Automatic driving dynamic path planning method and system and computer equipment

Abstract

The invention relates to an automatic driving dynamic path planning method and system, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: collecting real-time path planning information; transmitting the real-time path planning information to a path planning model, wherein the path planning model outputs an optimal path analysis result; generating a specific path planning scheme based on the optimal path analysis result, and transmitting the specific path planning scheme to an execution mechanism of the automatic driving system; and the execution mechanism is used for controlling the vehicle to run according to the specific path planning scheme. By adopting the method, automatic driving path planning can be realized by means of a big data model.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, computer device, computer-readable storage medium, and computer program product for dynamic path planning of autonomous driving. Background Technology

[0002] With the development of autonomous driving technology, path planning has become one of the key technologies to ensure the safe and efficient driving of vehicles.

[0003] Traditional path planning methods, typically based on static maps and preset rules, struggle to adapt to complex, dynamic traffic environments. While existing autonomous driving path planning methods can achieve dynamic path planning to some extent, they still fall short in handling real-time traffic information and road condition changes. For example, they cannot obtain the latest traffic data in a timely manner, leading to inaccurate path planning; and although they can acquire real-time data, the processing speed is slow, failing to meet the real-time requirements of autonomous driving.

[0004] With the rapid development of artificial intelligence technology, the combination of intelligent agents built on large language models (LLMs) and autonomous driving can leverage the integration of large-scale deep learning models to possess powerful information processing and decision-making capabilities. This enables autonomous vehicles to analyze complex traffic data, weather conditions, and vehicle status in real time, providing more accurate real-time path planning solutions. Therefore, there is an urgent need for a dynamic path planning method based on large language model (LLM) intelligent agents to analyze traffic data, weather conditions, and vehicle status in real time and optimize path selection. Summary of the Invention

[0005] Therefore, it is necessary to provide an autonomous driving dynamic path planning method, device, computer equipment, computer-readable storage medium, and computer program product to address the above-mentioned technical problems.

[0006] Firstly, this application provides a dynamic path planning method for autonomous driving, including:

[0007] Collect real-time path planning information;

[0008] Real-time route planning information is transmitted to the route planning model, and the route planning model outputs the optimal route analysis results.

[0009] Based on the optimal path analysis results, a specific path planning scheme is generated and transmitted to the actuator of the autonomous driving system; the actuator is used to control the vehicle to drive according to the specific path planning scheme.

[0010] In one embodiment, the route planning information includes real-time traffic data, real-time weather data, and real-time vehicle status information; collecting real-time route planning information includes:

[0011] It connects to a real-time traffic information system and collects real-time traffic data through preset communication technologies;

[0012] It connects to the real-time meteorological information system and obtains information from the meteorological information sensors on the vehicle to collect real-time weather data.

[0013] It connects to the integrated vehicle management system and obtains information from the vehicle status sensors to collect real-time vehicle status information.

[0014] In one embodiment, real-time route planning information is transmitted to a route planning model, which outputs the optimal route analysis result, including:

[0015] Real-time route planning information is transmitted to a route planning model. The route planning model extracts features from the input real-time route planning information and performs decision analysis based on the features to obtain the optimal route analysis result.

[0016] In one embodiment, based on the optimal path analysis results, a specific path planning scheme is generated, including:

[0017] Based on the optimal path analysis results and combined with real-time path planning information, a specific path planning scheme is generated with reference to preset standards.

[0018] In one embodiment, the method further includes:

[0019] Based on real-time path planning information, confirm whether any abnormal situations have occurred;

[0020] If an abnormal situation occurs, the process of transmitting real-time route planning information to the route planning model and subsequent steps will be re-executed.

[0021] If no abnormalities occur, feedback information and driving data are collected and transmitted to the path planning model to obtain the trained path planning model.

[0022] In one embodiment, feedback information and driving data are transmitted to the route planning model to obtain a trained route planning model, including:

[0023] The feedback information and driving data are transmitted to the path planning model, and the feedback information and driving data are used as training samples.

[0024] Based on training samples, the parameters of the path planning model are optimized by a preset algorithm, and the path planning model is obtained by simulating path planning tasks in different scenarios using a reinforcement learning mechanism.

[0025] Secondly, this application also provides an autonomous driving dynamic path planning system, comprising:

[0026] The data acquisition module is used to collect real-time route planning information; it transmits the real-time route planning information to the route planning model, and the route planning model outputs the optimal route analysis results.

[0027] The path planning module is used to generate a specific path planning scheme based on the optimal path analysis results and real-time path planning information, and transmit the specific path planning scheme to the actuator of the autonomous driving system; the actuator is used to control the vehicle to drive according to the specific path planning scheme.

[0028] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0029] Collect real-time path planning information;

[0030] Real-time route planning information is transmitted to the route planning model, and the route planning model outputs the optimal route analysis results.

[0031] Based on the optimal path analysis results, a specific path planning scheme is generated and transmitted to the actuator of the autonomous driving system; the actuator is used to control the vehicle to drive according to the specific path planning scheme.

[0032] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0033] Collect real-time path planning information;

[0034] Real-time route planning information is transmitted to the route planning model, and the route planning model outputs the optimal route analysis results.

[0035] Based on the optimal path analysis results, a specific path planning scheme is generated and transmitted to the actuator of the autonomous driving system; the actuator is used to control the vehicle to drive according to the specific path planning scheme.

[0036] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0037] Collect real-time path planning information;

[0038] Real-time route planning information is transmitted to the route planning model, and the route planning model outputs the optimal route analysis results.

[0039] Based on the optimal path analysis results, a specific path planning scheme is generated and transmitted to the actuator of the autonomous driving system; the actuator is used to control the vehicle to drive according to the specific path planning scheme.

[0040] The aforementioned autonomous driving dynamic path planning method, system, computer equipment, computer-readable storage medium, and computer program product collect real-time path planning information; transmit the real-time path planning information to a path planning model, which outputs the optimal path analysis result; based on the optimal path analysis result, generate a specific path planning scheme; transmit the specific path planning scheme to the actuator of the autonomous driving system; and the actuator controls the vehicle to drive according to the specific path planning scheme. By collecting real-time and multi-source path planning information, including traffic, weather, and vehicle status data, and utilizing the path planning model, the autonomous driving system finally achieves automatic route planning, ensuring that autonomous vehicles can make optimal path selections in various complex scenarios, significantly improving driving safety and efficiency.

[0041] By collecting multi-source data in real time and dynamically adjusting the path planning scheme, the system effectively solves the problem of unreasonable path selection caused by information lag in traditional methods. The system can make comprehensive decisions based on real-time traffic conditions, weather changes, and vehicle status, significantly improving the adaptability and driving safety of autonomous vehicles in complex environments. Simultaneously, by continuously optimizing the path planning model through a reinforcement learning mechanism, the system possesses the ability to learn autonomously and iteratively upgrade, further enhancing the practicality and forward-looking nature of the technical solution. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a diagram illustrating the application environment of an autonomous driving dynamic path planning method in one embodiment.

[0044] Figure 2 This is a flowchart illustrating an autonomous driving dynamic path planning method in one embodiment;

[0045] Figure 3 This is a flowchart illustrating the dynamic path planning method for autonomous driving in another embodiment;

[0046] Figure 4 This is a flowchart illustrating the structure of an autonomous driving dynamic path planning system in one embodiment.

[0047] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0049] The autonomous driving dynamic path planning method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on another network server.

[0050] Server 104 collects real-time path planning information from terminal 102; transmits the real-time path planning information from terminal 102 to the path planning model loaded on server 104, and uses the path planning model to output the optimal path analysis result; server 104 then generates a specific path planning scheme based on the optimal path analysis result; server 104 transmits the specific path planning scheme to the actuator of the autonomous driving system in terminal 102; the actuator is used to control the vehicle to drive according to the specific path planning scheme.

[0051] Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection equipment. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0052] In one exemplary embodiment, such as Figure 2 As shown, an autonomous driving dynamic path planning method is provided, which is applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps 202 to 206. Wherein:

[0053] Step 202: Collect real-time path planning information.

[0054] Real-time route planning information refers to all dynamic or static data that can influence route decisions, collected in real time by onboard sensors, external communication systems, and other means during vehicle operation.

[0055] Optionally, an external communication system interface or on-board sensors can be used to collect real-time path planning information.

[0056] Step 204: Transmit the real-time route planning information to the route planning model, and the route planning model outputs the optimal route analysis results.

[0057] The path planning model incorporates a Large Language Model (LLM) as its core inference engine. The optimal path analysis result is a set of one or more instructions or data that can be understood and used by a computer, output by the path planning model based on real-time path planning information after calculation and decision-making. This includes information such as path selection, estimated arrival time, and estimated energy consumption. The path planning model consists of an input layer, hidden layers, and an output layer. The input layer receives real-time path planning information, including but not limited to traffic data, weather data, and vehicle status data. The hidden layer comprises a multi-layered neural network structure, with each layer containing multiple neurons, used for feature extraction and decision analysis of the data received from the input layer. The output layer outputs the optimal path planning result, including information such as path selection, estimated arrival time, and estimated energy consumption.

[0058] For example, real-time path planning information is transmitted to a path planning model. The input layer of the path planning model receives the real-time path planning information, and after feature extraction and decision analysis by the input layer, the output layer outputs the optimal path analysis result.

[0059] Step 206: Based on the optimal path analysis results, generate a specific path planning scheme; transmit the specific path planning scheme to the actuator of the autonomous driving system; the actuator is used to control the vehicle to drive according to the specific path planning scheme.

[0060] The actuators of an autonomous driving system include steering, braking, and acceleration systems, which control the vehicle to travel according to a specific path planning scheme. The specific path planning scheme is a movement plan that the actuators of the autonomous driving system can directly execute, including the driving route, speed control, and obstacle avoidance strategies.

[0061] For example, based on the optimal path analysis results output by the path planning model, which include information such as path selection, estimated arrival time, and estimated energy consumption, and combined with real-time path planning information, a specific path planning scheme, including information such as driving route, vehicle speed control, and obstacle avoidance strategy, is dynamically generated; the specific path planning scheme is transmitted to the actuator of the autonomous driving system; the actuator is used to control the vehicle to drive according to the specific path planning scheme.

[0062] In the aforementioned dynamic path planning method for autonomous driving, real-time path planning information is collected; this information is then transmitted to a path planning model, which outputs the optimal path analysis result; based on the optimal path analysis result, a specific path planning scheme is generated and transmitted to the actuator of the autonomous driving system; the actuator controls the vehicle to travel according to the specific path planning scheme. By collecting real-time and multi-source path planning information, including traffic, weather, and vehicle status data, and utilizing the path planning model, the autonomous driving system finally achieves automatic route planning, ensuring that autonomous vehicles can make optimal path selections in various complex scenarios, significantly improving driving safety and efficiency.

[0063] In an exemplary embodiment, the route planning information includes real-time traffic data, real-time weather data, and real-time vehicle status information. Collecting real-time route planning information includes: accessing a real-time traffic information system and collecting real-time traffic data through a preset communication technology; accessing a real-time meteorological information system and obtaining information from meteorological sensors on the vehicle to collect real-time weather data; and accessing an integrated vehicle management system and obtaining information from vehicle status sensors on the vehicle to collect real-time vehicle status information.

[0064] The real-time traffic data includes road congestion index, average vehicle speed, traffic accidents, speed, location and direction of travel of nearby vehicles; the real-time weather data includes weather forecast, real-time weather data and weather conditions of the driving environment; and the real-time vehicle status information includes fuel level, battery level, tire pressure, braking system, vehicle location and status monitoring.

[0065] Optionally, by accessing the real-time traffic information system of the city traffic management center, information such as road congestion index, average vehicle speed, and traffic accidents can be collected; at the same time, by using vehicle-to-vehicle communication technology, data such as the speed, location, and direction of travel of nearby vehicles can be collected.

[0066] Optionally, the vehicle can collaborate with meteorological bureaus or other authoritative meteorological service agencies to collect accurate weather forecasts and real-time weather data via API interfaces; at the same time, it can acquire real-time weather conditions information of the driving environment by installing sensors such as temperature, humidity, and rainfall on the vehicle.

[0067] Optionally, by integrating a vehicle management system, real-time status information such as vehicle fuel level, battery level, tire pressure, and braking system can be collected; at the same time, multi-sensor fusion technology can be used to combine data from sensors such as GPS, inertial measurement unit (IMU), and lidar (LiDAR) to collect vehicle positioning information and status monitoring information.

[0068] In this embodiment, by collecting real-time path planning information through multiple channels and dimensions, rich and accurate data support can be provided for subsequent path planning models, ensuring the comprehensiveness and accuracy of path planning.

[0069] In one embodiment, real-time route planning information is transmitted to a route planning model, and the route planning model outputs the optimal route analysis result, including: transmitting real-time route planning information to a route planning model, the route planning model extracting features from the input real-time route planning information, and performing decision analysis based on the features to obtain the optimal route analysis result.

[0070] For example, real-time path planning information is transmitted to the input layer of the path planning model. Convolutional layers and fully connected layers are used in the hidden layer of the path planning model to extract key features from the input real-time path planning information. Based on the key features, structures such as recurrent neural networks (RNN) or long short-term memory networks (LSTM) are used to analyze the real-time path planning information to perform decision analysis and obtain the optimal path analysis result.

[0071] Optionally, the path planning model can correlate the current real-time path planning information with previously stored historical data to extract useful historical data. By fusing real-time path planning information with previously stored historical data, the path planning model can predict future environmental trends and calculate the optimal path analysis result accordingly. Simultaneously, the path planning model continuously optimizes its memory units using newly generated data, achieving self-evolution.

[0072] In this embodiment, the path planning model utilizes advanced deep learning algorithms to deeply mine and analyze the collected real-time path planning information. It not only considers the current traffic, weather, and vehicle status, but also predicts possible future trends by learning from historical data. This enables the output of more accurate and forward-looking optimal path analysis results, greatly improving the intelligence level of path planning and providing strong support for the safe and efficient driving of autonomous vehicles.

[0073] In one embodiment, generating a specific path planning scheme based on the optimal path analysis results includes: generating a specific path planning scheme based on the optimal path analysis results, combined with real-time path planning information, and referring to preset standards.

[0074] For example, based on the optimal path analysis results, combined with real-time path planning information, and taking into account the degree of road congestion, the impact of weather conditions on driving safety, and the vehicle's remaining battery or fuel, a relatively smooth path is selected that is more suitable for the current weather conditions and will not break down midway due to insufficient energy, thereby generating a specific path planning scheme.

[0075] In this embodiment, by closely integrating the optimal path analysis results with real-time traffic data and vehicle status information, the generated specific path planning scheme not only considers the current road conditions and vehicle performance, but can also be dynamically adjusted according to real-time changes.

[0076] In one embodiment, the method further includes: based on real-time route planning information, confirming whether an abnormal situation has occurred; if an abnormal situation has occurred, re-executing the steps of transmitting real-time route planning information to the route planning model and subsequent steps; if no abnormal situation has occurred, collecting feedback information and driving data, transmitting the feedback information and driving data to the route planning model, and obtaining the trained route planning model.

[0077] Abnormal situations include traffic accidents ahead or temporary road closures.

[0078] For example, based on real-time path planning information, it is confirmed whether any abnormal situations have occurred, such as traffic accidents ahead or temporary road closures. If an abnormal situation occurs, the current path planning scheme executed by the actuator is canceled, and the real-time path planning information is re-executed. The path planning model then outputs the adjusted optimal path analysis result. Based on the adjusted optimal path analysis result, an adjusted specific path planning scheme is generated. The adjusted specific path planning scheme is then transmitted to the actuator of the autonomous driving system. The actuator controls the vehicle to drive according to the adjusted specific path planning scheme. If no abnormal situation occurs, feedback information and driving data are collected and transmitted to the path planning model to obtain the trained path planning model.

[0079] In this embodiment, by monitoring abnormal situations in the path planning process in real time, such as sudden traffic accidents, sudden changes in severe weather, or sudden vehicle malfunctions, a rapid response is required to replan the route to ensure driving safety. This can effectively avoid path planning failures caused by abnormal situations, improve the robustness and adaptability of the autonomous driving system, and provide more intelligent and safer driving protection for autonomous vehicles.

[0080] In one embodiment, the feedback information and driving data are transmitted to the path planning model to obtain the trained path planning model, including: transmitting the feedback information and driving data to the path planning model and using the feedback information and driving data as training samples; optimizing the parameters of the path planning model based on the training samples using a preset algorithm, and using the reinforcement learning mechanism of the path planning model to simulate path planning tasks in different scenarios to obtain the trained path planning model.

[0081] The reinforcement learning mechanism defines a reward function to encourage the path planning model to choose a safe and efficient path; and it iteratively optimizes the behavior policy of the path planning model through policy iteration, enabling it to make the best decision under various circumstances.

[0082] For example, feedback information and driving data are used as historical traffic data, weather data, and vehicle status information, and are input into the path planning model as training samples. The model parameters are optimized through backpropagation. At the same time, a reinforcement learning mechanism is introduced, and a reward function is defined to encourage the path planning model to choose safe and efficient paths. The behavior strategy of the path planning model is gradually optimized through policy iteration, so that it can make the best decisions in various situations. The strategy is to iteratively optimize the path planning model by simulating path planning tasks in different scenarios.

[0083] In this embodiment, by inputting feedback information and driving data as training samples into the path planning model, the model will use the data generated during actual driving to iteratively adjust the model's weight parameters through a preset optimization algorithm. This can significantly improve the path planning model's adaptability to unknown scenarios, ultimately obtaining a well-trained path planning model with high generalization ability, providing reliable technical support for autonomous vehicles.

[0084] The following is for reference. Figure 3 The present application’s dynamic path planning method for autonomous driving will be described using a specific embodiment.

[0085] Real-time information such as road congestion, vehicle speed, and traffic accidents can be collected through sensors on the vehicle, such as GPS, radar, and cameras; current weather data, such as rainfall, can be obtained through data interfaces provided by meteorological departments; and vehicle status information, such as battery level and tire pressure, can be obtained through sensors built into the vehicle.

[0086] The collected data is input into the path planning model, which uses a large language model as its core inference engine. The path planning model will analyze and make decisions based on historical experience and real-time data. Taking into account factors such as current road congestion, the impact of rainfall on driving safety, and the vehicle's remaining battery power, the path planning model generates the optimal path planning scheme.

[0087] Based on the optimal path planning scheme output by the path planning model, and combined with real-time traffic data and vehicle status information, a specific path planning scheme is generated; the specific path planning scheme includes driving route, speed control, obstacle avoidance strategy, etc.

[0088] The specific path planning scheme is sent to the actuator of the autonomous driving system, which will then control the vehicle to travel according to the specific path planning scheme.

[0089] During the journey, the system monitors road congestion, weather changes, and vehicle status in real time. If any abnormalities occur, the system promptly obtains an adjusted route planning solution through the route planning model. If no abnormalities occur, the system collects user feedback and driving data after the journey to optimize the performance of the route planning model and the route planning algorithm.

[0090] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0091] Based on the same inventive concept, this application also provides an autonomous driving dynamic path planning system for implementing the aforementioned autonomous driving dynamic path planning method. The solution provided by this system is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more embodiments of the autonomous driving dynamic path planning system provided below can be found in the limitations of the autonomous driving dynamic path planning method described above, and will not be repeated here.

[0092] In one exemplary embodiment, such as Figure 4 As shown, an autonomous driving dynamic path planning system is provided, including: a data acquisition module 402 and a path planning module 404, wherein:

[0093] The data acquisition module 402 is used to collect real-time route planning information; transmit the real-time route planning information to the route planning model, and the route planning model outputs the optimal route analysis results;

[0094] The path planning module 404 is used to generate a specific path planning scheme based on the optimal path analysis results and real-time path planning information, and transmit the specific path planning scheme to the actuator of the autonomous driving system; the actuator is used to control the vehicle to drive according to the specific path planning scheme.

[0095] Among them, such as Figure 4As shown, the path planning model is loaded onto the data acquisition module 402. The data acquisition module 402 includes real-time data processing and model training and inference processes. The path planning module 404 mainly includes execution and feedback processes. Based on the real-time data processing of the data acquisition module 402, multimodal data such as traffic data, weather data, and vehicle status data are processed in real time. Through data exchange between the data acquisition module 402 and the path planning module 404, the path planning model training and inference, as well as the execution and feedback functions of the autonomous driving system, can be realized in the autonomous driving dynamic path planning system.

[0096] In one embodiment, the data acquisition module is also used to access a real-time traffic information system and acquire real-time traffic data information through a preset communication technology; access a real-time meteorological information system and obtain information from meteorological information sensors on the vehicle to acquire real-time weather data information; and access an integrated vehicle management system and obtain information from vehicle status sensors on the vehicle to acquire real-time vehicle status information.

[0097] In one embodiment, the data acquisition module is further configured to transmit real-time path planning information to a path planning model, which extracts features from the input real-time path planning information and performs decision analysis based on the features to obtain the optimal path analysis result.

[0098] In one embodiment, the path planning module is also used to generate a specific path planning scheme based on the optimal path analysis results, combined with real-time path planning information, and with reference to preset standards.

[0099] In one embodiment, the route planning module is further configured to confirm whether an abnormal situation has occurred based on real-time route planning information; if an abnormal situation has occurred, the real-time route planning information is re-transmitted to the route planning model, and subsequent steps are re-executed; if no abnormal situation has occurred, feedback information and driving data are collected, and the feedback information and driving data are transmitted to the route planning model to obtain the trained route planning model.

[0100] In one embodiment, the data acquisition module is further used to transmit feedback information and driving data to the path planning model, and use the feedback information and driving data as training samples; based on the training samples, the parameters of the path planning model are optimized by a preset algorithm, and the path planning model is simulated under different scenarios by using the reinforcement learning mechanism of the path planning model to obtain the trained path planning model.

[0101] The modules in the aforementioned autonomous driving dynamic path planning system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0102] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores real-time path planning information. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a dynamic path planning method for autonomous driving.

[0103] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0104] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0105] Collect real-time path planning information;

[0106] Real-time route planning information is transmitted to the route planning model, and the route planning model outputs the optimal route analysis results.

[0107] Based on the optimal path analysis results, a specific path planning scheme is generated and transmitted to the actuator of the autonomous driving system; the actuator is used to control the vehicle to drive according to the specific path planning scheme.

[0108] In one embodiment, when the processor executes the computer program, it further performs the following steps: accessing a real-time traffic information system and collecting real-time traffic data information through a preset communication technology; accessing a real-time weather information system and obtaining information from the weather information sensors on the vehicle to collect real-time weather data information; and accessing an integrated vehicle management system and obtaining information from the vehicle status sensors on the vehicle to collect real-time vehicle status information.

[0109] In one embodiment, when the processor executes the computer program, it further performs the following steps: transmitting real-time path planning information to a path planning model, the path planning model extracting features from the input real-time path planning information, and performing decision analysis based on the features to obtain the optimal path analysis result.

[0110] In one embodiment, when the processor executes the computer program, it also performs the following steps: based on the optimal path analysis results, combined with real-time path planning information, and referring to preset standards, a specific path planning scheme is generated.

[0111] In one embodiment, when the processor executes the computer program, it also performs the following steps: based on real-time route planning information, confirming whether an abnormal situation has occurred; if an abnormal situation has occurred, re-execute the steps of transmitting real-time route planning information to the route planning model and subsequent steps; if no abnormal situation has occurred, collect feedback information and driving data, transmit the feedback information and driving data to the route planning model, and obtain the trained route planning model.

[0112] In one embodiment, when the processor executes the computer program, it further performs the following steps: transmitting feedback information and driving data to the path planning model, and using the feedback information and driving data as training samples; based on the training samples, optimizing the parameters of the path planning model through a preset algorithm, and using the reinforcement learning mechanism of the path planning model to simulate path planning tasks in different scenarios, thereby obtaining the trained path planning model.

[0113] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0114] Collect real-time path planning information;

[0115] Real-time route planning information is transmitted to the route planning model, and the route planning model outputs the optimal route analysis results.

[0116] Based on the optimal path analysis results, a specific path planning scheme is generated and transmitted to the actuator of the autonomous driving system; the actuator is used to control the vehicle to drive according to the specific path planning scheme.

[0117] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: accessing a real-time traffic information system and collecting real-time traffic data information through a preset communication technology; accessing a real-time weather information system and obtaining information from the weather information sensors on the vehicle to collect real-time weather data information; and accessing an integrated vehicle management system and obtaining information from the vehicle status sensors on the vehicle to collect real-time vehicle status information.

[0118] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: transmitting real-time path planning information to a path planning model, the path planning model extracting features from the input real-time path planning information, and performing decision analysis based on the features to obtain the optimal path analysis result.

[0119] In one embodiment, when the computer program is executed by the processor, it also performs the following steps: generating a specific path planning scheme based on the optimal path analysis results, combined with real-time path planning information, and referring to preset standards.

[0120] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: based on real-time route planning information, confirming whether an abnormal situation has occurred; if an abnormal situation has occurred, re-executing the steps of transmitting real-time route planning information to the route planning model and subsequent steps; if no abnormal situation has occurred, collecting feedback information and driving data, transmitting the feedback information and driving data to the route planning model, and obtaining the trained route planning model.

[0121] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: transmitting feedback information and driving data to the path planning model, and using the feedback information and driving data as training samples; based on the training samples, optimizing the parameters of the path planning model through a preset algorithm, and using the reinforcement learning mechanism of the path planning model to simulate path planning tasks in different scenarios, thereby obtaining the trained path planning model.

[0122] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0123] Collect real-time path planning information;

[0124] Real-time route planning information is transmitted to the route planning model, and the route planning model outputs the optimal route analysis results.

[0125] Based on the optimal path analysis results, a specific path planning scheme is generated and transmitted to the actuator of the autonomous driving system; the actuator is used to control the vehicle to drive according to the specific path planning scheme.

[0126] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: accessing a real-time traffic information system and collecting real-time traffic data information through a preset communication technology; accessing a real-time weather information system and obtaining information from the weather information sensors on the vehicle to collect real-time weather data information; and accessing an integrated vehicle management system and obtaining information from the vehicle status sensors on the vehicle to collect real-time vehicle status information.

[0127] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: transmitting real-time path planning information to a path planning model, the path planning model extracting features from the input real-time path planning information, and performing decision analysis based on the features to obtain the optimal path analysis result.

[0128] In one embodiment, when the computer program is executed by the processor, it also performs the following steps: generating a specific path planning scheme based on the optimal path analysis results, combined with real-time path planning information, and referring to preset standards.

[0129] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: based on real-time route planning information, confirming whether an abnormal situation has occurred; if an abnormal situation has occurred, re-executing the steps of transmitting real-time route planning information to the route planning model and subsequent steps; if no abnormal situation has occurred, collecting feedback information and driving data, transmitting the feedback information and driving data to the route planning model, and obtaining the trained route planning model.

[0130] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: transmitting feedback information and driving data to the path planning model, and using the feedback information and driving data as training samples; based on the training samples, optimizing the parameters of the path planning model through a preset algorithm, and using the reinforcement learning mechanism of the path planning model to simulate path planning tasks in different scenarios, thereby obtaining the trained path planning model.

[0131] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0132] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0133] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An automatic driving dynamic path planning method, characterized in that, The method comprises: collecting real-time path planning information; transmitting the real-time path planning information to a path planning model, the path planning model outputting optimal path analysis results; based on the optimal path analysis results, generating a specific path planning scheme; transmitting the specific path planning scheme to an execution mechanism of an automatic driving system; the execution mechanism is used to control the vehicle to travel according to the specific path planning scheme.

2. The method of claim 1, wherein, The path planning information includes real-time traffic data information, real-time weather data information and real-time vehicle state information. The collection of real-time path planning information comprises: accessing a real-time traffic information system and collecting real-time traffic data information through a preset communication technology; accessing a real-time weather information system and collecting real-time weather data information by obtaining information of a weather information sensor on the vehicle; accessing an integrated vehicle management system and collecting real-time vehicle state information by obtaining information of a vehicle state sensor on the vehicle.

3. The method of claim 1, wherein, The transmission of the real-time path planning information to the path planning model, the path planning model outputting optimal path analysis results, comprises: transmitting the real-time path planning information to the path planning model, the path planning model extracting features in the input real-time path planning information and making decision analysis based on the features to obtain optimal path analysis results.

4. The method of claim 1, wherein, The generation of the specific path planning scheme based on the optimal path analysis results comprises: based on the optimal path analysis results, combining the real-time path planning information and referring to a preset standard to generate a specific path planning scheme.

5. The method of claim 1, wherein, The method further comprises: based on the real-time path planning information, determining whether an abnormal situation occurs; if an abnormal situation occurs, re-executing the transmission of the real-time path planning information to the path planning model and the subsequent steps; if no abnormal situation occurs, collecting feedback information and driving data, transmitting the feedback information and driving data to the path planning model to obtain a trained path planning model.

6. The method of claim 5, wherein, The transmission of the feedback information and driving data to the path planning model to obtain a trained path planning model comprises: transmitting the feedback information and driving data to the path planning model and taking the feedback information and driving data as training samples; based on the training samples, optimizing parameters of the path planning model through a preset algorithm and simulating path planning tasks in different scenarios by using a reinforcement learning mechanism of the path planning model to obtain a trained path planning model.

7. An automated driving dynamic path planning system, characterized by, The system comprises: a data collection module configured to collect real-time path planning information and transmit the real-time path planning information to a path planning model, the path planning model outputting optimal path analysis results; a path planning module configured to generate a specific path planning scheme based on the optimal path analysis results and the real-time path planning information, and transmit the specific path planning scheme to an execution mechanism of an automatic driving system; the execution mechanism is used to control the vehicle to travel according to the specific path planning scheme.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, which when executed by a processor, implements the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program, which when executed by a processor, implements the steps of the method of any one of claims 1 to 6.

Images