A controllable and explainable autonomous driving method and system

Abstract

A controllable and explainable autonomous driving method and system. The intelligent vehicle generates policies based on historical driving behavior and environmental feedback, using these policies to control decision-making. The system comprises a cognitive model, a decision model, and a value model. The cognitive model accepts environmental inputs to determine which policy to use. This model also infers policies based on decision outcomes or historical driving behavior. The decision model accepts environmental inputs and the policies output by the cognitive model, makes decisions, executes them, and learns from environmental feedback. The value model determines which decisions are appropriate for the current driving state, thereby assisting the decision model in learning. This system can thus self-generate cognitive driving policies and control decision-making through driving policies.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a controllable and explainable autonomous driving method and system. Background Art

[0002] Traditional autonomous driving systems typically rely on predefined rules and limited sensor data for environmental perception and driving decisions. This makes them limited when dealing with complex and dynamically changing driving environments. This is especially true in situations such as extreme weather, emergencies, or ambiguous traffic rules, where decision-making can be suboptimal. Furthermore, many current autonomous driving systems still face challenges in the controllability and explainability of their decision-making processes, as well as in generating optimized strategies, making them unable to fully meet the requirements of highly automated driving. Summary of the Invention

[0003] In order to overcome the shortcomings of the above-mentioned prior art, the purpose of the present invention is to provide a controllable and explainable autonomous driving method and system, so that artificial intelligence can self-generate cognitive strategies and be controllable in the decision-making process, further enable the decision-making of artificial intelligence to understand and adapt to the environment, and be subject to external management.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is:

[0005] The present invention provides a controllable and explainable autonomous driving method and system, comprising the following steps:

[0006] Step 1: Establish cognitive model, decision model and value model;

[0007] Step 2: During the operational phase, the cognitive model receives driving environment information and selects a strategy. The decision model uses the driving environment information and the strategy as input to make a decision. The driving environment information refers to information that can be used for decision-making in an autonomous driving scenario. The strategy is a collection of a series of driving operations for the vehicle. The decision refers to the decision on which driving operation to perform.

[0008] Step 3: By fixing the strategy selected by the cognitive model, the decision-making model is controlled to achieve controllable decision-making of the intelligent agent;

[0009] Step 4: During the self-learning training phase, the cognitive model receives driving environment information and selects a strategy. The decision model uses the driving environment information and the strategy as input to make a decision. After executing the corresponding driving operation based on the decision, the value model collects the driving results and receives the driving environment information as input to evaluate the quality of the corresponding driving operation.

[0010] Step 5: The decision model is optimized based on the evaluation results of the value model, the value model is optimized based on the gap between the environment and expectations after the driving operation is performed, and the cognitive model generates a strategy based on historical driving results;

[0011] Step 6: During the imitation learning training phase, appropriate driving data is collected, such as driving environment information, driving operation sequences, and driving results during excellent driving cases. The cognitive model receives the driving environment information during the driving process and selects a strategy. The decision model uses the driving environment information and the strategy as input to make decisions. The decision model is optimized based on whether the decision matches the collected driving operation sequence. The cognitive model generates a strategy based on the driving results.

[0012] In one embodiment, step 1 specifically includes the following steps:

[0013] Step 1.1: Establish the cognitive model using an artificial neural network and an embedding space containing a strategy representation vector, wherein the input of the cognitive model is driving environment information and the strategy representation vector is selected to form the output; the strategy representation vector is a vector of length d;

[0014] Step 1.2: Using an artificial neural network to establish the decision model, the input of the decision model is the driving environment information and its corresponding strategy representation vector, and the output is the driving operation to be performed;

[0015] Step 1.3: Use an artificial neural network to establish the value model, wherein the input of the value model is the driving environment information, and the output is an evaluation value of whether the driving operation to be performed in the current decision is suitable for the current driving environment.

[0016] In one embodiment, the size of the embedding space is n*d, where n represents the number of policy representation vectors contained and can be expanded with learning, and d is the length of the policy representation vector. All policy representation vectors are initially randomized; the driving environment information is input into the artificial neural network of the cognitive model, and a vector of length d is output; the similarity between the vector of length d and the policy representation vector in the embedding space is calculated, and a suitable policy vector in the embedding space is selected for output, or a combination of multiple policy representation vectors in the embedding space can be selected for output.

[0017] In one embodiment, step 2 specifically includes the following steps:

[0018] Step 2.1: Use an artificial neural network to establish feature extraction sub-models for both the cognitive model and the decision-making model. These two feature extraction sub-models can be the same feature extraction sub-model, that is, the two feature extraction sub-models can share weights;

[0019] Step 2.2: Input the driving environment information into the feature extraction sub-model, and the feature extraction sub-model outputs the corresponding environment representation vector;

[0020] Step 2.3: Input the corresponding environment representation vector into the cognitive model, and the cognitive model outputs the strategy representation vector;

[0021] Step 2.4: The decision model receives the corresponding environment representation vector and strategy representation vector, selects the optimal driving operation judged by the decision model as output, and executes it.

[0022] In one embodiment, step 3 specifically includes the following steps:

[0023] Step 3.1: During runtime, the decision is controlled. In this case, the cognitive model does not accept driving environment information as input, but directly selects a specific strategy representation vector in the embedding space as output. The specific strategy representation vector is selected based on the corresponding control effect after the strategy interpretation.

[0024] Step 3.2: The decision model receives the corresponding environment representation vector and strategy representation vector, selects the optimal driving operation judged by the decision model as output, and executes it.

[0025] In one embodiment, step 4 specifically includes the following steps:

[0026] Step 4.1: Based on step 2.1, use artificial neural network to build the feature extraction sub-model of the value model;

[0027] Step 4.2: Input the driving environment information into the feature extraction sub-model, and the feature extraction sub-model outputs the corresponding environment representation vector;

[0028] Step 4.3: Input the corresponding environment representation vector into the cognitive model, which then outputs the strategy representation vector. The decision model receives the corresponding environment representation vector and strategy representation vector, selects the optimal driving operation determined by the decision model as output, and executes it.

[0029] Step 4.4: The value model accepts the corresponding environment representation vector and outputs the gap between the environment and the expectation after the driving operation is performed.

[0030] In one embodiment, step 5 specifically includes the following steps:

[0031] Step 5.1: The decision model is optimized using gradient backpropagation based on the evaluation results of the value model as follows:

[0032] Step 5.1.1: Combine the decision model output of the selected optimal driving action described in step 4.3 and the gap described in step 4.4 into a gradient;

[0033] Step 5.1.2: Optimize the components of the decision model by backpropagating the gradients described in step 5.1.1.

[0034] Step 5.2: The value model is optimized using the error back propagation algorithm based on the difference between the environment and the expectation after the driving operation is performed. The process is as follows:

[0035] Step 5.2.1: Use the difference between the environment and the expectation after performing the driving operation as the loss function;

[0036] Step 5.2.2: Use the loss function described in step 5.2.1 to optimize the error back propagation algorithm;

[0037] Step 5.3: The cognitive model generates a strategy based on historical driving results. The process is as follows:

[0038] Step 5.3.1: The cognitive model receives and records the driving results;

[0039] Step 5.3.2: The cognitive model optimization objectives include two aspects: the first is to maximize the similarity between the output vector of the cognitive model's artificial neural network and the selected strategy representation vector; the second is to use the artificial neural network to construct a reconstruction sub-model. The reconstruction sub-model takes as input the driving maneuvers executed by historical decisions and their subsequent driving results, the driving environment information during execution, and the selected strategy representation vector. The output is the optimal driving maneuver, and the matching between the output driving maneuver and the executed driving maneuver is used as the loss function.

[0040] Step 5.3.3: Use the error backpropagation algorithm to update the artificial neural network and embedding space of the cognitive model.

[0041] In one embodiment, step 6 specifically includes the following steps:

[0042] Step 6.1: During the imitation learning training phase, collect appropriate driving data, such as driving environment information, driving operation sequences, and driving results during driving;

[0043] Step 6.2: The cognitive model receives driving environment information during driving and selects a strategy as described in step 2. The decision model uses the driving environment information and the strategy as input and makes a decision as described in step 2.

[0044] Step 6.3: The decision model is optimized as described in step 5 based on whether the decision and the collected driving operation sequence match as the error function;

[0045] Step 6.4: The cognitive model generates a strategy based on the driving results according to the method described in step 5.

[0046] The second aspect of the present invention provides a controllable intelligent agent decision system based on a self-generated cognitive strategy, the interpretable method of which is:

[0047] Step 7.1: Collect historical driving decision-making processes and determine the physical meaning or behavior pattern of the strategy represented by each decision representation vector in the embedding space;

[0048] Step 7.2: Explain the strategy chosen during driving.

[0049] The third invention of the present invention provides a controllable and explainable autonomous driving system, which includes a processor, which is used to execute a controllable and explainable autonomous driving method described in the present invention.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] 1. Controllable Decision-Making Process: This invention leverages the collaborative work of cognitive, decision-making, and value models to enable autonomous driving systems to control their decision-making processes according to predefined policies. By fixing the policy selected by the cognitive model, the output of the decision-making model can be effectively controlled, achieving controllable decision-making processes within the autonomous driving system. This provides greater flexibility and safety when addressing complex driving scenarios or specific needs.

[0052] 2. Self-learning and Imitation Learning Capabilities: This invention incorporates self-learning and imitation learning training mechanisms, enabling the system to continuously improve driving strategies and decision-making outcomes by continuously optimizing cognitive models, decision-making models, and value models. The self-learning phase uses feedback from the value model to evaluate driving results and optimize driving operations, while the imitation learning phase uses input from actual driving data to further enhance the system's driving strategies and improve the accuracy and adaptability of driving decisions.

[0053] 3. Decision Explainability: Traditional autonomous driving systems often lack transparency in their decision-making process, making it difficult to explain the rationale behind their choices. This invention, however, analyzes the physical meaning or behavioral patterns of policy representation vectors in the embedding space to explain decisions made during autonomous driving. This enhances the transparency and credibility of the system for users and regulators. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a schematic diagram of the system structure of the present invention.

[0055] Figure 2 It is a schematic diagram of the operation process of the present invention.

[0056] Figure 3 It is a schematic diagram of the self-learning implementation of the present invention.

[0057] Figure 4 It is a schematic diagram of the implementation of the strategy of the present invention.

[0058] Figure 5 It is a schematic diagram of the imitation learning implementation of the present invention. DETAILED DESCRIPTION

[0059] The embodiments of the present invention are described in detail below with reference to the accompanying drawings and examples.

[0060] To meet the requirements of controllability and explainability of the decision-making process, as well as the generation of optimized strategies, autonomous driving systems based on artificial neural networks can be considered. By incorporating cognitive, decision-making, and value models, not only can adaptive environmental perception and decision-making be achieved, but strategies can also be continuously optimized during self-learning, improving overall system performance. However, there is currently a lack of autonomous driving systems that organically integrate cognitive, decision-making, and value models and possess multi-stage training and optimization capabilities to cope with complex driving scenarios.

[0061] To this end, the present invention proposes an autonomous driving method and system based on artificial neural networks that coordinates cognition, decision-making, and value models to achieve controllable and explainable decision-making processes, and further optimize driving operations and strategies through a multi-stage training process, thereby improving the safety, stability, and adaptability of the system.

[0062] The autonomous driving method of the present invention can be specifically described as the following steps:

[0063] Step 1: Establish cognitive model, decision model and value model.

[0064] like Figure 1 As shown, this step can be specifically described as the following process:

[0065] Step 1.1: Build the cognitive model using an artificial neural network and an embedding space containing a policy representation vector. In this example, the artificial neural network is a long short-term memory recurrent neural network (LSTM). The input to the cognitive model is driving environment information, which in this example includes but is not limited to onboard camera data and onboard radar data, which can be acquired while the vehicle is in motion. The policy representation vector is selected as the output. The policy representation vector is a vector of length d.

[0066] The embedding space can be specifically described as follows: its size is n*d, where n represents the number of policy representation vectors contained and can be expanded with learning, and d is the length of the policy representation vector. Initially, all policy representation vectors are randomized. The driving environment information is input into the artificial neural network of the cognitive model, and a vector of length d is output. The similarity between the vector of length d and the policy representation vector in the embedding space is calculated. In this example, multiple policy representation vectors in the embedding space are combined and output.

[0067] In this example, the top k strategy representation vectors with the greatest similarity are selected. The combination method is to concatenate these strategy representation vectors to obtain a long vector.

[0068] Step 1.2: Use an artificial neural network to establish the decision model. In this example, a fully connected network is selected. The input of the decision model is the driving environment information and its corresponding strategy representation vector (i.e., the output of the cognitive model), and the output is the driving operation that needs to be performed.

[0069] Step 1.3: Use an artificial neural network to establish the value model. In this example, a fully connected network is selected. The input of the value model is the driving environment information, and the output is an evaluation value of whether the driving operation required to be performed in the current decision is suitable for the current driving environment. The larger the evaluation value, the more suitable the current driving operation.

[0070] Step 2: If Figure 2 As shown, during the operation phase, the cognitive model receives driving environment information and selects a strategy, and the decision model uses the driving environment information and the strategy as input to make a decision; the decision refers to deciding which driving operation to perform, which in this example includes: whether there is information about the steering direction of the steering wheel and the throttle within a unit time of 0.1 seconds.

[0071] This step can be specifically described as the following process:

[0072] Step 2.1: Use artificial neural networks to establish feature extraction sub-models for both the cognitive model and the decision model. In this example, a fully connected artificial neural network is selected, and the two feature extraction sub-models share weights.

[0073] Step 2.2: Input the driving environment information into the feature extraction sub-models of the cognitive model and the decision model. Each feature extraction sub-model outputs its corresponding environment representation vector.

[0074] Step 2.3: Input the corresponding environment representation vector into the cognitive model, which performs similarity calculation and outputs the strategy representation vector.

[0075] Step 2.4: The decision model receives the corresponding environment representation vector and strategy representation vector, selects the optimal driving operation judged by the decision model as output, and executes it, that is, the autonomous driving car.

[0076] Step 3: By fixing the strategy selected by the cognitive model, the decision of the decision model is controlled to achieve controllable decision-making of the intelligent agent.

[0077] This step can be specifically described as the following process:

[0078] Step 3.1: During runtime, decisions can be controlled. The cognitive model does not accept driving environment information as input, but directly selects a specific strategy representation vector in the embedding space as its output. This specific selection can be made based on the strategy interpretation in Step 7 and the corresponding control effect. For example, some strategy representation vectors represent low-speed, slow-paced driving strategies, and these strategies can be selected for autonomous driving control.

[0079] Step 3.2: The decision model receives the corresponding environment representation vector and strategy representation vector, selects the optimal driving operation judged by the decision model as output, and executes it, that is, the autonomous driving car.

[0080] Step 4: If Figure 3 As shown, during the self-learning training phase, the cognitive model receives driving environment information and selects a strategy, and the decision model uses the driving environment information and the strategy as input to make a decision. After executing the corresponding driving operation according to the decision, the value model collects the driving results and receives the driving environment information as input to evaluate the quality of this driving operation.

[0081] This step can be specifically described as the following process:

[0082] Step 4.1: Based on step 2.1, establish a feature extraction sub-model of the value model. In this example, a fully connected artificial neural network is selected.

[0083] Step 4.2: Input the driving environment information into each feature extraction sub-model, and each feature extraction sub-model outputs its corresponding environment representation vector.

[0084] Step 4.3: Input the corresponding environment representation vector into the cognitive model, which then outputs a strategy representation vector. The decision model receives the corresponding environment representation vector and the strategy representation vector and selects the optimal driving action determined by the decision model as its output. In this example, the optimal approach is the driving action with the highest decision model output value, and executes it.

[0085] Step 4.4: The value model receives the corresponding environment representation vector and outputs the gap between the environment after the driving operation and the expectation. In this example, the value model receives the current environment representation vector and the environment representation vector after the driving operation, outputs the value / expectation value of the current environment and the environment after the operation, and then receives the reward feedback from the driving environment after the driving operation, measures the gap between the expectation and the reward, and uses this gap, that is, the evaluation result of the value model, to optimize the model in the subsequent steps.

[0086] Step 5: The decision model is optimized based on the evaluation results of the value model. The cognitive model generates strategies based on historical driving results. The value model is optimized based on the gap between the environment and expectations after the driving operation is performed.

[0087] This step can be specifically described as the following process:

[0088] Step 5.1: The decision model is optimized using gradient backpropagation based on the evaluation results of the value model.

[0089] Step 5.1.1: Combine the decision model output of the selected optimal driving action described in step 4.3 and the gap described in step 4.4 into a gradient.

[0090] Step 5.1.2: Pass the gradient described in step 5.1.1 back to the feature extraction sub-model and other artificial neural network components of the decision model for gradient descent optimization.

[0091] Step 5.2: The value model is optimized using an error back propagation algorithm based on the difference between the environment and the expectation after the driving operation is performed.

[0092] Step 5.2.1: Use the difference between the environment and the desired state after performing the driving maneuver as the loss function.

[0093] Step 5.2.2: Use the loss function described in step 5.2.1 to optimize the error back propagation algorithm.

[0094] Step 5.3: The cognitive model generates a strategy based on historical driving results.

[0095] Step 5.3.1: The cognitive model receives and records the driving results.

[0096] Step 5.3.2: If Figure 4 As shown in , the optimization objectives of the cognitive model are divided into two: the first is to maximize the similarity between the output vector of the artificial neural network of the cognitive model and the selected strategy representation vector. In this example, the mean square error loss is used to measure the similarity, and the strategy representation vector is selected based on the similarity, as shown in Figure 4As shown in the lower part, the similarity values ​​between the d-dimensional vector output by the artificial neural network and the representation vectors of each strategy in the embedding space are calculated, the largest k are selected, and after selection, gradient backpropagation optimization is performed with the goal of maximizing these similarity values ​​during optimization; the second is to use the artificial neural network to build a reconstruction sub-model, such as Figure 4 As shown in the upper part, the reconstruction sub-model takes the driving operations executed by historical decisions and their subsequent driving results, the driving environment information during execution, and the selected strategy representation vector as input. The output is the optimal driving operation. The output driving operation and the actual driving operation are matched as the loss function. In this example, the cross-entropy function loss is used for matching, and this is used as the loss index for gradient backpropagation optimization.

[0097] Step 5.3.3: Use the error backpropagation algorithm to update the artificial neural network and embedding space of the cognitive model.

[0098] Step 6: Figure 5 As shown, during the imitation learning training phase, appropriate driving data is collected, such as driving environment information, driving operation sequences, and driving results. The cognitive model receives the driving environment information and selects a strategy. The decision model uses the driving environment information and the strategy as input to make decisions. The decision model optimizes based on whether the decision matches the collected driving operation sequence, and the cognitive model generates a strategy based on the driving results.

[0099] This step can be specifically described as the following process:

[0100] Step 6.1: During the imitation learning training phase, collect appropriate driving data, such as driving environment information during driving, driving operation sequences (such as Figure 5 real operations in the game) and driving results, etc.

[0101] Step 6.2: The cognitive model receives the driving environment information during the driving process and then selects a strategy as described in steps 2.1-2.3. The decision model uses the driving environment information and the strategy as input and makes a decision as described in step 2.4.

[0102] Step 6.3: The decision model uses the error function based on whether the decision matches the driving operation sequence collected in step 6.1. In this example, the match is measured using the cross entropy function and optimized as described in step 5.1.

[0103] Step 6.4: The cognitive model generates a strategy based on the driving results according to the method described in step 5.3.

[0104] The steps explained in the present invention can be specifically described as the following process:

[0105] Step 7.1: Collect historical driving decision-making processes and determine the physical meaning or behavior pattern of the strategy represented by each decision representation vector in the embedding space.

[0106] Step 7.2: Explain the strategy selected during driving. This method allows the present invention to develop a controllable intelligent agent decision-making system based on self-generated strategies. The system primarily comprises a decision-making model and a cognitive model. The cognitive model is used to select the appropriate strategy for the current environment based on received environmental information. The decision-making model is used to make decisions based on the environment and strategy, execute the decisions, and learn from environmental feedback. The cognitive model then summarizes and generates strategies based on environmental feedback. This system can thus self-generate cognitive strategies and control decisions through these strategies. Compared to other artificial intelligence decision-making methods, the present invention allows for controllable decision-making processes through control of the cognitive model.

[0107] In the CARLA simulated autonomous driving task, the average deviation between the actual running path and the ideal planned path of the present invention is about 5.7 cm, which is better than the 9.6 cm of the SAC and 13.4 cm of the PPO reinforcement learning algorithms of the same type.

[0108] The above-mentioned CARLA provides the concept of waypoints, and all vehicle information can be obtained through waypoints. Waypoints can be understood as discrete points distributed along the centerline of the lane. The minimum distance between these discrete points in CARLA is 2 cm. The process of a vehicle driving on the road is the process of passing through one waypoint after another. The ideal planned path is the set of optimal driving path points from point A to point B under the current traffic scenario. The actual operation path is the set of actual driving path points. By comparing the deviation values ​​of the actual operation path and the path points in the ideal planned path at the same time, the average value of the overall deviation is calculated.

[0109] The present invention statistically analyzes the strategies in the embedded space to summarize the different driving environment information and driving decisions corresponding to different strategies. For example, in a driving scenario where the right auxiliary road merges into the main road and then exits from the right auxiliary road, most of the strategies used show a clear tendency to turn right in the statistical analysis. In the straight driving scenario, the strategies used basically maintain straight driving in the statistical analysis. Therefore, the system of the present invention that implements the above-mentioned automatic driving method optimizes and controls driving decisions during actual driving through the collaborative work of cognitive models, decision models and value models, and can autonomously adapt to complex and changing driving environments. At the same time, it optimizes driving strategies and operations during the training phase of self-learning and imitation learning, thereby improving the robustness and decision transparency of the automatic driving system.

[0110] An embodiment of the present invention further provides a computer storage medium having a computer program stored thereon. When the computer program is executed by a computer, the computer is enabled to perform the method of the above-described method embodiment. Alternatively, an embodiment of the present invention further provides a computer program product containing instructions. When the computer is executed by the instructions, the computer is enabled to perform the method of the above-described method embodiment.

[0111] When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium, an optical medium, or a semiconductor medium, etc.

[0112] The method or system of the present invention can be implemented in an electronic device, either executing the method of the present invention in the electronic device or embedding the system obtained through training of the present invention into the electronic device. Furthermore, the electronic device can include a collection unit and a final operation unit. The hand information collected by the collection unit can be directly or after necessary pre-processing fed into the system of the present invention, and then processed by the operation unit.

Claims

1. A controllable and explainable autonomous driving method, characterized in that: The steps include: Step 1: Establish cognitive model, decision model and value model; Step 2: During the operational phase, the cognitive model receives driving environment information and selects a strategy. The decision model uses the driving environment information and the strategy as input to make a decision. The driving environment information refers to information that can be used for decision-making in an autonomous driving scenario. The strategy is a collection of a series of driving operations for the vehicle. The decision refers to the decision on which driving operation to perform. Step 3: By fixing the strategy selected by the cognitive model, the decision-making model is controlled to achieve controllable decision-making of the intelligent agent; Step 4: During the self-learning training phase, the cognitive model receives driving environment information and selects a strategy. The decision model uses the driving environment information and the strategy as input to make a decision. After executing the corresponding driving operation based on the decision, the value model collects the driving results and receives the driving environment information as input to evaluate the quality of the corresponding driving operation. Step 5: The decision model is optimized based on the evaluation results of the value model, the value model is optimized based on the gap between the environment and expectations after the driving operation is performed, and the cognitive model generates a strategy based on historical driving results; Step 6: During the imitation learning training phase, the cognitive model receives driving environment information during driving and selects a strategy. The decision model uses the driving environment information and the strategy as input to make a decision. The decision model is optimized based on whether the decision matches the collected driving operation sequence. The cognitive model generates a strategy based on the driving results.

2. The controllable and explainable autonomous driving method according to claim 1, characterized in that: The step 1 specifically includes the following steps: Step 1.1: Establish the cognitive model using an artificial neural network and an embedding space containing a strategy representation vector, wherein the input of the cognitive model is driving environment information and the strategy representation vector is selected to form the output; the strategy representation vector is a vector of length d; Step 1.2: Using an artificial neural network to establish the decision model, the input of the decision model is the driving environment information and its corresponding strategy representation vector, and the output is the driving operation to be performed; Step 1.3: Use an artificial neural network to establish the value model, wherein the input of the value model is the driving environment information, and the output is an evaluation value of whether the driving operation to be performed in the current decision is suitable for the current driving environment.

3. The controllable and explainable autonomous driving method according to claim 2, characterized in that: The size of the embedding space is n*d, where n represents the number of policy representation vectors contained and can be expanded with learning, and d is the length of the policy representation vector. All policy representation vectors are initially randomized; driving environment information is input into the artificial neural network of the cognitive model, and a vector of length d is output; the similarity between the vector of length d and the policy representation vector in the embedding space is calculated, and an appropriate policy vector in the embedding space is selected for output, or a combination of multiple policy representation vectors in the embedding space is selected for output.

4. The controllable and explainable autonomous driving method according to claim 1, characterized in that: The step 2 specifically includes the following steps: Step 2.1: Use artificial neural networks to build feature extraction sub-models of the cognitive model and decision-making model; Step 2.2: Input the driving environment information into the feature extraction sub-model, which outputs the corresponding environment representation vector; Step 2.3: Input the corresponding environment representation vector into the cognitive model, and the cognitive model outputs the strategy representation vector; Step 2.4: The decision model receives the corresponding environment representation vector and strategy representation vector, determines the optimal driving operation as output, and executes it.

5. The controllable and explainable autonomous driving method according to claim 1, characterized in that: The step 3 specifically includes the following steps: Step 3.1: During runtime, the decision is controlled. In this case, the cognitive model does not accept driving environment information as input, but directly selects a specific strategy representation vector in the embedding space as output. The specific strategy representation vector is selected based on the corresponding control effect after the strategy interpretation. Step 3.2: The decision model receives the corresponding environment representation vector and strategy representation vector, determines the optimal driving operation as output, and executes it.

6. The controllable and explainable autonomous driving method according to claim 1, characterized in that: The step 4 specifically includes the following steps: Step 4.1: Use artificial neural network to build the feature extraction sub-model of the value model; Step 4.2: Input the driving environment information into the feature extraction sub-model, which outputs the corresponding environment representation vector; Step 4.3: Input the corresponding environment representation vector into the cognitive model, which outputs the strategy representation vector. The decision model receives the corresponding environment representation vector and strategy representation vector, determines the optimal driving operation as output, and executes it. Step 4.4: The value model receives the corresponding environment representation vector and outputs the gap between the environment and the expectation after the driving operation is performed.

7. The controllable and explainable autonomous driving method according to claim 6, characterized in that: The step 5 specifically includes the following steps: Step 5.1: The decision model is optimized using gradient backpropagation based on the evaluation results of the value model. The process is as follows: Step 5.1.1: Combining the optimal driving operation and the gap into a gradient; Step 5.1.2: Pass the gradient back to each component of the decision model for optimization; Step 5.2: The value model is optimized using the error back propagation algorithm based on the difference between the environment and the expectation after the driving operation is performed. The process is as follows: Step 5.2.1: Use the difference between the environment and the expectation after performing the driving operation as the loss function; Step 5.2.2: Optimize the error back propagation algorithm using the loss function; Step 5.3: The cognitive model generates a strategy based on historical driving results. The process is as follows: Step 5.3.1: The cognitive model receives and records the driving results; Step 5.3.2: The cognitive model optimization objectives include two aspects: the first is to maximize the similarity between the output vector of the cognitive model's artificial neural network and the selected strategy representation vector; the second is to use the artificial neural network to construct a reconstruction sub-model. This reconstruction sub-model takes the driving maneuvers executed by historical decisions and their subsequent driving results, the driving environment information during execution, and the selected strategy representation vector as inputs, and outputs the optimal driving maneuver. The matching between the output driving maneuver and the executed driving maneuver is used as the loss function. Step 5.3.3: Use the error backpropagation algorithm to update the artificial neural network and embedding space of the cognitive model.

8. The controllable and explainable autonomous driving method according to claim 1, characterized in that: In step 6, the cognitive model uses the driving environment information during driving to perform strategy selection as in step 2, and the decision model uses the driving environment information and the strategy to perform decision making as in step 2; the decision model uses whether the decision and the collected driving operation sequence match as an error function to perform optimization as in step 5; The cognitive model performs strategy induction generation as in step 5.

9. A controllable and explainable autonomous driving method according to any one of claims 1 to 8, characterized in that: Explain the decision by following these steps to demonstrate explainability: Step 7.1: Collect historical driving decision-making processes and determine the physical meaning or behavior pattern of the strategy represented by each decision representation vector in the embedding space; Step 7.2: Explain the strategy chosen during driving.

10. A controllable and explainable autonomous driving system, comprising a processor, wherein the processor is used to execute a controllable and explainable autonomous driving method as described in any one of claims 1 to 9.

Images