Automatic driving remote dynamic takeover method and system

Abstract

The invention belongs to the technical field of automatic driving, and discloses an automatic driving remote dynamic takeover method and system, and the method comprises the steps: initializing nodes, and configuring a special region for storing path data for each node; generating path data based on a path optimization algorithm; receiving the path data, and performing data decoding and verification in sequence; analyzing and comparing the path received by each node with a currently stored initial path, and determining optimal path data of each node based on an analysis and comparison result; on the basis of a global optimization algorithm, optimal path data is optimized, and dynamic adjustment is carried out in combination with real-time traffic conditions; and controlling the automatic driving vehicle to run automatically according to the adjusted optimal path. According to the invention, by introducing a multi-node data backup and dynamic takeover mechanism and storing and comparing path data in real time, the consistency and accuracy of the data are ensured, and meanwhile, by dynamically adjusting the priority of the path, the adaptability of the system to a complex environment is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an autonomous driving remote dynamic takeover method and system. Background Art

[0002] At present, in the development of current autonomous driving technology, although significant achievements have been made, it still faces many technical challenges, especially in terms of the stability and real-time performance of data transmission, the accuracy and consistency of path information, and the system's ability to respond in emergency situations. Existing autonomous driving systems have the following limitations:

[0003] 1) Data loss and delay: In traditional autonomous driving systems, path data may be lost or delayed during transmission due to signal interference, non-line-of-sight problems or equipment failures, resulting in the autonomous driving vehicle being unable to obtain correct navigation instructions in a timely manner.

[0004] 2) Consistency and accuracy issues of path data: Past technologies may not have an effective mechanism to ensure that the path data received by all nodes is consistent. This may lead to inconsistent path information between different nodes, affecting the collaborative operation of autonomous vehicles.

[0005] 3) Lack of dynamic adjustment mechanism: Traditional systems may lack the ability to dynamically adjust path priorities according to real-time conditions. In complex traffic environments, this may result in the inability of autonomous vehicles to effectively avoid risks or choose the best path.

[0006] 4) Inadequate backup and recovery mechanisms: Past technologies may not have fully considered the need for data backup and rapid recovery. In the event of data loss, the system may take a long time to resume operation, affecting the continuity and safety of autonomous driving. Summary of the invention

[0007] The embodiment of the present invention provides a method and system for remote dynamic takeover of autonomous driving. By introducing multi-node data backup and dynamic takeover mechanisms, path data is stored and compared in real time, ensuring data consistency and accuracy. At the same time, by dynamically adjusting path priorities, the system's adaptability to complex environments is enhanced. In addition, an effective backup and recovery mechanism is provided to ensure the stable operation of the autonomous driving system. These improvements significantly improve the reliability and safety of the autonomous driving system and provide a solid foundation for the future development of autonomous driving technology.

[0008] In order to have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended to be a general review, nor is it intended to identify key / important components or to delineate the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a preface to the detailed description that follows.

[0009] According to a first aspect of an embodiment of the present invention, a method for remote dynamic takeover of autonomous driving is provided.

[0010] In one embodiment, the autonomous driving remote dynamic takeover method includes:

[0011] Initialize the nodes and configure a dedicated area for storing path data for each node; load the preset standard path or the last used path as the initial path;

[0012] Based on the path optimization algorithm, the path data is generated by combining traffic conditions, vehicle status, destination information and environmental factors, and sent to all nodes for synchronization;

[0013] The node receives the path data, and decodes and verifies the data in turn; based on the verification result, the node stores the verified path data and feeds back a reception confirmation signal;

[0014] Analyze and compare the path received by each node with the currently stored initial path, determine the best path data for each node based on the analysis and comparison results, and synchronize them to other nodes;

[0015] Based on the global optimization algorithm, the best path data is optimized and dynamically adjusted according to the real-time traffic conditions; the autonomous driving vehicle is controlled to drive automatically according to the adjusted best path.

[0016] In one embodiment, the path optimization algorithm is based on combining traffic conditions, vehicle status, destination information and environmental factors to generate path data, and sending it to all nodes synchronously includes:

[0017] Real-time monitoring and analysis of current traffic conditions, vehicle status, destination and environmental factors, and use of path optimization algorithms to generate path data;

[0018] Verify the security of the generated path data, package the verified path data into a preset transmission format, and check its integrity and accuracy; based on broadcast or directional sending technology, send the checked path data to all nodes.

[0019] In one embodiment, the traffic condition information includes data on real-time traffic flow, accident information and traffic signal status; the vehicle status information includes data on vehicle speed, acceleration, fuel / power level and driving mode; the destination information includes data on the destination location and the surrounding environment of the destination; and the environmental factor information includes data on weather conditions and road conditions.

[0020] In one embodiment, the analyzing and comparing the path received by each node with the currently stored initial path, determining the best path data of each node based on the analysis and comparison results, and synchronizing to other nodes includes:

[0021] According to the starting point, destination and main passing points, it is determined whether the received path of each node is the same as the current initial path stored in its own dedicated area. If so, the current initial path is used as the best path data of the node and the stored path data is updated. If not, the received path is compared with the historical path;

[0022] According to the detailed path parameters and traffic condition information, determine whether the received path of each node is the same as the historical path. If so, do not save the received path, and use the current initial path as the best path data of the node to update the stored path data. If not, calculate the priority of the received path and the historical path respectively.

[0023] Determine whether the priority of the receiving path of each node is higher than the priority of the historical path. If not, use the current initial path as the best path data of the node and update the stored path data. If so, save the receiving path and use the receiving path as the best path data of the node, update the stored path data, and synchronize the path update information to other nodes.

[0024] In one embodiment, the detailed route parameters include coordinates of waypoints, estimated travel time, and data on road types and conditions.

[0025] In one embodiment, calculating the path priority includes:

[0026] Determine the priority indicators of the path and the corresponding indicator weights, and quantify each priority indicator to obtain the score of each priority indicator;

[0027] Based on the weighted sum method, the priority score of the path is calculated by combining the score of each priority indicator and the corresponding indicator weight.

[0028] In one embodiment, the priority indicators include safety, time efficiency, energy efficiency, passenger experience, reliability, regulations and compliance, emergency handling capabilities, future predictability, and cost-effectiveness.

[0029] In one embodiment, the calculation formula of the priority score is:

[0030]

[0031] In the formula, P represents the priority score;

[0032] n represents the number of priority indicators;

[0033] C i represents the score of the i-th priority indicator;

[0034] ω i Represents the weight of the i-th priority indicator.

[0035] In one embodiment, the optimizing the optimal path data based on the global optimization algorithm and dynamically adjusting it in combination with the real-time traffic conditions; and controlling the automatic driving vehicle to automatically drive according to the adjusted optimal path includes:

[0036] Obtain historical traffic flow data in the traffic network and build a training machine learning model; predict future traffic flow and congestion based on the trained machine learning model;

[0037] Based on graph theory, the traffic network is represented as a graph, and the shortest path algorithm and maximum flow / minimum flow algorithm are used to optimize the traffic network. The nodes in the graph represent intersections, and the edges represent roads.

[0038] Taking minimizing the total driving time, minimizing energy consumption and reducing emissions as the optimization goals, a multi-objective optimization algorithm is used to find the optimal solution;

[0039] Based on real-time traffic data, emergencies and vehicle status, the path priority and vehicle driving route are dynamically adjusted, and the autonomous driving vehicle is controlled to drive automatically according to the adjusted optimal path.

[0040] According to a second aspect of an embodiment of the present invention, an automatic driving remote dynamic takeover system is provided.

[0041] In one embodiment, the autonomous driving remote dynamic takeover system includes:

[0042] The data initialization module is used to initialize the nodes, configure a dedicated area for storing path data for each node, and load the preset standard path or the last used path as the initial path;

[0043] The path data generation module is used to generate path data based on the path optimization algorithm, combined with traffic conditions, vehicle status, destination information and environmental factors, and send it to all nodes for synchronization;

[0044] The path data storage module is used for receiving path data at the node, and decoding and verifying the data in turn; based on the verification result, the verified path data is stored, and a reception confirmation signal is fed back;

[0045] The path data comparison module is used to analyze and compare the path received by each node with the currently stored initial path, determine the best path data for each node based on the analysis and comparison results, and synchronize it to other nodes;

[0046] The global optimization module is used to optimize the optimal path data based on the global optimization algorithm, and dynamically adjust it according to the real-time traffic conditions; the autonomous driving vehicle is controlled to drive automatically according to the adjusted optimal path.

[0047] According to a third aspect of an embodiment of the present invention, a computer device is provided.

[0048] In some embodiments, the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0049] According to a fourth aspect of embodiments of the present invention, a computer-readable storage medium is provided.

[0050] In one embodiment, the computer-readable storage medium stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0051] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0052] 1) The present invention can respond to changes in traffic conditions and system status in real time through a dynamic adjustment mechanism to ensure that the vehicle always travels on the safest path, and the backup mechanism provides rapid recovery in the event of data loss or system failure, reducing potential safety risks.

[0053] 2) The monitoring mechanism of the present invention can ensure that all system nodes are synchronized, thereby reducing errors caused by information asynchrony, and the feedback mechanism allows the system to adjust according to real-time data, thereby improving the stability and reliability of the system.

[0054] 3) The present invention can not only optimize traffic flow, reduce congestion and improve overall traffic efficiency by dynamically adjusting path priorities and sending strategies, but also quickly identify and resolve performance bottlenecks through real-time monitoring and feedback, thereby further improving operational efficiency.

[0055] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0057] Figure 1 is a flow chart of a method for remote dynamic takeover of autonomous driving according to an exemplary embodiment;

[0058] Figure 2 is a structural block diagram of an automatic driving remote dynamic takeover system according to an exemplary embodiment;

[0059] Figure 3 The figure is a schematic diagram showing the structure of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0060] The following description and accompanying drawings fully illustrate the specific embodiments of this article so that those skilled in the art can practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of this article includes the entire scope of the claims, as well as all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such structure, device or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements. Each embodiment is described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other.

[0061] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0062] As used herein, the term "plurality" means two or more than two, unless otherwise specified.

[0063] In this document, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0064] In this article, the term "and / or" is a description of the association relationship between objects, indicating that three relationships may exist. For example, A and / or B means: A or B, or, A and B.

[0065] It should be understood that, although the various steps in the flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0066] Each module in the device or system of the present application can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above modules.

[0067] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0068] Figure 1An embodiment of an automatic driving remote dynamic takeover method of the present invention is shown.

[0069] In this optional embodiment, the autonomous driving remote dynamic takeover method includes:

[0070] Step S101, initializing nodes, configuring a dedicated area for storing path data for each node; loading a preset standard path or a last used path as an initial path;

[0071] Step S103: Generate path data based on the path optimization algorithm, combining traffic conditions, vehicle status, destination information and environmental factors, and send it to all nodes synchronously;

[0072] Step S105: The node receives the path data, and decodes and verifies the data in sequence; based on the verification result, the node stores the verified path data, and feeds back a reception confirmation signal;

[0073] Step S107: Analyze and compare the path received by each node with the currently stored initial path, determine the best path data of each node based on the analysis and comparison results, and synchronize them to other nodes;

[0074] Step S109: Based on the global optimization algorithm, the optimal path data is optimized and dynamically adjusted in combination with the real-time traffic conditions; the autonomous driving vehicle is controlled to automatically drive according to the adjusted optimal path.

[0075] Figure 2 An embodiment of an automatic driving remote dynamic takeover system of the present invention is shown.

[0076] In this optional embodiment, the automatic driving remote dynamic takeover system includes:

[0077] The data initialization module 201 is used to initialize the nodes, configure a dedicated area for storing path data for each node, and load a preset standard path or a last used path as the initial path;

[0078] The path data generation module 203 is used to generate path data based on the path optimization algorithm, combined with traffic conditions, vehicle status, destination information and environmental factors, and send it to all nodes synchronously;

[0079] The path data storage module 205 is used for receiving the path data at the node, and decoding and verifying the data in sequence; based on the verification result, the path data that has passed the verification is stored, and a reception confirmation signal is fed back;

[0080] The path data comparison module 207 is used to analyze and compare the path received by each node with the currently stored initial path, determine the best path data of each node based on the analysis and comparison results, and synchronize it to other nodes;

[0081] The global optimization module 209 is used to optimize the optimal path data based on the global optimization algorithm, and dynamically adjust it in combination with the real-time traffic conditions; and control the automatic driving vehicle to automatically drive according to the adjusted optimal path.

[0082] In order to facilitate understanding of the above technical solutions of the present invention, the above technical solutions of the present invention are further described below from the perspective of architecture and principle, as follows:

[0083] The present invention proposes a remote dynamic takeover scheme for autonomous driving based on multi-node data backup. For path planning, for the path that has been regionally coded, due to factors such as non-line-of-sight, interference, and reduction, it is impossible to ensure that all terminals can receive it. Therefore, it is necessary to set a dedicated area in the node to store past path data to avoid path loss, but it is not suitable to store all paths. Therefore, the present invention proposes a scheme. Before each path is sent, the current path must be stored, and the current sending path is compared with the receiving path. If the two are the same, the current sending path continues to be stored without change. If the two are different, the received path is compared with the past path. Once the same, the receiving path is not saved and the current sending path is still sent. If they are different, a distinction must be made at this time. If the priority of the new receiving path is higher than the current sending path, the receiving path is retained and the new receiving path is sent. If the priority of the new receiving path is lower than the current sending path, the current sending path continues to be stored without change. Further, the present invention proposes that low-priority paths must avoid high-priority paths. Through this path saving and comparison method, remote dynamic takeover of autonomous driving with multi-node data backup is realized.

[0084] Storage and backup of path data: A dedicated area is set up in each node to store the latest path data. This storage mechanism ensures that even if some nodes cannot receive path information, the latest path data can be obtained through other nodes. Before sending a path each time, the system (i.e., the autonomous driving system) automatically stores the current path, which helps to quickly restore and resend the path information.

[0085] Comparison and decision of path data: The system will compare the sent path with the received path. If the two are the same, the current sent path will continue to be used and stored. If the received path is different from the sent path, the system will further compare the received path with the historical path. If the received path is the same as the historical path, the received path will not be saved and the current path will continue to be sent. If the received path is different from the historical path, the system will evaluate the priority of the new received path. If the priority of the new path is higher than the current path, the new path will be saved and sent; if the priority is lower than the current path, the current path will continue to be used.

[0086] Processing of path priority: The present invention particularly emphasizes that low-priority paths must avoid high-priority paths. This rule ensures that high-priority paths are given priority in path selection, thereby improving the efficiency and safety of overall path planning. Through this complex but efficient path management mechanism, the autonomous driving system can maintain a high degree of flexibility and responsiveness during remote dynamic takeover. This method not only improves the reliability of data transmission, but also enhances the system's ability to respond to emergencies, thereby providing important technical support for the development of autonomous driving technology.

[0087] The workflow of this solution is to ensure the efficient and safe operation of the autonomous driving system in complex environments through multi-node data backup and dynamic takeover mechanisms. The following is the detailed workflow of the solution:

[0088] 1. Initialization and path data storage

[0089] Initialization: When the system starts, each node starts listening and preparing to receive path data. Path data storage: Each node sets up a dedicated area to store the latest path data. Initially, the node stores the preset standard path or the last used path.

[0090] 1) Initialization process

[0091] During the system startup phase, the initialization process is a key step to ensure that all nodes can enter the working state smoothly. The following are the detailed steps of initialization:

[0092] Start signal: When the autonomous driving system is started, the central control system sends a start signal to notify all relevant nodes to start the initialization process.

[0093] Node self-check: Each node performs self-check to ensure that the hardware and software are in normal status and can receive and process data.

[0094] Listening mode activated: The node enters the listening mode and is ready to receive path data from the central control system. During this stage, the node will check whether the communication interface is unobstructed to ensure the reliability of data transmission.

[0095] State synchronization: Synchronize state information between nodes to ensure that all nodes are ready to receive path data. This step is critical to ensure synchronization and consistency of the entire system.

[0096] 2) Path data storage

[0097] Path data storage is a key step to ensure that the system can effectively manage and use path information. The following are the detailed steps for path data storage:

[0098] Dedicated storage area allocation: Each node is allocated a dedicated storage area for storing path data. This area usually has enough capacity to store multiple path information and keep the data real-time and accurate.

[0099] Initial path loading: During the initialization phase, the node loads the preset standard path or the last used path as the initial path. These paths are usually based on historical data or preset default paths to ensure that the system can operate normally without any new data input.

[0100] Path data update: When a node receives new path data, it updates the path information in the storage area. This process includes verifying the correctness and validity of the new path, ensuring that only the correct path data is stored and used.

[0101] Data backup: Each time the path data is updated, the node will automatically back up the old path data. This is done to quickly restore to the most recent valid state in the event of data loss or system failure.

[0102] Storage management: Nodes also need to manage storage areas, including cleaning up obsolete path data, optimizing the use of storage space, and ensuring storage efficiency and data access speed.

[0103] Through these detailed steps, initialization and path data storage ensure that the autonomous driving system can quickly enter the working state after startup, and effectively manage and use the path information, providing a solid foundation for subsequent path planning and execution.

[0104] 2. Sending and receiving path data

[0105] Sending path: The central control system or path planning module generates path data and sends it to all relevant nodes. Receiving path: Each node receives the path data and prepares for the next step of processing.

[0106] 1) Sending of path data

[0107] The sending of path data is a key step to ensure that all nodes can obtain the latest path information. The following is the detailed process of sending path data:

[0108] Path generation: The central control system or path planning module generates path data based on current traffic conditions, vehicle status, and destination information. This process at least includes considering factors such as real-time traffic flow, road conditions, weather conditions, etc. to ensure that the generated path is both safe and efficient. The following is a detailed description of the path generation process:

[0109] a. Traffic condition analysis: The central control system or path planning module needs to monitor and analyze the current traffic conditions in real time. This includes:

[0110] Real-time traffic flow: Through traffic monitoring cameras, sensors and data analysis, real-time flow information of vehicles on the road can be obtained to identify congested and unobstructed sections of the road.

[0111] Accident Information: Receive accident reports from traffic management centers or other vehicles so that routes can be adjusted in a timely manner to avoid blocked areas.

[0112] Traffic signal status: Understand the current traffic light status to optimize vehicle travel speed and path selection.

[0113] b. Vehicle status assessment, path generation also needs to consider the status of the vehicle itself, including:

[0114] Speed ​​and acceleration: The current vehicle speed and acceleration capability to ensure that the path design is consistent with the vehicle's dynamic performance.

[0115] Fuel / Charge Level: Consider the vehicle's fuel or battery level to select efficient routes to charging or refueling stations.

[0116] Driving Mode: Adjusts the route to optimize performance or energy saving according to the driving mode set for the vehicle (such as economy mode, sport mode, etc.).

[0117] c. Destination information processing. Destination-related information is also crucial, including:

[0118] Destination location: Precise GPS coordinates to ensure the end point of the route is accurate.

[0119] Destination Surroundings: Evaluate factors such as road conditions, parking conditions, and safety near your destination to optimize your arrival method.

[0120] d. Environmental factors consideration: During the path generation process, external environmental factors need to be considered in real time, such as:

[0121] Weather conditions: Rain, snow, fog, haze and other weather conditions will affect the feasibility and safety of the road, so the route needs to be adjusted in time to avoid dangerous areas.

[0122] Road conditions: Use sensors and map data to understand road maintenance conditions, such as potholes and construction, to plan safer driving routes.

[0123] e. Path optimization algorithm, using advanced path planning algorithms (such as A* algorithm, Dijkstra algorithm, genetic algorithm, etc.) to combine the above information to generate an optimized path. These algorithms can:

[0124] Shortest path calculation: Ensures that the generated path is the shortest or optimal route from the starting point to the destination.

[0125] Dynamic Adjustment: Dynamically adjust the route in real time based on changing traffic conditions and environmental factors to ensure safety and efficiency.

[0126] f. Security verification: After the path generation is completed, the system needs to perform security verification on the generated path, including:

[0127] Conflict Detection: Verify the path for potential conflicts with other vehicles, pedestrians, and obstacles.

[0128] Emergency Considerations: Consider the possibility of emergency stops or lane changes to ensure a safe response in unexpected situations.

[0129] Data Packaging: The generated route data is packaged into a format suitable for transmission. This usually includes encoding the route information into a specific data structure, such as a structured data packet containing information such as the starting point, destination, waypoints, and estimated travel time.

[0130] Sending preparation: Before sending the path data, the system will perform a series of preparations, including checking the integrity and accuracy of the data packet and confirming the communication status of all relevant nodes.

[0131] Broadcast or Directed Sending: Path data can be sent to all nodes via broadcast, or directed to specific nodes as needed. Broadcasting is suitable for situations where all nodes need to be updated synchronously, while directed sending is suitable for nodes in specific tasks or specific areas.

[0132] Send confirmation: After sending the path data, the system will wait for the confirmation signal from the receiving node. This step ensures that the data has been successfully sent and the node is ready to receive and process the data.

[0133] 2) Receiving path data

[0134] The reception of path data is the prerequisite for the node to prepare for the next step of processing. The following is the detailed process of receiving path data:

[0135] Receive preparation: The node is in listening mode and is ready to receive path data. This includes ensuring that the communication interface is unblocked and the receiving function is functioning normally.

[0136] Data Reception: When a node receives path data, it immediately begins decoding and parsing the data packets. This process involves converting the received data into information that the node can understand and process.

[0137] Data verification: The received path data needs to be verified to ensure its integrity and accuracy. It also includes checking the data checksum, timestamp and other information to prevent errors or tampering during data transmission.

[0138] Storing path data: After verification, the node stores the path data in its dedicated storage area. This step ensures the persistence and availability of the path data for subsequent processing and use.

[0139] Send and receive confirmation: After successfully receiving and storing the path data, the node sends a reception confirmation signal to the central control system. This step is the key to ensure the integrity of data transmission and is also the basis for the central control system to proceed to the next step.

[0140] Through these detailed sending and receiving processes, the autonomous driving system can ensure that all nodes can obtain the latest path information in a timely manner, providing a solid foundation for safe and efficient vehicle navigation.

[0141] 3. Comparison and verification of path data

[0142] Comparison of sent and received paths: Each node compares the received path with the currently stored path. If the two are the same, the node continues to use and store the currently sent path. If the two are different, proceed to the next step of detailed comparison.

[0143] Comparison and verification of route data is a key step to ensure that the system uses the latest and most accurate route information. The following is a detailed comparison and verification process:

[0144] Preliminary comparison: Comparison of received path with stored path: Each node first performs a preliminary comparison of the received path data with the currently stored path data. This step mainly compares the basic information of the path, such as the starting point, destination, and major transit points. Handling of identical situations: If the received path is the same as the stored path, the node will continue to use the current path and update the stored path data to reflect the latest path information. Handling of different situations: If the preliminary comparison finds that the received path is different from the stored path, the node will enter the detailed comparison stage.

[0145] 4. Detailed comparison and decision making

[0146] Comparison of received path with historical path: The node compares the received path with the historically stored path. If the received path is the same as the historical path, the node does not save the received path and continues to send the current path. If the received path is different from the historical path, the system evaluates the priority of the new received path. If the new path has a higher priority than the current path, the node saves and sends the new path. If the new path has a lower priority than the current path, the node continues to use the current path.

[0147] In the autonomous driving system, detailed comparison and decision-making is a key process that ensures that the system can make the best navigation decision based on the latest path information. The following is a detailed description of this process:

[0148] Comparison of historical path and received path: Data extraction: The node extracts historical path data from its storage and compares it with the newly received path data. This step involves comparing key parameters of the path, such as the specific coordinates of each waypoint, estimated travel time, possible traffic conditions, etc. Same path processing: If the newly received path is exactly the same as the historical path, the node does not make any changes and continues to use and send the current path. The following is a detailed explanation of the detailed comparison stage:

[0149] 1) Detailed path parameter analysis. In the detailed comparison stage, the system analyzes multiple key parameters of the path, including:

[0150] Waypoint coordinates: The waypoints of each route are composed of specific GPS coordinates. The system will compare the coordinates of each waypoint in the received route with the stored route one by one to ensure spatial consistency.

[0151] Estimated travel time: The system calculates an estimated travel time for each route. This time depends not only on distance, but also on current and predicted traffic conditions, speed limits, and other factors. By comparing these times, you can assess which route is more time-efficient under given conditions.

[0152] Road types and conditions: Each route may pass through different types of roads (highways, urban roads, rural roads, etc.) and may have different road conditions (flat, rugged, under construction, etc.). The system will analyze the characteristics of these road sections to assess the safety and comfort of the route.

[0153] 2) Traffic condition assessment. In the detailed comparison stage, the system also needs to consider the impact of the following traffic conditions:

[0154] Real-time traffic flow: Obtain instant traffic flow data from the traffic monitoring system and compare the current flow and expected congestion on two routes.

[0155] Incident and Obstacle Information: Check the real-time data about incidents or obstacles in the traffic management system to determine which route is safer or whether a detour is needed.

[0156] Traffic signal status: Compare the status of traffic lights along two routes to determine which route is likely to encounter more red lights and wait times during travel.

[0157] 3) Path priority and security. In the detailed comparison process, path priority and security are also important considerations:

[0158] Priority evaluation: The system will evaluate the advantages and disadvantages of the received new paths and stored paths according to the previously set priority rules. For example, for emergency response, some paths may be given higher priority.

[0159] Safety analysis: Evaluate the potential risks of each path, including the surrounding environment, pedestrians, the dynamics of other vehicles, and road conditions, to ensure that the selected path is safe.

[0160] 4) Overall path benefit comparison: Based on all the collected data, the system will compare the overall benefits of the two paths, including: Time efficiency: which path can shorten the arrival time. Energy efficiency: calculate the estimated fuel consumption or power consumption of each path and choose the more economical route.

[0161] Path Difference Analysis: Difference Identification: If the newly received path differs from the historical path, the node will further analyze these differences. This can include minor adjustments to the path or completely different path choices. Detailed Comparison: The node compares the differences in detail and evaluates the potential impact of these changes on driving efficiency and safety.

[0162] Decision and update: Path selection: Based on the comparison and verification results, the node decides whether to adopt a new path. After the detailed comparison phase is over, the system will make a decision based on the above analysis:

[0163] Path selection: If the received new path is better than the storage path in multiple parameters, the system will update the storage path to the new path; if the storage path is better, the storage path will continue to be used.

[0164] Feedback mechanism: After making a decision, the system will record the results of the comparative analysis for future reference and improvement of the path planning algorithm, enhancing the intelligence and adaptability of the system. If the new path is considered to be a better choice, the node will update its stored path data and prepare to implement the new path.

[0165] System synchronization: If the path is updated, the node will send a confirmation message to the central control system and need to synchronize the new path information with other nodes to ensure the path consistency of the entire system.

[0166] Records and feedback:

[0167] Record changes: Nodes record detailed information about path changes, including the time, reason, and result of the change. These records are very important for subsequent path optimization and system maintenance.

[0168] Feedback mechanism: Nodes also provide feedback to the central control system, reporting the results of path changes and any relevant system performance data, helping the central control system optimize the path planning algorithm.

[0169] Through these detailed comparison and verification steps, the autonomous driving system can ensure that the path data it uses is the latest, most accurate and safest, thereby improving the operating efficiency and safety of the entire system.

[0170] 5. Processing of path priority

[0171] Avoidance rules: The system ensures that low-priority paths avoid high-priority paths to optimize overall path planning and traffic efficiency. In an autonomous driving system, the handling of path priorities is a key link in ensuring smooth and safe traffic. The following is a detailed description of how path priorities are handled:

[0172] Priority definition: Priority criteria: The system defines a clear set of priority criteria, which include factors such as the safety, efficiency, traffic conditions, energy consumption, etc. of the path. For example, a path may be given a higher priority if it is shorter, safer, or has smoother traffic. Dynamic adjustment: The priority criteria are dynamically adjusted according to real-time traffic information and system status to ensure that the path selection always reflects the latest traffic conditions.

[0173] To achieve efficient decision-making in path selection for the autonomous driving system, we can assign reasonable weights to each priority criterion and form a unified priority score through weighted combination. The following are the steps to elaborate on this solution:

[0174] 1) Identify the priority criteria: safety, time efficiency, energy efficiency, passenger experience, reliability, regulations and compliance, emergency response capabilities, future predictability, and cost-effectiveness.

[0175] 2) Assign weights: To ensure that the impact of each criterion on the final priority score is consistent with its importance, we can assign weights to each criterion, as shown in Table 1 below:

[0176] Table 1 Weight of each criterion

[0177] Priority Criteria Weight (%) Security 30 Time efficiency 25 Energy efficiency 15 Passenger Experience 10 reliability 5 Regulation and Compliance 5 Emergency handling capabilities 5 Future predictability 3 Cost-effectiveness 2 total 100

[0178] 3) Scoring mechanism. In order to convert each criterion into a quantifiable score, we can use the following scoring method:

[0179] Safety: The score ranges from 0 to 10 based on data such as accident rate and obstacle density.

[0180] Time efficiency: Calculates the estimated travel time compared to other alternative routes, with a score range of 0-10.

[0181] Energy efficiency: Evaluated based on estimated fuel / electricity consumption, with a score range of 0-10.

[0182] Passenger experience: Rated on a scale of 0-10 based on factors such as ride smoothness and noise level.

[0183] Reliability: Based on historical traffic records and real-time feedback, the score range is 0-10.

[0184] Regulation and Compliance: By assessing the route's compliance with regulations, scoring it on a scale of 0-10.

[0185] Emergency handling capability: The score ranges from 0-10 based on how operable the route is in an emergency.

[0186] Future predictability: Assess the accuracy of the prediction of future traffic flow, with a score range of 0-10.

[0187] Cost-effectiveness: Based on an assessment of economic costs, with a score range of 0-10.

[0188] 4) Weighted merging: Use the weighted merging formula to multiply the score of each priority criterion by its weight, and finally sum them up to get a unified priority score. The calculation formula is:

[0189]

[0190] In the formula, P represents the priority score;

[0191] n represents the number of priority indicators;

[0192] C i represents the score of the i-th priority indicator;

[0193] ω i Represents the weight of the i-th priority indicator.

[0194] For example, if a route is scored as follows: safety 8 points, time efficiency 7 points, energy efficiency 6 points, passenger experience 9 points, reliability 5 points, regulations and compliance 10 points, emergency handling capability 7 points, future predictability 6 points, and cost-effectiveness 4 points;

[0195] The corresponding unified priority score is calculated as follows: P = (8×0.3) + (7×0.25) + (6×0.15) + (9×0.1) + (5×0.05) + (10×0.05) + (7×0.05) + (6×0.03) + (4×0.02) = 7.41.

[0196] Avoidance rule enforcement: Low priority path avoidance: When the system detects that a low priority path conflicts or overlaps with a high priority path, the low priority path will be automatically adjusted to avoid conflict with the high priority path. This may involve re-planning the path, selecting different waypoints, or adjusting the travel time. Conflict detection: The system detects potential path conflicts by monitoring and analyzing traffic data in real time. This includes checking intersections of paths, shared road sections, and other areas that may cause conflicts.

[0197] Path Optimization: Global Optimization: The system considers not only the path of a single vehicle, but also the path planning of the entire traffic network. Through global optimization, the system can reduce traffic congestion and improve overall traffic efficiency. Real-time Adjustment: Based on real-time traffic data and events (such as accidents, road construction, etc.), the system adjusts the path priority in real time to ensure that the path selection of all vehicles is optimal.

[0198] The following is a detailed explanation of global optimization and real-time adjustment.

[0199] 1. Global Optimization

[0200] Global optimization refers to the systematic optimization of each vehicle's path while considering the dynamic state of the entire traffic network. Compared with local optimization, this method can more effectively solve traffic congestion and improve overall traffic efficiency. Specifically, global optimization includes the following aspects:

[0201] 1) Comprehensive traffic data analysis

[0202] Traffic flow monitoring: Using sensors, cameras and GPS data, real-time monitoring of vehicle flow, speed and density throughout the transportation network.

[0203] Prediction model: Based on historical data and real-time data, through machine learning and prediction algorithms, predict future traffic flow and congestion.

[0204] These algorithms include, but are not limited to, machine learning and artificial intelligence technologies, specifically the following aspects:

[0205] a. Machine Learning Model

[0206] Predictive models: Machine learning algorithms (such as regression analysis, decision trees, and random forests) are used to analyze historical traffic data and predict future traffic volumes and patterns. These models can dynamically adjust route priorities based on factors such as time, location, weather conditions, holidays, etc.

[0207] Classification and clustering: Use clustering algorithms (such as K-means clustering) to group real-time traffic data and identify congested areas and high-traffic periods so that the system can avoid these areas when planning routes.

[0208] b. Deep learning technology

[0209] Neural Networks: Deep learning models such as convolutional neural networks and recurrent neural networks can process complex input data and identify underlying patterns and changes in traffic flow. These models excel in image recognition and time series forecasting, and can analyze traffic video streams and historical data in real time.

[0210] Reinforcement learning: Through reinforcement learning, the system can optimize its decision-making in the continuous feedback. The agent gradually improves the path selection strategy based on the interactive learning with the environment to achieve the best traffic flow efficiency.

[0211] c. Data fusion and analysis

[0212] Multi-source data integration: The system integrates data from multiple sources (such as sensors, GPS, social media, and traffic management agencies) to generate a more comprehensive view of traffic conditions through data fusion technology. This comprehensive analysis helps enhance the accuracy of predictions and the effectiveness of route optimization.

[0213] Real-time analysis capabilities: Through stream processing technologies (such as Apache Kafka and Apache Flink), the system can process and analyze data streams in real time, respond to changes quickly, and make decisions.

[0214] 2) Network optimization algorithm

[0215] Application of graph theory: Represent the traffic network as a graph, where nodes represent intersections and edges represent roads. Use the shortest path algorithm (such as Dijkstra algorithm or A* algorithm) and the maximum flow / minimum flow algorithm to optimize the entire network.

[0216] In traffic network optimization, the use of graph theory can significantly improve the path planning and traffic management of autonomous driving systems. The following are the specific steps of representing the traffic network as a graph and applying the shortest path algorithm and flow optimization algorithm, which are described in detail in combination with relevant algorithms and formulas.

[0217] 1. Model construction

[0218] a. Graph definition: The traffic network is represented as a graph G = (V, E), where:

[0219] Node V: represents intersection, parking lot, destination, etc.

[0220] Edge E: represents the road connecting the nodes. The weight of the edge can represent the length of the road, travel time or other influencing factors.

[0221] b. Attribute setting, set the weight of each edge to, which can be expressed as:

[0222] =f(d ij ,t ij ,c ij )

[0223] Among them, d ij is the distance, t ij is the travel time, c ij is the traffic flow, and f is a function that takes these factors into consideration.

[0224] 2. Data Collection and Preprocessing

[0225] a. Data source: Traffic data is collected through sensors, GPS, surveillance cameras and other equipment, including real-time traffic flow, road conditions and historical traffic data.

[0226] b. Data cleaning and integration: Clean the collected data, handle missing values ​​and outliers, and integrate data from different sources to ensure data quality and consistency.

[0227] 3. Application of shortest path algorithm

[0228] a. Dijkstra algorithm

[0229] Initialization: Set the distance of the starting node s to 0, the distances of other nodes to infinity, and record the visited nodes and unvisited nodes.

[0230] Iteration process:

[0231] Find the unvisited node u closest to the starting node and mark it as visited.

[0232] For each adjacent node v:

[0233] d[v]=min(d[v],d[u]+w uv )

[0234] Where d[v] represents the currently known shortest distance from the starting node s to the node v; d[u] represents the currently known shortest distance from the starting node s to the node u; w uv Represents the weight of edge (u,v), that is, the distance or cost from node u to node v.

[0235] Update the predecessor node p[v]=u (only when d[v] is updated).

[0236] Termination condition: When the target node t is visited, the path is determined; or all nodes are visited.

[0237] bA* algorithm

[0238] Heuristic function design: Define the heuristic function h(), for example using straight-line distance:

[0239]

[0240] In the formula, (x v ,y v ) represents the coordinates of node v; (x t ,y t ) represents the coordinates of the target node t;

[0241] Priority Queue: Use the priority queue to process nodes and select the node with the lowest cost for processing:

[0242] f(v)=g(v)+h(v)

[0243] Among them, f(v) is the total cost (i.e., cost) from the starting node s to the current node v, including the actual cost and the estimated cost, g(v) is the actual cost (known path cost) from the starting node s to the current node v, and h(v) is the heuristic estimated cost from the current node v to the target node t.

[0244] Update path: Similar to the Dijkstra algorithm, update the distances of adjacent nodes until the target node is found. The update process is as follows:

[0245] For each adjacent node u (a node directly connected to the current node v):

[0246] If the new path from s to u is shorter, update g(u) and f(u), and record the predecessor node:

[0247] g(u)=min(g(u),g(v)+w uv )

[0248] f(u)=g(u)+h(u)

[0249] Update the predecessor node p[u] = v (only when g(u) is updated);

[0250] 4. Application of traffic optimization algorithm

[0251] a. Maximum flow algorithm

[0252] Build flow network: Convert the traffic network into a flow network and set the start and destination nodes.

[0253] Find augmenting paths: Use depth-first search or breadth-first search to find available augmenting paths and make traffic adjustments:

[0254] f(u,v)≤c(u,v)

[0255] Among them, f(u,v) is the flow rate and c(u,v) is the capacity of the edge.

[0256] b. Minimum flow algorithm

[0257] Flow control: Set the flow threshold c for each edge ij , to ensure that the road flow does not exceed the maximum carrying capacity:

[0258]

[0259] In the formula, f ij is the flow from node i to node j (actual flow); the above formula indicates that the sum of flows from node i must be less than or equal to the flow threshold c ij ;

[0260] Adjust routes: Dynamically adjust routes based on traffic distribution to reduce congestion.

[0261] 5. Path optimization and dynamic adjustment

[0262] a. Global Optimization

[0263] Combined with real-time traffic data, the route can be globally optimized and adjusted using dynamic programming or other optimization algorithms, taking into account traffic changes in different time periods.

[0264] b. Priority adjustment

[0265] Dynamically adjust path priorities based on road conditions (such as accidents, construction, etc.) to ensure that the selected path is always the best.

[0266] 6. Result verification and feedback

[0267] Compare and analyze the optimized path with the actual driving results, collect feedback data to adjust and optimize the algorithm model, and continuously improve system performance and adaptability.

[0268] Multi-objective optimization: Consider multiple objectives in path planning, such as minimizing total driving time, minimizing energy consumption, reducing emissions, etc., and use multi-objective optimization algorithms (such as genetic algorithms and particle swarm optimization) to find the optimal solution.

[0269] In path planning, multi-objective optimization is an effective method that can consider multiple objectives at the same time, such as minimizing the total travel time, energy consumption and emissions. The following are the specific steps of applying multi-objective optimization algorithms (such as genetic algorithms and particle swarm optimization) for path planning, which are described in detail in combination with relevant algorithms and formulas.

[0270] 1. Problem Definition

[0271] First, define multiple goals in path planning. Set the objective function:

[0272] f1(x): total driving time;

[0273] f2(x): energy consumption;

[0274] f3(x): emission;

[0275] The formal expression is a multi-objective optimization problem:

[0276]

[0277] Condition x∈X, where X is the feasible solution space.

[0278] 2. Objective function modeling

[0279] A mathematical model is established for each objective function. Assuming x is the parameter of the path, the objective function can be expressed as:

[0280] Total driving time:

[0281]

[0282] Energy consumption:

[0283]

[0284] Emissions:

[0285]

[0286] Among them, d i,i+1 is the distance of the road section, v i,i+1 is the speed, E i,i+1 is the energy consumption of each road segment, C i,i+1 is the emission of each section of road; n is the number of paths, and i,i+1 means the parameter amount from i to i+1.

[0287] 3. Choose a multi-objective optimization algorithm

[0288] Choose a suitable multi-objective optimization algorithm, such as genetic algorithm or particle swarm optimization.

[0289] a. Genetic Algorithm Steps

[0290] Initialization: Generate an initial population, where each individual represents a possible path.

[0291] Evaluate fitness: Calculate the fitness value of each individual, using the objective function:

[0292]

[0293] In the formula, f1(x i )、f2(x i )、f3(x i ) represent the objective function values ​​of the total driving time, energy consumption and emission of the ith individual respectively;

[0294] Selection operation: select individuals based on fitness, using methods such as roulette selection and tournament selection.

[0295] Crossover operation: Crossover the selected individuals to generate the next generation of individuals. Commonly used crossover methods include single-point crossover and multi-point crossover.

[0296] Mutation operation: mutate individuals to increase diversity, usually using small-probability mutation operations.

[0297] Update the population: Generate a new population and repeat the fitness evaluation and selection operations until a predetermined number of generations or convergence conditions are reached.

[0298] b. Particle Swarm Optimization (PSO) Steps

[0299] Initialize particles: Randomly generate N particles, each particle represents a path solution, and initialize the velocity.

[0300] Evaluate fitness: Calculate the fitness value of each particle:

[0301]

[0302] In the formula, pi represents the individual optimal position of the i-th particle;

[0303] Update individual and global optimality: record the optimal position pbest and the global optimal position gbest of each particle.

[0304] Update speed:

[0305] v i =w·v i +c1·r1·(p best -p i )+c2·r2·(g best -p i )

[0306] Update location:

[0307] p i =p i +v i

[0308] Among them, w is the weight factor, c1 and c2 are learning factors, and r1 and r2 are random numbers.

[0309] Iteration: Repeat the fitness evaluation and update operations until the termination condition is reached.

[0310] 4. Non-dominated sorting and Pareto optimization

[0311] Since it is a multi-objective optimization, the non-dominated sorting method is usually used to deal with multiple objectives. Specific steps:

[0312] Non-dominated sorting: Perform non-dominated sorting on the paths in the population to find the dominating relationship.

[0313] Establish Pareto front: The non-dominated solutions are grouped into Pareto front, which represents the optimal solution set under the current objective.

[0314] Select the optimal solution: Select the optimal solution from the Pareto front. Further decisions may be required depending on the application requirements.

[0315] 5. Result analysis and optimization

[0316] Analyze the obtained Pareto solution set and examine the performance of each solution on each objective. The following techniques can be used:

[0317] Sensitivity analysis: Analyze the impact of different objective weights on the final solution.

[0318] Weighted sum method: Assign weights to each objective, convert multiple objectives into a single objective, and optimize:

[0319] f weighted (x) = w1f1(x) + w2f2(x) + w3f3(x)

[0320] Among them, w1+w2+w3=1.

[0321] 3) Interactive Path Coordination

[0322] Vehicle-to-vehicle coordination: Through vehicle-to-vehicle (V2V) communication, collaborative driving is achieved, conflicts between vehicles are reduced, and the efficiency of passing through intersections is improved.

[0323] Signal control optimization: Combined with the traffic signal system, the timing of traffic lights is adjusted through real-time data to optimize traffic flow.

[0324] 2. Real-time adjustment

[0325] Real-time adjustment refers to dynamically adjusting the path priority and selection based on real-time traffic data and emergencies during driving. This ensures that the vehicle can always choose the optimal path when facing a constantly changing traffic environment. Real-time adjustment includes the following aspects:

[0326] 1) Real-time data acquisition

[0327] Traffic incident monitoring: Obtain real-time information about accidents, road construction, weather changes, and other events through various data sources (such as traffic monitoring cameras, sensors, social media, etc.).

[0328] Road status update: Get real-time road status information, including road conditions, traffic signal status, obstacles, etc.

[0329] 2) Dynamic path evaluation

[0330] Priority reassessment: Based on real-time data, various priority criteria (safety, time efficiency, energy efficiency, etc.) are reassessed to ensure that the route selection is based on the latest traffic conditions.

[0331] Re-routing: Once new congestion, accidents or other emergencies are discovered, the system can quickly recalculate the route and provide the best alternative route.

[0332] 3) Adaptive Traffic Management

[0333] Adaptive algorithm: Use intelligent algorithm to adaptively adjust the vehicle's route according to real-time traffic conditions and vehicle status.

[0334] Swarm behavior simulation: When multiple vehicles are driving in parallel, swarm intelligence technology is used to simulate the behavior of the entire traffic flow and optimize the driving path of the group.

[0335] 3. Synergy between global optimization and real-time adjustment

[0336] Global optimization and real-time adjustment complement each other and jointly improve the overall efficiency and safety of the transportation system.

[0337] Specifically:

[0338] Real-time optimization feedback: Global optimization provides macro traffic flow prediction and route planning, while real-time adjustment performs micro route optimization based on immediate feedback. The combination of the two can respond to traffic changes more flexibly.

[0339] Dynamic adjustment and long-term planning: Through real-time adjustment, the system can respond quickly to emergencies, while global optimization provides data support and strategic basis for future traffic planning, forming a closed-loop traffic management system.

[0340] Improve user experience: Through global optimization and real-time adjustment, vehicles can quickly find the optimal route under complex traffic conditions, thereby reducing waiting time and improving passenger satisfaction.

[0341] Decision Support System: Intelligent Algorithms: The system uses advanced algorithms, such as machine learning and artificial intelligence, to predict traffic flow and path efficiency, thereby more accurately setting path priorities. User Interaction: In some cases, the system allows users or operators to intervene to manually adjust path priorities, especially in emergency situations or special events.

[0342] 6. Dynamic adjustment and backup

[0343] Dynamic adjustment: The system can dynamically adjust the path priority and sending strategy according to the real-time traffic conditions and system status. Backup mechanism: Before sending each path, the system automatically backs up the current path to ensure rapid recovery in case of data loss.

[0344] In the autonomous driving system, dynamic adjustment and backup mechanisms are key components to ensure system stability and responsiveness. The following is a detailed description of these two mechanisms:

[0345] Dynamic Adjustment: Real-time traffic condition monitoring: The system continuously monitors traffic conditions, including traffic volume, road conditions, weather changes, etc. through integrated high-precision sensors and real-time data streams. System status assessment: The system also monitors its own status, such as battery power, vehicle health, navigation system performance, etc., to ensure that all components are operating in optimal conditions. Path priority adjustment: Based on the real-time data collected, the system dynamically adjusts path priorities. For example, if a sudden increase in traffic on a certain path is detected, the system may lower the priority of that path and recommend other, smoother paths. Sending strategy adjustment: The system may also adjust the sending strategy of path information, such as sending frequency and target receiving nodes, to ensure the timeliness and accuracy of information delivery.

[0346] Backup Mechanism: Automatic backup: Before each route information is sent, the system automatically creates a backup of the current route. This typically involves storing route data in multiple locations, such as local storage and cloud servers. Fast recovery: In the event of data loss or system failure, the backup mechanism allows the system to quickly recover to the most recent route state. This can be achieved by retrieving the data from the backup and reloading it into the system. Backup verification: The system regularly verifies the integrity and availability of backup data to ensure that these backups can be relied upon when needed. Version control: The backup mechanism may also include version control, recording the history of route changes for easy tracing and analysis.

[0347] Integration and collaboration: Seamless integration: Dynamic adjustment and backup mechanisms are often seamlessly integrated with other parts of the system (such as decision support systems and user interfaces) to ensure the efficient operation of the entire system. Collaborative work: These mechanisms work together to improve the overall performance and reliability of the system. For example, dynamic adjustments can help the system respond to traffic changes in real time, while backup mechanisms ensure that the system remains stable in any unexpected situations. Through these detailed dynamic adjustments and backup mechanisms, the autonomous driving system can effectively respond to various traffic and system challenges, ensuring a safe and efficient driving experience.

[0348] 7. Monitoring and feedback

[0349] Monitoring: The system continuously monitors the sending and receiving status of the path data to ensure that all nodes are synchronized. Feedback: Nodes can feedback the receiving status and path execution to the central control system so that necessary adjustments can be made.

[0350] In an autonomous driving system, monitoring and feedback mechanisms are key to ensuring coordinated operation and continuous optimization of the system. The following is a detailed description of these two mechanisms:

[0351] Monitoring: Real-time data monitoring: The system tracks the sending and receiving status of path data in real time through integrated and efficient monitoring tools. This includes monitoring the transmission speed, success rate and any delays or errors of data packets. Node synchronization: The monitoring mechanism ensures that all system nodes (such as vehicles, traffic management centers, etc.) remain synchronized. This means that all nodes receive the same path information at the same time, thus avoiding confusion and conflicts. Anomaly detection: The system is able to detect and mark any anomalies such as data loss, transmission errors or node failures. These anomalies are immediately identified and the corresponding troubleshooting process is triggered.

[0352] Feedback: Status Reporting: Each node (vehicle or other system component) sends status reports to the central control system at regular intervals. These reports include the status of the node receiving path data, the progress of path execution, and any obstacles or problems encountered. Real-time Feedback: In the event of an emergency or major change, the node can send feedback to the central control system in real time. This real-time feedback mechanism enables the system to respond quickly and make necessary adjustments. Adjustment and Optimization: The central control system analyzes the feedback received and adjusts the path planning and sending strategy. This continuous feedback loop helps the system continuously optimize its performance and improve overall efficiency and safety.

[0353] Integration and synergy: System integration: Monitoring and feedback mechanisms are tightly integrated with other parts of the system, such as data processing, decision support, and user interfaces. This integration ensures seamless operation of the entire system. Synergy: Monitoring and feedback mechanisms support each other and work together to improve the responsiveness and adaptability of the system. For example, effective monitoring ensures that problems are discovered in a timely manner, while timely feedback allows the system to quickly adjust to meet these challenges.

[0354] Through these detailed monitoring and feedback mechanisms, the autonomous driving system can achieve efficient communication and coordination to ensure safe and smooth operation in complex and dynamic traffic environments.

[0355] Through this series of sophisticated workflows, this solution ensures that the autonomous driving system can maintain efficient and safe operation in the face of complex and changing traffic environments. This multi-node data backup and dynamic takeover mechanism significantly improves the reliability and responsiveness of the system, providing solid technical support for the practical application of autonomous driving technology.

[0356] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

[0357] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0358] In addition, the present invention also provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiment when executing the computer program.

[0359] In addition, the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0360] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0361] The present invention is not limited to the structures which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for remote dynamic takeover of automatic driving, characterized in that: include: Initialize the nodes and configure a dedicated area for each node to store path data; Load a preset standard path or the last used path as the initial path; Based on the path optimization algorithm, the path data is generated by combining traffic conditions, vehicle status, destination information and environmental factors, and sent to all nodes for synchronization; The node receives the path data, and decodes and verifies the data in turn; based on the verification result, the node stores the verified path data and feeds back a reception confirmation signal; Analyze and compare the path received by each node with the currently stored initial path, determine the best path data for each node based on the analysis and comparison results, and synchronize them to other nodes; Based on the global optimization algorithm, the best path data is optimized and dynamically adjusted according to the real-time traffic conditions; the autonomous driving vehicle is controlled to drive automatically according to the adjusted best path.

2. The automatic driving remote dynamic takeover method according to claim 1, characterized in that: The path optimization algorithm generates path data based on traffic conditions, vehicle status, destination information and environmental factors, and sends it to all nodes synchronously, including: Real-time monitoring and analysis of current traffic conditions, vehicle status, destination and environmental factors, and use of path optimization algorithms to generate path data; Verify the security of the generated path data, package the verified path data into a preset transmission format, and check its integrity and accuracy; based on broadcast or directional sending technology, send the checked path data to all nodes.

3. The automatic driving remote dynamic takeover method according to claim 2, characterized in that: The traffic condition information includes data on real-time traffic flow, accident information and traffic signal status; the vehicle status information includes data on vehicle speed, acceleration, fuel / power level and driving mode; the destination information includes data on the destination location and the surrounding environment of the destination; the environmental factor information includes data on weather conditions and road conditions.

4. The automatic driving remote dynamic takeover method according to claim 1, characterized in that: The analyzing and comparing the path received by each node with the currently stored initial path, determining the best path data of each node based on the analysis and comparison results, and synchronizing to other nodes includes: According to the starting point, destination and main passing points, it is determined whether the received path of each node is the same as the current initial path stored in its own dedicated area. If so, the current initial path is used as the best path data of the node and the stored path data is updated. If not, the received path is compared with the historical path; According to the detailed path parameters and traffic condition information, determine whether the received path of each node is the same as the historical path. If so, do not save the received path, and use the current initial path as the best path data of the node to update the stored path data. If not, calculate the priority of the received path and the historical path respectively. Determine whether the priority of the receiving path of each node is higher than the priority of the historical path. If not, use the current initial path as the best path data of the node and update the stored path data. If so, save the receiving path and use the receiving path as the best path data of the node, update the stored path data, and synchronize the path update information to other nodes.

5. The automatic driving remote dynamic takeover method according to claim 4, characterized in that: The detailed route parameters include the coordinates of waypoints, estimated travel time, and data on road types and conditions.

6. The automatic driving remote dynamic takeover method according to claim 4, characterized in that: Calculation path priorities include: Determine the priority indicators of the path and the corresponding indicator weights, and quantify each priority indicator to obtain the score of each priority indicator; Based on the weighted sum method, the priority score of the path is calculated by combining the score of each priority indicator and the corresponding indicator weight.

7. The automatic driving remote dynamic takeover method according to claim 6, characterized in that: The priority indicators include safety, time efficiency, energy efficiency, passenger experience, reliability, regulations and compliance, emergency response capabilities, future predictability and cost-effectiveness.

8. The automatic driving remote dynamic takeover method according to claim 6, characterized in that: The calculation formula of the priority score is: In the formula, P represents the priority score; n represents the number of priority indicators; C i represents the score of the i-th priority indicator; ω i Represents the weight of the i-th priority indicator.

9. The automatic driving remote dynamic takeover method according to claim 1, characterized in that: Based on the global optimization algorithm, the best path data is optimized and dynamically adjusted in combination with the real-time traffic conditions; Controlling the autonomous driving vehicle to automatically drive according to the adjusted optimal path includes: Obtain historical traffic flow data in the traffic network and build a training machine learning model; predict future traffic flow and congestion based on the trained machine learning model; Based on graph theory, the traffic network is represented as a graph, and the shortest path algorithm and maximum flow / minimum flow algorithm are used to optimize the traffic network. The nodes in the graph represent intersections, and the edges represent roads. Taking minimizing the total driving time, minimizing energy consumption and reducing emissions as the optimization goals, a multi-objective optimization algorithm is used to find the optimal solution; Based on real-time traffic data, emergencies and vehicle status, the path priority and vehicle driving route are dynamically adjusted, and the autonomous driving vehicle is controlled to drive automatically according to the adjusted optimal path.

10. An automatic driving remote dynamic takeover system, characterized in that: include: A data initialization module, used to initialize nodes and configure a dedicated area for storing path data for each node; Load a preset standard path or the last used path as the initial path; The path data generation module is used to generate path data based on the path optimization algorithm, combined with traffic conditions, vehicle status, destination information and environmental factors, and send it to all nodes for synchronization; The path data storage module is used for receiving path data at the node, and decoding and verifying the data in turn; based on the verification result, the verified path data is stored, and a reception confirmation signal is fed back; The path data comparison module is used to analyze and compare the path received by each node with the currently stored initial path, determine the best path data for each node based on the analysis and comparison results, and synchronize it to other nodes; The global optimization module is used to optimize the optimal path data based on the global optimization algorithm, and dynamically adjust it according to the real-time traffic conditions; the autonomous driving vehicle is controlled to drive automatically according to the adjusted optimal path.

Images