Automatic driving electronic and electrical system

Abstract

The invention discloses an automatic driving electronic and electrical system, and relates to the technical field of automatic driving, and the system comprises a central scheduling manager, a sensing module, a decision module, a control module, a plurality of first computing nodes, and a plurality of edge computing nodes. The sensing module, the decision module, the control module and the plurality of first computing nodes are all connected with the central scheduling manager; each edge computing node is connected with one vehicle-mounted sensor, and the edge computing nodes are used for preprocessing data of the vehicle-mounted sensors and sending the preprocessed data to the sensing module; each first computing node is used for executing a specific instruction, the specific instruction comprises a resource allocation instruction generated by the central scheduling manager according to a real-time computing resource state, and the resource allocation instruction is used for allocating computing resources to the sensing module, the decision module and the control module. According to the invention, the maintenance and expansion difficulty of the system is reduced.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving, and in particular to an autonomous driving electronic and electrical system. Background Art

[0002] With the rapid development of autonomous driving technology, the demand for real-time data processing capabilities has increased significantly. The existing centralized computing architecture is difficult to efficiently process the large amount of sensor data in autonomous driving scenarios, and the system reliability and scalability are greatly limited. In addition, with the continuous iteration of new technologies, the various functional modules in the autonomous driving system need to be frequently upgraded and replaced, and the difficulty of maintaining and expanding the existing system needs to be reduced. Summary of the invention

[0003] The purpose of this application is to provide an autonomous driving electronic and electrical system that reduces the difficulty of system maintenance and expansion.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] The present application provides an autonomous driving electronic and electrical system, comprising: a central scheduling manager, a perception module, a decision module, a control module, a plurality of first computing nodes, and a plurality of edge computing nodes; each of the edge computing nodes is connected to the perception module, the perception module is connected to the decision module, and the decision module is connected to the control module; the perception module, the decision module, the control module, and the plurality of first computing nodes are all connected to the central scheduling manager;

[0006] Each of the edge computing nodes is connected to a vehicle-mounted sensor, and the edge computing node is used to pre-process the vehicle-mounted sensor data and send the pre-processed data to the perception module;

[0007] The perception module is used to fuse the pre-processed data corresponding to the multiple vehicle-mounted sensors to generate a three-dimensional environment model, and send the three-dimensional environment model to the decision module and the central scheduling manager;

[0008] The decision module is used to perform path planning, behavior prediction and driving strategy generation in sequence according to the three-dimensional environment model, and send the driving strategy to the control module;

[0009] The control module is used to generate a vehicle control command according to the driving strategy;

[0010] Each of the first computing nodes is used to execute a specific instruction, which includes a resource allocation instruction generated by the central scheduling manager according to the real-time computing resource status, and the resource allocation instruction is used to allocate computing resources to the perception module, the decision module and the control module.

[0011] Optionally, the autonomous driving electronic and electrical system further includes: a plurality of second computing nodes, each second computing node being connected to a functional module, the functional module including the perception module, the decision module and the control module;

[0012] Each of the second computing nodes is used to execute computing tasks corresponding to each of the functional modules.

[0013] Optionally, the autonomous driving electronic and electrical system also includes: multiple third computing nodes, which are used to perform auxiliary computing tasks, including data storage, map updating, remote communication and system log recording.

[0014] Optionally, the central scheduling manager is also used to monitor the load condition of each of the computing nodes, and schedule tasks for each of the computing nodes according to the load condition of each of the computing nodes, the computing nodes including a first computing node, a second computing node and a third computing node; each of the computing nodes communicates with the central scheduling manager through a high-speed communication network.

[0015] Optionally, the vehicle-mounted sensor includes a camera, a laser radar, a millimeter-wave radar, and an ultrasonic radar;

[0016] The sensor data collected by the camera is image data, the sensor data collected by the lidar is three-dimensional point cloud data, the sensor data collected by the millimeter wave radar is the relative distance and speed between the detected object and the vehicle, and the sensor data collected by the ultrasonic radar is the distance of objects within a set range.

[0017] Optionally, the edge computing node includes a data preprocessing unit; the data preprocessing unit is used to filter, downsample and detect edges on the image data; and perform noise reduction and object recognition on the three-dimensional point cloud data.

[0018] Optionally, the perception module includes a three-dimensional environment model generation unit, which uses a deep learning method to perform feature extraction and feature fusion on the preprocessed image data and the preprocessed three-dimensional point cloud data to generate a three-dimensional environment model.

[0019] Optionally, the central dispatch manager is also used to determine whether to generate an obstacle avoidance driving strategy based on the relative distance and speed between the detected object and the vehicle, and the distance of the object within a set range.

[0020] Optionally, the decision module and the control module communicate via a high-speed communication network.

[0021] Optionally, the vehicle control commands include steering, acceleration, deceleration and braking.

[0022] According to the specific embodiments provided in the present application, the present application discloses the following technical effects: The present application provides an autonomous driving electronic and electrical system, which realizes the modularization of the system architecture through a central scheduling manager, a perception module, a decision module, a control module, multiple first computing nodes and multiple edge computing nodes, and can realize the rapid replacement and upgrade of each functional module, thereby reducing the difficulty of system maintenance and expansion. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 A schematic diagram of the structure of an autonomous driving electronic and electrical system provided for one embodiment of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0027] The present application provides an autonomous driving electronic and electrical system, such as Figure 1 As shown, the autonomous driving electronic and electrical system includes: a central scheduling manager, a perception module, a decision module, a control module, multiple first computing nodes and multiple edge computing nodes; each of the edge computing nodes is connected to the perception module, the perception module is connected to the decision module, and the decision module is connected to the control module; the perception module, the decision module, the control module and multiple first computing nodes are all connected to the central scheduling manager.

[0028] The autonomous driving electronic and electrical system also includes: multiple second computing nodes, each second computing node is connected to a functional module, and the functional module includes the perception module, the decision module and the control module.

[0029] Each of the second computing nodes is used to execute computing tasks corresponding to each of the functional modules.

[0030] The autonomous driving electronic and electrical system also includes: a plurality of third computing nodes, wherein the third computing nodes are used to perform auxiliary computing tasks, and the auxiliary computing tasks include data storage, map updating, remote communication and system log recording.

[0031] The central scheduling manager is the core control unit of the system, responsible for the task allocation, resource management and coordination of the entire system. The central scheduling manager monitors the operating status of each module and the load of each computing node, adjusts the task allocation in real time, and ensures the efficient operation of each functional module. The central scheduling manager is connected to each functional module (such as perception module, decision module, control module) through a high-speed communication network. It is also connected to all distributed computing nodes to allocate computing tasks, transmit instructions and monitor system operation.

[0032] The central scheduling manager is also used to monitor the load condition of each computing node and schedule tasks for each computing node according to the load condition of each computing node. The computing nodes include a first computing node, a second computing node and a third computing node. Each computing node communicates with the central scheduling manager through a high-speed communication network.

[0033] For example, when the system enters complex road conditions, the central dispatch manager will prioritize allocating more computing resources to the decision-making module to ensure that path planning and obstacle avoidance algorithms can be completed quickly. If a computing node is overloaded or fails, the central dispatch manager can quickly migrate tasks to other redundant nodes to ensure high reliability and stability of the system.

[0034] The perception module is used to fuse the pre-processed data corresponding to multiple vehicle-mounted sensors, generate a three-dimensional environment model, and send the three-dimensional environment model to the decision module and the central scheduling manager.

[0035] The vehicle-mounted sensors include cameras, laser radars, millimeter-wave radars, and ultrasonic radars. The vehicle-mounted sensors capture information from the external environment in real time. The signals generated by these sensors contain data about the surrounding environment, such as roads, pedestrians, and other vehicles, and at the same time collect the vehicle's own status signals, such as vehicle speed, steering angle, acceleration, braking status, etc. This information serves as the basic data input for the system operation.

[0036] Each of the edge computing nodes is connected to a vehicle-mounted sensor and is located near the vehicle-mounted sensor. The edge computing node is used to preprocess the vehicle-mounted sensor data and perform simple target recognition, and send the preprocessed data to the perception module, thereby reducing computing pressure and improving the real-time performance of the system.

[0037] Each of the first computing nodes is used to execute a specific instruction, wherein the specific instruction includes a resource allocation instruction generated by the central scheduling manager according to the real-time computing resource status, and the resource allocation instruction is used to allocate computing resources to the perception module, the decision module and the control module. The first computing node dynamically allocates task loads according to the instructions of the central scheduling manager and undertakes the computing work of the perception, decision and control modules.

[0038] The functional modules are connected or communicated through standardized interfaces.

[0039] This application uses standardized interfaces to achieve rapid replacement and upgrade of functional modules, and uses the flexible scheduling of distributed computing resources to optimize system performance. This architecture not only improves the reliability and scalability of the system, but also enhances the real-time and flexibility of the autonomous driving system in dealing with complex road conditions.

[0040] The sensor data collected by the camera is image data, the sensor data collected by the lidar is three-dimensional point cloud data, the sensor data collected by the millimeter wave radar is the relative distance and speed between the detected object and the vehicle, and the sensor data collected by the ultrasonic radar is the distance of objects within a set range.

[0041] The edge computing node includes a data preprocessing unit; the data preprocessing unit is used to filter, downsample and detect edges of the image data; and perform noise reduction and object recognition on the three-dimensional point cloud data.

[0042] The data preprocessing unit preprocesses the sensor data collected by the millimeter wave radar, including: noise filtering, target detection and preliminary classification, distance and speed estimation, and target tracking.

[0043] 1. Noise filtering: Millimeter-wave radar is easily affected by noise, such as interference from other radar systems, environmental reflections, etc. The edge computing node will first execute a noise filtering algorithm to remove invalid or unreliable signals to ensure the accuracy of subsequent processing.

[0044] 2. Target detection and preliminary classification: Millimeter wave radar is used to detect the relative distance and speed of objects. The edge computing node processes the radar echo signal and performs preliminary classification after detecting the target, such as identifying moving objects (such as vehicles and pedestrians) or stationary objects (such as roadblocks). Preliminary classification helps reduce the computing burden of the central system.

[0045] 3. Distance and speed estimation: Millimeter wave radar measures the relative speed of an object through the Doppler effect. The edge node is responsible for quickly processing the Doppler frequency shift signal, estimating the speed and distance of the target object, and providing accurate input data for subsequent decision modules.

[0046] 4. Target tracking: The edge computing node will execute a simple target tracking algorithm to track multiple detected objects and determine their relative motion trajectories to facilitate subsequent dynamic planning and obstacle avoidance.

[0047] The data preprocessing unit preprocesses the sensor data collected by the ultrasonic sensor, including: signal noise reduction and filtering, distance estimation and object detection, and obstacle size and type inference.

[0048] 1. Signal noise reduction and filtering: The signal of the ultrasonic sensor is easily interfered by environmental factors such as air flow and humidity. The edge computing node will first perform signal noise reduction processing to filter out false echoes or environmental interference to improve data accuracy.

[0049] 2. Distance estimation and object detection: Ultrasonic sensors are mainly used to detect objects at close range. The edge node processes the echo time, accurately estimates the distance of the object, and outputs the detection results in real time to ensure that the system can accurately sense the location of obstacles in low-speed environments or during parking.

[0050] 3. Obstacle size and type inference: The edge computing node can infer the size and possible type of obstacles (such as vehicles, walls, and other objects) by analyzing the reflection intensity and echo characteristics of the ultrasonic signal, providing further information support for the decision-making module.

[0051] The preprocessing of millimeter-wave radar mainly focuses on noise filtering, target detection, distance and speed estimation, target tracking, etc., to ensure that the system can understand the dynamic objects around the vehicle in real time.

[0052] The preprocessing of ultrasonic sensors focuses on signal noise reduction, close-range obstacle detection, and obstacle feature inference, and is usually used for accurate perception in parking scenarios and low-speed driving.

[0053] The perception module includes a data acquisition unit and a three-dimensional environment model generation unit. The data acquisition unit is used to receive data transmitted by the edge computing node. The three-dimensional environment model generation unit uses a deep learning method to extract and fuse features of the pre-processed image data and the pre-processed three-dimensional point cloud data to generate a three-dimensional environment model. The data processing at this stage is intended to provide the system with an overall and accurate model of the surrounding environment.

[0054] The decision module is used to perform path planning, behavior prediction and generate driving strategies in sequence according to the three-dimensional environment model, and send the driving strategies to the control module. The driving strategies include the vehicle's steering, acceleration, deceleration and obstacle avoidance strategies. Specifically, firstly, based on the current road conditions and vehicle position, the path planning algorithm is run to generate the optimal driving path for the vehicle. At the same time, the behavior prediction algorithm is used to predict the movement trajectories of other dynamic objects (such as pedestrians and vehicles), and the necessary obstacle avoidance strategies are executed. During this process, the system will comprehensively consider the current vehicle speed, steering angle and obstacle distribution around the vehicle to ensure that the generated driving strategy is safe and efficient.

[0055] The control module receives the control commands generated by the decision module and is responsible for the execution of the vehicle's actions, including steering, acceleration, braking and other operations. It is the execution layer for the vehicle to interact with the external environment and directly controls the vehicle's power and control systems. Specifically: After completing the path planning, the decision module will generate specific control instructions, such as acceleration, deceleration, steering and braking. These instructions are then transmitted to the control module through a high-speed communication network. The control module is responsible for converting these instructions into actual vehicle operations. The control module is connected to the vehicle's steering system, brake system and power system and other execution units, and directly controls these hardware devices through the electronic control unit (ECU). For example, when the decision module requires the vehicle to turn right, the control module transmits the instruction to the steering system to adjust the steering wheel angle. Similarly, if an obstacle is detected ahead and emergency braking is required, the control module will immediately activate the braking system to ensure that the vehicle stops safely.

[0056] The autonomous driving electronic and electrical system also includes a high-speed communication network, such as Ethernet, which is used to ensure real-time communication between modules and nodes, especially in the process of autonomous driving, where high-precision, low-latency data transmission is required. It has time synchronization, flow control and delay guarantee functions to ensure that data interaction between different modules in the system can be completed within a predetermined time window. The central scheduling manager, perception module, decision module, control module and edge computing node are all closely connected through a high-speed communication network to ensure that data and instructions can be transmitted within milliseconds.

[0057] The first computing node, the second computing node and the third computing node of the present application are three types of computing nodes. The third computing node is an independent processing unit, distributed at different locations, and is responsible for processing specific tasks.

[0058] The first computing node dynamically allocates task loads according to the instructions of the central scheduling manager and undertakes the computing work of the perception, decision-making and control modules. More specifically, the functions of the first computing node include: resource allocation and load balancing, task scheduling execution and high-priority task processing.

[0059] The first computing node receives resource allocation instructions from the central scheduling manager and performs system-level task allocation and load balancing. The first computing node is responsible for dynamically allocating resources and executing tasks according to real-time computing requirements.

[0060] The central scheduling manager issues tasks through the first computing node, and the first computing node performs global task scheduling. For example, emergency obstacle avoidance tasks and complex path planning will be efficiently processed on these nodes.

[0061] The first computing node is usually used to process high-priority tasks, which are tasks that have a direct impact on system security, such as computing processing of perception modules and decision modules.

[0062] The first computing node is usually located in a central control unit of the vehicle (such as a domain controller or a central processing unit), and the first computing node is concentrated on a main computing platform of the vehicle to achieve fast communication and task allocation.

[0063] The second computing node is directly connected to a specific functional module (such as a perception module, a decision module, a control module, etc.) and is responsible for processing the local tasks of the module. They process specific functions according to the instructions of the central scheduling manager or the requirements of the task module. The role of the second computing node specifically includes local computing and data processing, data preprocessing and fusion, task execution and feedback.

[0064] Local computing and data processing: The second computing node is dedicated to processing data related to the functional module to which it is connected. For example, the second computing node connected to the perception module is responsible for preliminary processing of data from sensors such as lidar and cameras; the second computing node connected to the decision module is responsible for calculating path planning, obstacle avoidance, etc.

[0065] Data preprocessing and fusion: The second computing node of the perception module performs sensor data preprocessing and data fusion, such as comprehensive processing of camera, lidar, and millimeter-wave radar data, and generates a preliminary environmental model.

[0066] Task execution and feedback: The second computing node is responsible for executing the computing tasks related to its functional module and feeding back the results to the central scheduling manager. For example, the second computing node of the control module is responsible for executing specific control instructions (such as steering, acceleration, braking) and reporting the task status to the scheduling manager.

[0067] The second computing node is set at the distributed controller position: it may be located in multiple locations of the vehicle to disperse the processing of tasks related to perception, decision-making, and control, reducing the performance bottleneck caused by centralized computing.

[0068] The third computing node is not directly connected to the central dispatch manager or specific functional modules, but independently processes certain tasks or provides auxiliary computing capabilities for the system. They are usually used to handle tasks that do not require real-time performance or do not directly affect the core decisions of the system. The third computing node is used to undertake some non-core, low-priority tasks that do not require real-time response but are critical to the long-term stability and data accumulation of the system. The third computing node is also used as a redundant backup for the system, taking over some tasks when the main computing node fails to ensure the fault tolerance of the system. The third computing node is also used to handle remote communication tasks and is responsible for communication with external cloud platforms or other vehicles for data exchange and sharing.

[0069] The third computing node is usually deployed in a location that does not affect the layout of the main sensors, such as the roof, trunk, or other non-core control areas. These locations are convenient for expanding computing resources and connecting to external networks.

[0070] The control module is used to generate a vehicle control command according to the driving strategy.

[0071] The central dispatch manager is also used to determine whether to generate an obstacle avoidance driving strategy based on the relative distance and speed between the detected object and the vehicle, and the distance of the object within a set range.

[0072] The decision module and the control module communicate via a high-speed communication network.

[0073] The vehicle control commands include steering, acceleration, deceleration and braking.

[0074] The dynamic allocation of computing resources and task scheduling for the central scheduling manager specifically include:

[0075] 1. Real-time monitoring of system status: The central scheduling manager continuously monitors the real-time status of each computing node (specifically central processing unit, dedicated controller, etc.) and each edge computing node. Monitoring indicators include CPU and GPU usage, memory usage, network latency, task queue length, etc. At the same time, the system will also monitor each functional module (such as perception module, decision module, control module) to check the parameters such as the task volume, task priority, and task computational complexity of each functional module. Through these monitoring, the central scheduling manager can dynamically obtain the current resource usage and task load as the basis for subsequent resource scheduling.

[0076] 2. Task priority analysis: Tasks in the autonomous driving system are divided into different priorities according to their importance and real-time nature. For example, emergency obstacle avoidance tasks have the highest priority, while tasks such as path planning and map updates have relatively lower priorities. The central scheduling manager allocates resources based on the priority and latency requirements of the tasks. For example, high-priority tasks (such as obstacle avoidance calculations) are immediately assigned to the most idle or most suitable computing nodes, while low-priority tasks (such as data storage or background map updates) are delayed or assigned to lower-performance nodes.

[0077] 3. Dynamic allocation of computing resources: The central scheduling manager dynamically selects the appropriate computing node to perform the task based on the real-time status of each computing node (such as available resources, communication bandwidth, processing power, etc.) and the computational complexity of the task. The specialties of different computing nodes may be considered here. For example, some nodes are good at parallel processing (suitable for processing lidar data), while other nodes may be more suitable for image processing (suitable for processing camera data). To avoid overloading computing nodes, the central scheduling manager will implement a load balancing strategy. When the load of a computing node reaches a certain threshold, the scheduling manager will automatically assign new tasks to nodes with lower loads, thereby preventing the performance bottleneck of a single node from affecting the response time of the entire system. When the priority of a task changes or the amount of tasks suddenly increases, the central scheduling manager can dynamically adjust resource allocation. For example, when the system detects a complex scene or emergency situation (such as an obstacle ahead that needs to be avoided), the scheduling manager will immediately allocate more computing resources to the decision module to ensure that the obstacle avoidance strategy can be generated quickly.

[0078] 4. Task Scheduling and Migration: The central scheduling manager usually adopts a variety of scheduling strategies, such as the earliest deadline first (EDF), minimum slack time first, or polling scheduling. These strategies help the system decide which task should be executed first to ensure that time-sensitive tasks can be completed on time. When a computing node is overloaded, fails, or requires system maintenance, the central scheduling manager can migrate the executing tasks to other available nodes. This process is achieved through virtualization technology or containerization technology, which can smoothly migrate without interrupting task execution. For example, tasks may migrate from central nodes to edge computing nodes, or between different edge nodes. The central scheduling manager also reserves a portion of computing resources for processing sudden tasks. For example, when it is expected that the vehicle is about to enter complex road conditions, the central scheduling manager will allocate more computing resources to the perception and decision-making modules in advance to cope with the upcoming increase in computing needs.

[0079] The present application discloses an autonomous driving electronic and electrical system, specifically a schematic diagram of an autonomous driving electronic and electrical system based on a modular distributed computing architecture, with a specific workflow: when the vehicle starts, the central dispatch manager first monitors the system status and collects real-time data from each module; the perception module pre-processes the data from multiple sensors through the edge node, and then passes the fused data to the decision module; the decision module generates driving strategies and control commands based on these data, and then executes specific vehicle operations through the control module. During the entire process, the central dispatch manager allocates and adjusts the task load of each computing node in real time to ensure efficient and reliable operation of the system under different working conditions.

[0080] The modular design of this application allows for flexible replacement and upgrading of decision-making units according to different algorithms or driving strategies. The control module is responsible for the output of control instructions such as steering, acceleration, and braking of the vehicle, and operates independently of other modules to ensure real-time control response in a distributed system. Distributed computing and task scheduling can reduce communication delays and improve real-time performance. The central scheduling manager allocates computing tasks in real time based on the load of the computing nodes and the current road conditions. The tasks of the perception module can be preferentially assigned to edge nodes close to the sensor, while the tasks of the decision module and the control module are handled by central nodes with stronger computing power. The scheduling algorithm can dynamically adjust the task allocation of nodes according to the real-time performance requirements of the system to ensure optimal performance.

[0081] Each module of this application has a redundant design, that is, when a module or node fails, the system can quickly switch to the backup node to ensure uninterrupted functions. In addition, through the self-diagnosis system, each module can be monitored in real time. When an abnormality is detected, the system can self-repair or switch to a spare computing node to ensure the high availability of the autonomous driving system.

[0082] Each module in this application uses a standardized interface, and each module can be quickly replaced or upgraded according to the latest technology without the need to reconstruct the entire system. For example, the perception module can improve the perception accuracy by replacing new sensor hardware or upgrading the algorithm. This design simplifies the maintenance process of the system and reduces the cost and complexity of subsequent upgrades.

[0083] This application uses a distributed architecture to efficiently process a variety of signals collected by on-board sensors, and uses modular design to enable each functional module to operate independently and collaborate dynamically. The acquisition, processing, decision-making and execution of signals are closely integrated, and the central scheduling manager ensures reasonable task allocation and optimized resource utilization. Ultimately, the safe and reliable operation of autonomous driving vehicles in complex environments is achieved, with high real-time performance, high reliability and flexibility. Through this modular distributed computing architecture, the system can not only meet the high computing requirements of autonomous driving, but also improve reliability, scalability and flexibility. This application can effectively respond to the rapid changes in future autonomous driving technology and provide efficient vehicle control and environmental perception capabilities.

[0084] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0085] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. An automatic driving electronic and electrical system, characterized in that: The autonomous driving electronic and electrical system comprises: a central dispatch manager, a perception module, a decision module, a control module, a plurality of first computing nodes and a plurality of edge computing nodes; each of the edge computing nodes is connected to the perception module, the perception module is connected to the decision module, and the decision module is connected to the control module; the perception module, the decision module, the control module and the plurality of first computing nodes are all connected to the central dispatch manager; Each of the edge computing nodes is connected to a vehicle-mounted sensor, and the edge computing node is used to pre-process the vehicle-mounted sensor data and send the pre-processed data to the perception module; The perception module is used to fuse the pre-processed data corresponding to the multiple vehicle-mounted sensors to generate a three-dimensional environment model, and send the three-dimensional environment model to the decision module and the central scheduling manager; The decision module is used to perform path planning, behavior prediction and driving strategy generation in sequence according to the three-dimensional environment model, and send the driving strategy to the control module; The control module is used to generate a vehicle control command according to the driving strategy; Each of the first computing nodes is used to execute a specific instruction, which includes a resource allocation instruction generated by the central scheduling manager according to the real-time computing resource status, and the resource allocation instruction is used to allocate computing resources to the perception module, the decision module and the control module.

2. The automatic driving electronic and electrical system according to claim 1, characterized in that: The autonomous driving electronic and electrical system further includes: a plurality of second computing nodes, each second computing node being connected to a functional module, the functional module including the perception module, the decision module and the control module; Each of the second computing nodes is used to execute computing tasks corresponding to each of the functional modules.

3. The automatic driving electronic and electrical system according to claim 2, characterized in that: The autonomous driving electronic and electrical system also includes: a plurality of third computing nodes, wherein the third computing nodes are used to perform auxiliary computing tasks, and the auxiliary computing tasks include data storage, map updating, remote communication and system log recording.

4. The automatic driving electronic and electrical system according to claim 3, characterized in that: The central scheduling manager is also used to monitor the load condition of each computing node and schedule tasks for each computing node according to the load condition of each computing node. The computing nodes include a first computing node, a second computing node and a third computing node. Each computing node communicates with the central scheduling manager through a high-speed communication network.

5. The automatic driving electronic and electrical system according to claim 1, characterized in that: The vehicle-mounted sensors include cameras, laser radars, millimeter-wave radars and ultrasonic radars; The sensor data collected by the camera is image data, the sensor data collected by the lidar is three-dimensional point cloud data, the sensor data collected by the millimeter wave radar is the relative distance and speed between the detected object and the vehicle, and the sensor data collected by the ultrasonic radar is the distance of objects within a set range.

6. The automatic driving electronic and electrical system according to claim 5, characterized in that: The edge computing node includes a data preprocessing unit; the data preprocessing unit is used to filter, downsample and detect edges of the image data; and perform noise reduction and object recognition on the three-dimensional point cloud data.

7. The automatic driving electronic and electrical system according to claim 5, characterized in that: The perception module includes a three-dimensional environment model generation unit, which uses a deep learning method to perform feature extraction and feature fusion on the preprocessed image data and the preprocessed three-dimensional point cloud data to generate a three-dimensional environment model.

8. The automatic driving electronic and electrical system according to claim 5, characterized in that: The central dispatch manager is also used to determine whether to generate an obstacle avoidance driving strategy based on the relative distance and speed between the detected object and the vehicle, and the distance of the object within a set range.

9. The automatic driving electronic and electrical system according to claim 1, characterized in that: The decision module and the control module communicate via a high-speed communication network.

10. The automatic driving electronic and electrical system according to claim 1, characterized in that: The vehicle control commands include steering, acceleration, deceleration and braking.

Images