaction, and constructing a collision prevention circular curve.

[0136] First, the terminal obtains a series of initial candidate paths from the global path sub-model. These paths may be generated based on map information, target location, traffic rules, etc., and these initial candidate paths are screened using the preset dynamic constraint sub-model. The dynamic constraint sub-model takes into account the dynamic characteristics of the vehicle, such as maximum control speed, acceleration, maximum control angle, etc., to ensure the feasibility of the initial candidate paths.

[0137] Step 604 , performing a secondary screening on the initially screened candidate paths according to a preset collision safety constraint sub-model to obtain a first candidate path.

[0138] In the embodiment of the present application, the terminal is also pre-set with a dynamic constraint sub-model constructed according to the vehicle dynamics information and the current state information, combined with the vehicle limit variable constraint information, the maximum control speed and acceleration, and the maximum control angle. For each preliminary screening candidate path, the terminal evaluates whether its distance from other objects in the road environment meets the minimum safety distance requirements and whether a collision is likely to occur through a preset collision safety constraint sub-model, completes the secondary screening of the preliminary screening candidate paths, and obtains the first candidate path, which meets both the dynamic constraints and the collision safety requirements, and is the basis for subsequent path planning and decision-making.

[0139] In this embodiment, by presetting the collision safety constraint sub-model and the preset dynamic constraint sub-model, it can be ensured that the first candidate path finally obtained not only meets the requirements of global planning, but also takes into account the dynamic characteristics and driving safety of the vehicle. In addition, the preliminary screening according to the preset collision safety constraint sub-model and the preset dynamic constraint sub-model can reduce the amount of calculation compared to calculating the decision cost of each initial candidate path, thereby improving the computational efficiency of path planning.

[0140] In an exemplary embodiment, Figure 7As shown, the decision cost function includes a decision safety cost function, a decision efficiency cost function and a decision comfort cost function; the decision cost includes a decision safety cost, a decision efficiency cost and a decision comfort cost; step 106 includes steps 702 to 706. Wherein:

[0141] Step 702 : determining a decision safety cost based on the initial candidate path, the first predicted trajectory, the first importance weight, and the decision safety cost function.

[0142] In the embodiment of the present application, the terminal first constructs a decision safety cost function to evaluate the collision risk between the first candidate path and the first predicted trajectory. , and the first predicted trajectory of a traffic participant , based on the basic idea of ​​keeping a safe distance from surrounding traffic participants, the decision safety cost function The calculation formula is:

[0143]

[0144] in, Indicates the number of multimodalities, representing the number of different traffic participants and exhibiting different behavior patterns (e.g., going straight, turning, accelerating, etc.), represents the planning time domain, Represents the first importance weight generated by the trajectory prediction model. Characterized by time A traffic participant at the time The first predicted trajectory of Characterizing the first prediction trajectory The corresponding first importance weight.

[0145] Step 704 , determining the decision efficiency cost based on the initial candidate path, the destination coordinates and the decision efficiency cost function.

[0146] In the embodiment of the present application, for the decision efficiency cost function, the terminal accelerates the autonomous driving car to reach the destination The basic idea of ​​efficiency, decision efficiency cost function The calculation formula is:

[0147]

[0148] in, is the first candidate path in The location at the moment, For the destination.

[0149] Step 706 , determining the decision comfort cost based on the initial candidate path and the decision comfort cost function.

[0150] In the embodiment of the present application, for constructing a decision comfort cost function, the terminal is based on the basic idea of ​​ensuring the safety of the autonomous driving car and controlling the cost, and the decision comfort cost function is constructed. The calculation formula is:

[0151]

[0152] in, The distance traveled in the forward direction after the route is converted to the Frenet coordinate system.

[0153] In this embodiment, a comprehensive evaluation of the path planning of the autonomous driving vehicle is achieved by constructing a decision safety cost function, a decision efficiency cost function, and a decision comfort cost function. Overall, these three cost functions help the autonomous driving system balance safety, efficiency, and comfort when planning the path, so as to make better decisions. At the same time, the upstream trajectory prediction model and the downstream planning model are uniformly constrained and designed through the decision cost function, so as to achieve consistency between upstream and downstream tasks to ensure the improvement of planning effect, ensure the unity of the safety utility of the autonomous driving decision method, and thus improve the safety and reliability of the autonomous driving system.

[0154] In an exemplary embodiment, Figure 8 As shown, step 602 includes steps 802 to 806. Among them:

[0155] Step 802, obtaining a preset path starting point and path end point.

[0156] In an embodiment of the present application, the terminal may use the current position of the vehicle as the starting point of the path and obtain the destination input by the user as the end point of the path.

[0157] Step 804: Generate a global path based on the path start point and the path end point.

[0158] In the embodiment of the present application, during the first planning, the terminal first generates a global planning path, and obtains a global path G connecting the path starting point and the path end point through a deep search method.

[0159] Step 806 , generating a plurality of initial candidate paths of the target object according to the preset horizontal and vertical offset distances and the global path.

[0160] In the embodiment of the present application, each subsequent planning sampling local planning path wherein the specific sampling method is combined with the global path G, such as Fig. 9 As shown in FIG. 1 , different lateral and longitudinal offset distances are used to obtain candidate trajectory points using a quartic spline curve to form a trajectory sampling set. The trajectory sampling set contains multiple sampled candidate trajectories pointing to the target position point to form an initial candidate path.

[0161] In this embodiment, according to the preset lateral and longitudinal offset distances, multiple initial candidate paths are generated on the basis of the global path, and the candidate paths provide abundant choices for subsequent path screening and optimization, thereby improving the diversity and accuracy of path screening.

[0162] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0163] Based on the same inventive concept, the embodiment of the present application also provides an autonomous driving decision-making device for implementing the autonomous driving decision-making method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more autonomous driving decision-making device embodiments provided below can refer to the limitations of the autonomous driving decision-making method above, and will not be repeated here.

[0164] In an exemplary embodiment, Fig. 9 As shown, an automatic driving decision-making device 900 is provided, including: a first acquisition module 901, a first prediction module 902 and a planning module 903, wherein:

[0165] A first acquisition module 901 is used to acquire environmental information of the environment where the target object is located and a plurality of first candidate paths of the target object;

[0166] The first prediction module 902 is used to determine a plurality of first predicted trajectories corresponding to each traffic participant in the current environment and a first importance weight corresponding to each first predicted trajectory according to the trajectory prediction model and the environmental information; the trajectory prediction model is trained by a decision cost function;

[0167] The planning module 903 is used to determine the decision cost corresponding to each first candidate path based on the first candidate path, the first predicted trajectory, the first importance weight and the decision cost function, and determine the target path among the first candidate paths according to the decision cost.

[0168] In one embodiment, the device further comprises:

[0169] The second acquisition module is used to acquire the sample data set and the trajectory label and path selection label corresponding to each sample data in the sample data set;

[0170] A second prediction module is used to perform prediction processing on each sample data according to the trajectory prediction model to be trained, and obtain a second predicted trajectory and a second importance weight corresponding to each second predicted trajectory;

[0171] a loss calculation module, configured to determine an accuracy prediction loss based on the trajectory label and the second predicted trajectory, and to determine a path planning loss based on the second importance weight, a decision cost function, and the path selection label;

[0172] The training module is used to update the model parameters of the trajectory prediction model to be trained through back propagation until the accuracy prediction loss and the path planning loss meet the preset loss threshold, thereby obtaining a trained trajectory prediction model.

[0173] In one of the embodiments, the loss calculation module is specifically used to construct a historical sampling space based on the sample data set; the historical sampling space includes a plurality of historical candidate paths determined based on the sample data;

[0174] Among the historical candidate paths, the historical candidate path with the smallest distance to the path selection label is determined as the expert trajectory;

[0175] Based on the expert trajectory and the decision cost function, the path planning loss is determined.

[0176] In one embodiment, the device further comprises:

[0177] The first screening module is used to obtain initial candidate paths, screen the initial candidate paths according to a preset dynamic constraint sub-model, and obtain preliminary screening candidate paths;

[0178] The second screening module is used to perform a secondary screening on the initially screened candidate paths according to a preset collision safety constraint sub-model to obtain a first candidate path.

[0179] In one embodiment, the decision cost function includes a decision safety cost function, a decision efficiency cost function and a decision comfort cost function; the decision cost includes a decision safety cost, a decision efficiency cost and a decision comfort cost;

[0180] The planning module 903 is specifically used to determine the decision safety cost based on the initial candidate path, the first predicted trajectory, the first importance weight and the decision safety cost function;

[0181] determining a decision efficiency cost based on the initial candidate paths, the destination coordinates, and the decision efficiency cost function;

[0182] The decision comfort cost is determined based on the initial candidate paths and the decision comfort cost function.

[0183] In one embodiment, the planning module 903 is specifically used to obtain a preset path starting point and a path end point;

[0184] Generate a global path based on the path start point and path end point;

[0185] A plurality of initial candidate paths of the target object are generated according to the preset lateral and longitudinal offset distances and the global path.

[0186] Each module in the above-mentioned automatic driving decision-making device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0187] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.10 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (Near Field Communication, NFC) or other technologies. When the computer program is executed by the processor, an automatic driving decision method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0188] Those skilled in the art will understand that Fig.10The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0189] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0190] Acquire environmental information of an environment where a target object is located and a plurality of first candidate paths of the target object;

[0191] Determining a plurality of first predicted trajectories corresponding to each traffic participant in the current environment and a first importance weight corresponding to each first predicted trajectory according to the trajectory prediction model and the environmental information; the trajectory prediction model is trained by a decision cost function;

[0192] Based on the first candidate paths, the first predicted trajectory, the first importance weight and the decision cost function, the decision cost corresponding to each first candidate path is determined, and the target path is determined from the first candidate paths according to the decision cost.

[0193] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0194] Obtain a sample data set and a trajectory label and a path selection label corresponding to each sample data in the sample data set;

[0195] Perform prediction processing on each sample data according to the trajectory prediction model to be trained to obtain a second predicted trajectory and a second importance weight corresponding to each second predicted trajectory;

[0196] determining an accuracy prediction loss based on the trajectory label and the second predicted trajectory, and determining a path planning loss based on the second importance weight, the decision cost function, and the path selection label;

[0197] The model parameters of the trajectory prediction model to be trained are updated through back propagation until the accuracy prediction loss and path planning loss meet the preset loss threshold, and the trained trajectory prediction model is obtained.

[0198] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0199] Constructing a historical sampling space according to the sample data set; the historical sampling space includes a plurality of historical candidate paths determined based on the sample data;

[0200] Among the historical candidate paths, the historical candidate path with the smallest distance to the path selection label is determined as the expert trajectory;

[0201] Based on the expert trajectory and the decision cost function, the path planning loss is determined.

[0202] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0203] Obtaining initial candidate paths, screening the initial candidate paths according to a preset dynamic constraint sub-model, and obtaining preliminary screening candidate paths;

[0204] The initially screened candidate paths are screened again according to the preset collision safety constraint sub-model to obtain the first candidate path.

[0205] In one embodiment, the decision cost function includes a decision safety cost function, a decision efficiency cost function and a decision comfort cost function; the decision cost includes a decision safety cost, a decision efficiency cost and a decision comfort cost; when the processor executes the computer program, the following steps are also implemented:

[0206] determining a decision safety cost based on the initial candidate path, the first predicted trajectory, the first importance weight, and the decision safety cost function;

[0207] determining a decision efficiency cost based on the initial candidate paths, the destination coordinates, and the decision efficiency cost function;

[0208] The decision comfort cost is determined based on the initial candidate paths and the decision comfort cost function.

[0209] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0210] Get the preset path starting point and path end point;

[0211] Generate a global path based on the path start point and path end point;

[0212] A plurality of initial candidate paths of the target object are generated according to the preset lateral and longitudinal offset distances and the global path.

[0213] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0214] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0215] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0216] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0217] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0218] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An automatic driving decision-making method, characterized in that: The method comprises: Acquire environmental information of an environment where a target object is located and a plurality of first candidate paths of the target object; Determine, according to the trajectory prediction model and the environmental information, a plurality of first predicted trajectories corresponding to each traffic participant in the current environment and a first importance weight corresponding to each of the first predicted trajectories; the trajectory prediction model is trained by a decision cost function; Based on the first candidate paths, the first predicted trajectory, the first importance weight, and the decision cost function, a decision cost corresponding to each of the first candidate paths is determined, and a target path is determined among the first candidate paths according to the decision cost.

2. The method according to claim 1, characterized in that Before acquiring the environment information of the environment in which the target object is located and the plurality of first candidate paths of the target object, the method further includes: Obtaining a sample data set and a trajectory label and a path selection label corresponding to each sample data in the sample data set; Performing prediction processing on each of the sample data according to the trajectory prediction model to be trained, to obtain a second predicted trajectory and a second importance weight corresponding to each of the second predicted trajectories; determining an accuracy prediction loss based on the trajectory label and the second predicted trajectory, and determining a path planning loss based on the second importance weight, the decision cost function, and the path selection label; The model parameters of the trajectory prediction model to be trained are updated through back propagation until the accuracy prediction loss and the path planning loss meet a preset loss threshold, thereby obtaining a trained trajectory prediction model.

3. The method according to claim 2, characterized in that The determining of the path planning loss based on the second importance weight, the decision cost function and the path selection label includes: Constructing a historical sampling space according to the sample data set; the historical sampling space includes a plurality of historical candidate paths determined based on the sample data; Among the historical candidate paths, determining the historical candidate path with the smallest distance to the path selection label as the expert trajectory; A path planning loss is determined based on the expert trajectory and the decision cost function.

4. The method according to claim 1, characterized in that: Before determining the decision cost corresponding to each of the first candidate paths based on the first candidate paths, the first predicted trajectory, the first importance weight, and the decision cost function, the method further includes: Acquire initial candidate paths, and screen the initial candidate paths according to a preset dynamic constraint sub-model to obtain preliminary screening candidate paths; The initially screened candidate paths are screened a second time according to a preset collision safety constraint sub-model to obtain a first candidate path.

5. The method according to claim 1 or 4, characterized in that: The decision cost function includes a decision safety cost function, a decision efficiency cost function and a decision comfort cost function; the decision cost includes a decision safety cost, a decision efficiency cost and a decision comfort cost; The determining, based on the first candidate paths, the first predicted trajectories, the first importance weights, and the decision cost function, a decision cost corresponding to each of the first candidate paths includes: Determine the decision safety cost based on the initial candidate path, the first predicted trajectory, the first importance weight, and the decision safety cost function; Determining the decision efficiency cost based on the initial candidate path, the destination coordinates and a decision efficiency cost function; The decision comfort cost is determined based on the initial candidate path and a decision comfort cost function.

6. The method according to claim 4, characterized in that The obtaining of the initial candidate path comprises: Get the preset path starting point and path end point; generating a global path based on the path starting point and the path end point; A plurality of initial candidate paths for the target object are generated according to preset lateral and longitudinal offset distances and the global path.

7. An automatic driving decision-making device, characterized in that: The device comprises: A first acquisition module, used to acquire environmental information of an environment where a target object is located and a plurality of first candidate paths of the target object; A first prediction module, used to determine a plurality of first predicted trajectories corresponding to each traffic participant in the current environment and a first importance weight corresponding to each of the first predicted trajectories according to a trajectory prediction model and the environmental information; the trajectory prediction model is trained by a decision cost function; A planning module is used to determine the decision cost corresponding to each of the first candidate paths based on the first candidate paths, the first predicted trajectory, the first importance weight and the decision cost function, and determine the target path among the first candidate paths according to the decision cost.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images