Electronic and electrical architecture applied to intelligent networked automobile

By designing an integrated electronic and electrical architecture in intelligent connected vehicles, the problems of low data interaction efficiency and insufficient standardization are solved, efficient and reliable data processing and cloud interaction are achieved, and the performance of intelligent driving and new energy vehicle control is improved. .

CN119058749APending Publication Date: 2024-12-03WESTERN CHINA SCI CITY INNOVATION CENT OF INTELLIGENT & CONNECTED VEHICLES (CHONGQING) CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411342371.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-25
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the prior art Under the centralized computing platform, the data interaction and access of intelligent connected vehicles have problems such as low efficiency, insufficient standardization, low compatibility, and lack of reliable cloud interaction solutions.

Method used

An electronic and electrical architecture including a central computing platform and regional control module was designed, integrating autonomous driving module, vehicle control center module, interactive center module and data center module, using Ethernet and CAN bus communication to achieve centralization of computing power and data Unified management and redundant control ensure data processing capabilities and cloud interaction reliability.

Benefits of technology

Improve the efficiency and reliability of intelligent driving, vehicle control and cloud interaction, reduce the number of ECUs, realize the decoupling of software and hardware, meet the technical requirements of intelligent driving, new energy vehicle control and cloud interaction, and improve the overall operation of the car Safety and reliability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119058749A_ABST
    Figure CN119058749A_ABST
Patent Text Reader

Abstract

The electronic and electrical architecture comprises a central computing platform and an area control module, and the central computing platform is provided with an automatic driving module, a vehicle control center module, an interaction center module and a data center module in an integrated mode, the automatic driving module is used for intelligent driving control of the intelligent networked automobile; the interaction center module is used for man-machine interaction of the intelligent network connection automobile and communication and interaction control of the intelligent network connection automobile; the data center module is used for carrying out data customization processing and data storage on the multi-source heterogeneous data of the intelligent networked automobile, and is used for cloud interaction of the intelligent networked automobile; the area control module comprises a left front area control module, a left rear area control module, a right front area control module and a right rear area control module which are respectively communicated with the central computing platform, the left front area control module is communicated with the right front area control module, and the left rear area control module is communicated with the right rear area control module.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of automotive technology, and more specifically, to an electronic and electrical architecture applied to intelligent connected vehicles. Background Art

[0002] At present, the automotive industry is moving towards the new four-in-one route of electrification, intelligence, networking and sharing, and the electronic and electrical architecture is also developing rapidly with the trend. The overall evolution of automotive electronic and electrical architecture has evolved from distributed architecture to domain control architecture, then to domain centralized architecture, and then to central centralized architecture. In the later period, it gradually developed towards a central centralized architecture for networking. The electronic and electrical architecture for intelligent networking needs to meet the requirements of intelligence and networking, so it should be a heterogeneous service-oriented computing platform on the vehicle side. However, the existing technical solutions do not take into account the cumbersome blocking problems of data interaction and access generated under the centralized computing platform. For services for the needs of intelligent connected vehicles, there are technical problems such as low efficiency, insufficient standardization, low compatibility, and lack of reliable cloud interaction solutions. Summary of the invention

[0003] The present application provides an electronic and electrical architecture applied to an intelligent connected vehicle to overcome at least one technical problem existing in the prior art.

[0004] The specific technical solutions are as follows:

[0005] The embodiment of the present application provides an electronic and electrical architecture applied to an intelligent networked vehicle, wherein the electronic and electrical architecture includes a central computing platform and a regional control module.

[0006] The central computing platform is integrated with an autonomous driving module, a vehicle control center module, an interactive center module and a data center module which are interconnected in pairs; the autonomous driving module is used for the intelligent driving control of the intelligent connected vehicle; the vehicle control center module is used for the power control, chassis control, body control and redundancy control of the intelligent connected vehicle; the interactive center module is used for the human-computer interaction of the intelligent connected vehicle, and for the communication and interactive control of the intelligent connected vehicle; the data center module is used for data customization processing and data storage of multi-source heterogeneous data of the intelligent connected vehicle, and is used for cloud interaction of the intelligent connected vehicle;

[0007] The regional control module includes a left front regional control module, a left rear regional control module, a right front regional control module, and a right rear regional control module, which are respectively connected to the central computing platform, and the left front regional control module is connected to the right front regional control module, and the left rear regional control module is connected to the right rear regional control module; the left front regional control module is used for the left front physical area control of the intelligent connected vehicle; the left rear regional control module is used for the left rear physical area control of the intelligent connected vehicle; the right front regional control module is used for the right front physical area control of the intelligent connected vehicle; and the right rear regional control module is used for the right rear physical area control of the intelligent connected vehicle.

[0008] In some embodiments of the present application, the autonomous driving module includes a vehicle decision unit, a path planning unit and an AI training unit; the vehicle decision unit is used to make driving decisions based on vehicle perception signals and based on the autonomous driving model, and output decision execution instructions; the path planning unit is used to perform travel planning based on the path planning algorithm according to the cloud data interacting with the cloud control platform, and output a transportation travel plan; the AI ​​training unit is used to iteratively train the autonomous driving model and update the model parameters according to the user's driving data.

[0009] In some embodiments of the present application, the path planning algorithm includes:

[0010] In the initialization phase of the random rapid search tree RRT, the node set and edge set of the RRT tree are initialized, the initialized node set is the initial state of the tree node, and the initialized edge set is empty;

[0011] In the growth stage of the RRT tree, the random sampling and expansion step is repeatedly performed until the expanded new node is the travel destination, wherein the random sampling and expansion step includes: randomly sampling the map of the environment in which the intelligent connected vehicle is located, and when the sampling point falls in the safe area of ​​the map, selecting the node closest to the sampling point in the current RRT tree, and expanding the node toward the sampling point, and if the trajectory generated after adding the node does not collide with the obstacle, then the trajectory is added to the edge set, and the node is added to the node set.

[0012] In some embodiments of the present application, the vehicle control center module includes a power control unit, a chassis control unit, a body control unit and a redundant control unit; the power control unit is used for the whole vehicle control, drive shaft control, engine control, transmission control, whole vehicle mode control and cruise control of the intelligent connected vehicle; the chassis control unit is used for the steering control and braking control of the intelligent connected vehicle; the body control unit is used for the physical area control and whole vehicle wake-up and sleep control of the intelligent connected vehicle; the redundant control unit is used for the redundant control between the left front area control module and the right front area control module, the redundant control between the left rear area control module and the right rear area control module, and for the redundant control between the automatic driving module, the vehicle control center module, the interactive center module and the data center module.

[0013] In some embodiments of the present application, the interaction center module includes an intelligent gateway unit, an intelligent cockpit unit, a remote interaction unit and a communication control unit; the intelligent gateway unit is used to make vehicle driving decisions for the intelligent connected vehicle, and is used for wireless communication control of the intelligent connected vehicle; the intelligent cockpit unit is used for human-machine interface HMI control and multimedia control of the intelligent connected vehicle, and performs driving behavior simulation based on multimodal data in the cockpit; the remote interaction unit is used for OTA system control of the intelligent connected vehicle; the communication control unit is used for in-vehicle communication control and network control of the intelligent connected vehicle.

[0014] In some embodiments of the present application, the data center module includes a customized processing unit, a data storage unit and a cloud interaction unit; the customized processing unit is used to perform standardized customized processing on the multi-source heterogeneous data to obtain processed standardized data; the data storage unit is used to store the standardized data and cached data during the interaction between the intelligent connected vehicle and the cloud control platform; the cloud interaction unit is used for data transmission between the customized processing unit and the cloud control platform.

[0015] In some embodiments of the present application, the standardized customization processing includes data preprocessing, preset format conversion processing, feature extraction processing, data fusion processing and data compression processing;

[0016] The data preprocessing includes: performing data enhancement, filtering and normalization processing on the multi-source heterogeneous data, and converting the data storage format of the multi-source heterogeneous data;

[0017] The preset format conversion process includes: classifying the multi-source heterogeneous data according to the customized data type, and converting each type of the multi-source heterogeneous data after the data classification into a standardized data format, wherein the customized data type includes a visual information data type, a vehicle behavior data type, a communication data type, a positioning and radar data type, a fault alarm data type, a cloud interaction data type, and a driver behavior data type;

[0018] The feature extraction process includes: extracting HOG features, LBP features, and Haar features from the multi-source heterogeneous data based on the OpenCV algorithm library and convolutional neural network, and / or extracting targets from the multi-source heterogeneous data using a target detection extraction algorithm;

[0019] The data fusion processing includes: performing multi-sensor fusion on the multi-source heterogeneous data based on a random fusion algorithm and an artificial intelligence fusion algorithm, wherein the random fusion algorithm includes a weighted average method, a Kalman filter method, a multi-Bayesian estimation method, a D-S evidence reasoning method and a production rule, and the artificial intelligence fusion algorithm includes a fuzzy logic thrust algorithm and an artificial neural network algorithm;

[0020] The data compression processing includes: performing PCA dimensionality reduction processing on the multi-source heterogeneous data, or acquiring and reconstructing sparse signals based on compressed sensing technology; at the same time, using an image reconstruction algorithm to restore and enhance the multi-source heterogeneous data of the visual information data class.

[0021] In some embodiments of the present application, the multi-source heterogeneous data of the visual information data class is subjected to data fusion processing, including:

[0022] Obtain visual image data collected by the camera, point cloud data collected by the laser radar, depth radar image data collected by the millimeter wave radar, and close-range image data collected by the ultrasonic radar;

[0023] According to the weights of different environmental background influencing factors of the visual image data in the application scenario, the visual image data of different environments are weightedly fused to obtain visual fusion data, and the visual fusion data is fused with the point cloud data, the depth radar image data, and the close-range image data to obtain a fused output image; wherein the environmental background influencing factors include illumination factors, road marking line factors, road sign factors, and road obstacle factors, and the calculation formula of the fused output image is:

[0024]

[0025] Among them, S represents the fused output image; u(x) represents visual image data; u(y) represents point cloud data; u(z) represents depth radar image data; u(l) represents close-range image data; n represents the total number of environmental background influencing factors, n=4; W1 represents the weight coefficient of the illumination factor, and its value is determined by the illumination level; W2 represents the weight coefficient of the road marking line factor, and its value is determined by the recognition rate of the road marking line; W3 represents the weight coefficient of the road sign factor, and its value is determined by the recognition rate of the road sign; W4 represents the weight coefficient of the road obstacle factor, and its value is determined by the distance of the obstacle.

[0026] In some embodiments of the present application, the left front area control module is also used for low-voltage power supply control, intelligent fuse box control and pedal control of the intelligent connected vehicle; the left rear area control module is also used for charging control, cabin ventilation control and body accessory control of the intelligent connected vehicle; the right front area control module is also used for intelligent power distribution, motor control, battery management system control and thermal management system control of the intelligent connected vehicle; the right rear area control module is also used for air conditioning control, lighting control and door and window control of the intelligent connected vehicle.

[0027] In some embodiments of the present application, the communication methods of the autonomous driving module and the interactive center module are both Ethernet, and the communication method of the vehicle control center module is CAN bus or CAN FD bus.

[0028] The innovative features of the embodiments of the present application include but are not limited to the following:

[0029] 1. The autonomous driving module, vehicle control center module, interactive center module and data center module are integrated on the central computing platform to realize the centralization of computing power, reduce the number of ECUs, achieve software and hardware decoupling, and allocate a large amount of resources to the intelligent driving functional domain, the intelligent cockpit interaction domain and the communication interaction functional domain, further ensuring the efficient execution of traditional functional domains.

[0030] 2. Deploy the data center module on the central computing platform to uniformly manage the multi-source heterogeneous data generated, perform specific processing and standardization on the data, meet the reliability of interaction with the cloud, and have strong data processing capabilities.

[0031] 3. Use a reliable redundancy solution to ensure that when a controller fails, the overall communication link is still open, avoiding serious consequences caused by a module failure in an emergency.

[0032] 4. Deploy domain controllers in the four areas of the vehicle, namely the left front, right front, left rear and right rear. This can not only perform reliable perception of the vehicle in various scenarios, but also coordinate control with the central control to meet the instructions issued by the central computing platform, and can also provide timely feedback on vehicle status signals. In addition, the ECU controller in the physical area is applied on the computing basic platform, which can realize the decoupling of software and hardware functions and achieve cross-domain sharing.

[0033] 5. The electronic and electrical architecture adopts hierarchical control, with the central computing platform as the highest level, making high-dimensional upper-level decisions, and the physical area control module performing basic functions and basic edge sensing and execution.

[0034] The beneficial effects of the embodiments of the present application are as follows:

[0035] Compared with the traditional five domains of intelligent driving, intelligent cockpit, body, chassis, and power, this electronic and electrical architecture deploys the data center on the central computing platform. It can uniformly manage the massive data generated under the current Ethernet transmission, standardize the interaction of data of each functional module, and adopt a high-efficiency redundancy solution to solve the communication redundancy problem caused by centralized control in the existing technology. It greatly improves the efficiency of the overall operation of the car and the realization of the overall function, and is safer and more reliable. The design meets the technical requirements of intelligent driving, new energy vehicle control, smart cockpit and cloud interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 A structural block diagram of an electronic and electrical architecture applied to an intelligent connected vehicle provided in an embodiment of the present application;

[0038] Figure 2 A block diagram of the composition of an autonomous driving module in an electronic and electrical architecture applied to an intelligent connected vehicle provided in an embodiment of the present application;

[0039] Figure 3 A block diagram of the composition of a vehicle control center module in an electronic and electrical architecture applied to an intelligent connected vehicle provided in an embodiment of the present application;

[0040] Figure 4 A block diagram of the composition of an interactive center module in an electronic and electrical architecture applied to an intelligent connected vehicle provided in an embodiment of the present application;

[0041] Figure 5 A block diagram of the composition of a data center module in an electronic and electrical architecture applied to an intelligent connected vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] 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, rather than 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.

[0043] It should be noted that, in the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The terms "including" and "having" in the embodiments of the present application and the accompanying drawings and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0044] The present application discloses an electronic and electrical architecture for use in an intelligent networked vehicle, which is described in detail below.

[0045] Figure 1 An electronic and electrical architecture for an intelligent connected vehicle provided in accordance with an embodiment of the present application is shown, such as Figure 1 As shown, the electronic and electrical architecture mainly includes a central computing platform 1 and a regional control module. The centralized central computing platform 1 is the embodiment of centralized computing power, on which various functional areas are deployed, namely, the autonomous driving module 2, the vehicle control center module 3, the interactive center module 4 and the data center module 5. The autonomous driving module 2, the vehicle control center module 3, the interactive center module 4 and the data center module 5 are integrated on the central computing platform 1. The chip of the central computing platform 1 can be used to strongly support the AI ​​(Artificial Intelligence) computing system, and efficiently realize computing access decision-making and other functions. Connected to the central computing platform 1 is the regional control module at the physical level. In the physical regional control, regional perception and execution as well as low-latitude control can be realized.

[0046] Specifically, Figure 1As shown, the autonomous driving module 2, vehicle control center module 3, interactive center module 4 and data center module 5 integrated on the central computing platform 1 are interconnected in pairs. In the embodiment of the present application, the communication network of the central computing platform 1 is a multi-mode heterogeneous communication network based on Ethernet, which can realize efficient interaction of large amounts of data. Furthermore, the communication mode of the autonomous driving module 2 and the interactive center module 4 is Ethernet, and high-speed Ethernet can be selected. The functional modules connected by Ethernet between the autonomous driving module 2 and the interactive center module 4 are both interconnected and independent of each other, and can be safely isolated. It should be noted that if the communication modes of each module are different, they need to be connected through a central gateway. The communication mode of the vehicle control center module 3 is CAN (Controller Area Network, area network controller) bus or CAN FD (Controller Area Network with Flexible Data Rate, variable rate area network controller) bus, and high-speed CAN bus or high-speed CAN FD bus can be used for interaction to ensure the reliability of in-vehicle communication. The data center module 5 serves as a management module for data processing, which can simultaneously meet the transmission requirements of CAN bus, CAN FD bus and Ethernet. It should be noted that Figure 1 The single solid line shown in represents Ethernet, and the double solid line represents a CAN bus or a CAN FD bus.

[0047] In some embodiments, the automatic driving module 2 is used for intelligent driving control of intelligent networked vehicles, and has vehicle decision-making functions, vehicle path planning functions, and AI training functions. Figure 2As shown, the automatic driving module 2 includes a vehicle decision unit 21, a path planning unit 22 and an AI training unit 23. The vehicle decision unit 21 is used to make driving decisions based on the vehicle perception signal and the automatic driving model, and output decision execution instructions. At the vehicle decision level, the vehicle perception signal relied on by the vehicle decision unit 21 is the data perceived by the camera, millimeter wave radar, laser radar and ultrasonic radar. The automatic driving model makes vehicle decisions based on these perceived data, outputs decision execution instructions, and then commands the actuator to execute to achieve intelligent control. Its control dimension can be divided into horizontal dimension and vertical dimension. The functions of the horizontal dimension include automatic steering, steering assistance, lane keeping and deviation warning, and the functions of the vertical dimension include active braking management, adaptive cruise control (Adaptive Cruise Control, ACC) and other functions. The path planning unit 22 is used to plan travel based on the cloud data interacting with the cloud control platform and the path planning algorithm, and output the traffic travel plan. At the path planning level, the automatic driving module 2 interacts with the cloud data of the cloud control platform, and plans the commuting data through the path planning algorithm decision to improve travel efficiency. The AI ​​training unit 23 is used to iteratively train the autonomous driving model and update model parameters based on user driving data. At the AI ​​machine learning level, the user driving data of the intelligent connected vehicle is used as a training sample and is continuously iterated in the autonomous driving model. The solution algorithm used by each OEM can be used to generate scenarios, thereby making the autonomous driving more proficient during iteration. The autonomous driving scenario is based on a data-driven approach and uses the BEVcontrol architecture in the prior art to generate scenarios.

[0048] In a specific embodiment, the path planning algorithm adopted by the automatic driving module 2 may include the following steps:

[0049] Step S110, in the initialization phase of the Rapidly-exploring Random Trees (RRT), the node set and edge set of the RRT tree are initialized, the initialized node set is the initial state of the tree nodes, and the initialized edge set is empty.

[0050] Step S120, in the growth stage of the RRT tree, repeatedly execute the random sampling expansion step until the expanded new node is the travel destination, wherein the random sampling expansion step includes: randomly sampling the map of the environment in which the intelligent connected vehicle is located, and when the sampling point falls in the safe area of ​​the map, select the node closest to the sampling point in the current RRT tree, and expand the node to the sampling point. If the trajectory generated after adding the node does not collide with the obstacle, the trajectory is added to the edge set and the node is added to the node set.

[0051] This path planning algorithm uses an incremental sampling search method without setting any resolution parameters, and its search tree is composed of many shorter curves or paths. In extreme cases, the search tree formed will cover the entire space with high density.

[0052] In some embodiments, the vehicle control center module 3 is used for power control, chassis control, body control and redundant control of the intelligent networked vehicle. It includes most of the functional modules of the traditional automotive electronic and electrical architecture, integrates high-dimensional control of power control, chassis control and body control, and includes redundant control. Figure 3As shown, the vehicle control center module 3 includes a power control unit 31, a chassis control unit 32, a body control unit 33 and a redundant control unit 34. The power control unit 31 is used for the whole vehicle control, drive shaft control, engine control, gearbox control, whole vehicle mode control and cruise control of the intelligent networked vehicle. At the power control level, the main functions of the vehicle control center module 3 include whole vehicle three-electric control, traditional power control and drive shaft control. Among them, the whole vehicle three-electric control is the same as the whole vehicle three-electric control (i.e., vehicle control VCU, Vehicle control unit) in the traditional domain control electronic and electrical architecture, mainly including the functions of whole vehicle power on and off, whole vehicle energy management, whole vehicle drive management and functional safety control. Traditional power control includes engine control, gearbox control, whole vehicle mode control and cruise control. Drive shaft control mainly includes four-wheel drive control function. The chassis control unit 32 is used for steering control and brake control of the intelligent networked vehicle. At the chassis control level, the vehicle control center module 3 has control over the brake acceleration decision layer, as well as control over the auxiliary driving layer such as ABS (Antilock Brake System) and ESP (Electronic Stability Program). The body control unit 33 is used for physical area control and vehicle wake-up and sleep control of the intelligent networked vehicle. At the body control level, the vehicle control center module 3 mainly deploys high-latitude control of physical area control and coordinates the overall execution of each area. In addition, it also has functions such as body wake-up and sleep management to facilitate vehicle management. The redundant control unit 34 is used for redundant control between the left front area control module 6 and the right front area control module 8, redundant control between the left rear area control module 7 and the right rear area control module 9, and redundant control between the automatic driving module 2, the vehicle control center module 3, the interactive center module 4 and the data center module 5. The setting of the redundant control unit 34 solves the problem of communication loss in the physical area due to an accident or communication blockage. When this situation occurs, the physical area can interact with the central computing platform 1 through another communication channel. For example, the left front area and the right front area are redundant with each other. When the communication link of one party fails, the data can interact with the central computing platform 1 through another channel. At the same time, the main functional modules integrated in the central computing platform 1 also have the function of mutual redundancy. Specifically, the vehicle control center module 3 has a redundant solution for the automatic driving module 2 and the interactive center module 4. When the automatic driving module 2 and the interactive center module 4 fail, they can quickly enter the failure mode.

[0053] In some embodiments, the interaction center module 4 is used for human-machine interaction of the intelligent networked vehicle, and for communication and interactive control of the intelligent networked vehicle, so as to better complete the interaction between the driver and the vehicle, the interaction inside the vehicle, and the interaction between the vehicle and the outside. Figure 4As shown, the interactive center module 4 includes an intelligent gateway unit 41, an intelligent cockpit unit 42, a remote interactive unit 43 and a communication control unit 44. The intelligent cockpit unit 42 is used for human-machine interface HMI control and multimedia control of the intelligent networked car, and performs driving behavior simulation based on the multimodal data in the cockpit. At the intelligent cockpit level, the interactive center module 4 in the embodiment of the present application has a cloud interaction in addition to the infotainment system, which can simulate the driver's style behavior. Specifically, in the functional area of ​​the intelligent cockpit, there are human-computer interaction functions, including but not limited to screen interaction, intelligent voice interaction, seat interaction, vehicle HUD (Head Up Display), AR (Augmented Reality) intelligent scenes. In terms of driver style simulation, the cloud control platform collects the driver's behavior data and emotional state information, and iteratively trains through the convolutional neural network algorithm, so as to simulate the driver's style during the driver's driving process, so that the driver can drive the vehicle more easily and gradually free his hands and feet. The interactive center module 4 in the embodiment of the present application, at the level of intelligent gateway and in-vehicle and out-vehicle communication, the vehicle network communication technology can meet the requirements of high-level autonomous driving and big data for high bandwidth, high synchronization, low latency, multi-redundancy, multi-fusion, scalability, and high reliability of in-vehicle and out-vehicle network communication. The intelligent gateway unit 41 is used to make vehicle driving decisions for intelligent networked vehicles and is used for wireless communication control of intelligent networked vehicles. At the level of intelligent gateway, the interactive center module 4 is used to coordinate different communication protocols to meet the different communication protocols in the vehicle. For out-vehicle communication, its internal deployment consists of V2X (Vehicle to Everything, vehicle wireless communication) / 5G wireless communication modules, and out-vehicle wireless communication can be set based on future vehicle-mounted wireless technology.The communication control unit 44 is used for in-vehicle communication control and network control of the intelligent connected vehicle. For in-vehicle communication, the interactive center module 4 deploys an Ethernet transmission module. The Ethernet transmission function adopts the SOME / IP (Scalable service-Oriented MiddlewarE over IP, scalable service-oriented middleware based on IP) protocol for communication, and at the same time adopts DDS (Data Distribution Service) to enrich the functions of Ethernet, and has Ethernet AVB (Audio Video Bridging) protocol and TSN (Time-Sensitive Network) technology, providing a set of time-sensitive mechanisms to ensure the time synchronization and determinism of Ethernet during the communication process, and can support the interactivity between different network protocols. In terms of diagnosis, the DoIP (Diagnostic communication over Internet Protocol, a diagnostic communication protocol based on Ethernet) diagnostic protocol is adopted to facilitate unified management. The entire automotive communication application is under the vehicle-road-cloud collaborative architecture, using the new generation of information and communication technology to connect the physical layer, information layer, and application layer of the vehicle, road, and cloud into one, and conduct integrated perception, decision-making, and control, which can achieve a comprehensive improvement in the performance of vehicle driving and traffic operation safety, efficiency, etc. A cyber-physical system. The remote interaction unit 43 is used for OTA (Over-the-Air Technology) system control of intelligent networked vehicles. In terms of OTA, the interactive center module 4 not only supports remote upgrades SOTA (Software OTA), but also supports fixed-level upgrades FOTA (Firmware OTA), supports changes in the software management layer, and performs information interaction layer transmission rule definition, network parameter configuration, software platform adaptation diagnosis, software upgrades, etc. for user functional requirements. It also has remote fault detection, information security, and other functions.

[0054] In some embodiments, the data center module 5 is used for data customization processing and data storage of multi-source heterogeneous data of intelligent connected vehicles, and for cloud interaction of intelligent connected vehicles. The data center module 5 is built into the central computing platform 1, and the massive and cumbersome data generated by the electronic and electrical architecture can be uniformly managed and standardized through the data center module 5. The data center module 5 is closely connected to the central computing platform 1, and communicates and interoperates data through SPI (Serial Peripheral Interface), and at the same time, it interoperates with external sensor data, can receive data from various sensors of the intelligent connected vehicle, and process the received data. In the present application, the data center module 5 mainly has three functions: data customization processing, data storage, and cloud interaction. For details, see Figure 5 As shown, the data center module 5 includes a customized processing unit 51, a data storage unit 52 and a cloud interaction unit 53, wherein the customized processing unit 51 is used to perform standardized customized processing on multi-source heterogeneous data to obtain processed standardized data, the data storage unit 52 is used to store standardized data and cached data in the interaction process between the intelligent connected vehicle and the cloud control platform, and a ROM (Read-Only Memory) area used exclusively by the data center module 5 is provided in the central computing platform 1, which stores data efficiently and quickly through automotive-grade DDR5 (Double Data rate fifth-generation Synchronous Dynamic Random-access Memory) or UFS (Universal Flash Storage) flash memory technology, and the cloud interaction unit 53 is used for data transmission between the customized processing unit 51 and the cloud control platform.

[0055] The data center module 5 performs standardized customized processing such as data preprocessing, preset format conversion processing, feature extraction processing, data fusion processing and data compression processing on multi-source heterogeneous data to ensure that the data is effectively used and avoid the problems of data from different sources being unable to be retrieved from each other and low transmission efficiency due to different hardware platforms or software platforms. Specifically, data preprocessing includes: data enhancement, filtering and normalization processing on multi-source heterogeneous data, and converting the data storage format of multi-source heterogeneous data; preset format conversion processing includes: data classification of multi-source heterogeneous data according to customized data types, and standardized data format conversion of each type of multi-source heterogeneous data after data classification, wherein the customized data types include visual information data class, vehicle behavior data class, communication data class, positioning and radar data class, fault alarm data class, cloud interaction data class and driver behavior data class; feature extraction processing includes: based on OpenCV (Open Source Computer Vision Library) algorithm library and convolutional neural network, HOG (Histogram of Oriented Gradient) features, LBP (Local Binary Image Processing) features are performed on multi-source heterogeneous data. Patterns, local binary pattern) features, Haar feature extraction, and / or target extraction of multi-source heterogeneous data using target detection and extraction algorithms; data fusion processing includes: multi-sensor fusion of multi-source heterogeneous data based on random fusion algorithms and artificial intelligence fusion algorithms, among which random fusion algorithms include weighted average method, Kalman filtering method, multi-Bayesian estimation method, D–S (Dempster–Shafer evidence theory) evidence reasoning method and production rules, and artificial intelligence fusion algorithms include fuzzy logic thrust algorithm and artificial neural network algorithm; data compression processing includes: PCA (Principal Component Analysis) dimensionality reduction processing of multi-source heterogeneous data, or acquisition and reconstruction of sparse signals based on compressed sensing technology; at the same time, image reconstruction algorithm is used to restore and enhance multi-source heterogeneous data of visual information data. At the core function data customization processing level, the data center module 5 has data from visual perception, and performs standardized preprocessing on the video data, so that other modules or the cloud control platform can calculate the data, for example, radar data, or the fusion of radar data and video data. For other intelligent modules, the data can be standardized and compressed. The compressed data is temporarily stored in the data center through ROM for transmission when needed. In addition, the data can be extracted in a customized manner through feature extraction, and unnecessary data information is discarded, making data interaction and storage more efficient.

[0056] Among them, in some specific implementation processes, multi-source heterogeneous data of visual information data are subjected to data fusion processing, including the following steps:

[0057] Step S210, obtaining visual image data collected by the camera, point cloud data collected by the laser radar, depth radar image data collected by the millimeter wave radar, and close-range image data collected by the ultrasonic radar.

[0058] In the embodiment of the present application, the data sources of multi-source heterogeneous data fusion of visual information data are mainly lidar, millimeter-wave radar, camera and ultrasonic radar. Among them, lidar collects point cloud data, millimeter-wave radar collects depth radar information containing angular velocity, that is, depth radar image data, the camera collects image information, that is, visual image data, and ultrasonic radar collects obstacle information, that is, close-range image data.

[0059] Step S220, according to the weights of different environmental background influencing factors of the visual image data in the application scenario, weighted fusion is performed on the visual image data of different environments to calculate visual fusion data, and the visual fusion data is fused with the point cloud data, the depth radar image data, and the close-range image data to calculate a fused output image; wherein the environmental background influencing factors include illumination factors, road marking line factors, road sign factors, and road obstacle factors, and the calculation formula for the fused output image is:

[0060]

[0061] Among them, S represents the fused output image; u(x) represents visual image data; u(y) represents point cloud data; u(z) represents depth radar image data; u(l) represents close-range image data; n represents the total number of environmental background influencing factors, n=4; W1 represents the weight coefficient of the illumination factor, and its value is determined by the illumination level; W2 represents the weight coefficient of the road marking line factor, and its value is determined by the recognition rate of the road marking line; W3 represents the weight coefficient of the road sign factor, and its value is determined by the recognition rate of the road sign; W4 represents the weight coefficient of the road obstacle factor, and its value is determined by the distance of the obstacle.

[0062] In the embodiment of the present application, the data fusion of visual information data mainly considers two factors, namely, complex background factors and three-dimensional information factors (i.e., information collected by laser radar, millimeter-wave radar, camera, and ultrasonic radar). The camera is mainly used to identify the color of objects, but it is affected by rainy weather, that is, affected by light. The millimeter-wave radar can make up for the disadvantage of the camera being affected by rainy days, and can identify obstacles at a relatively long distance, such as pedestrians, roadblocks, etc., but cannot identify the specific shape of the obstacles. The laser radar can make up for the disadvantage that the millimeter-wave radar cannot identify the specific shape of the obstacles. In addition, the ultrasonic radar can identify close obstacles of the vehicle body, so that a panoramic perception can be formed by fusing the external data collected by different sensors. Further, since the visual image data collected by the camera is affected by light, the complex background factor mainly considers the light intensity and the distance of the obstruction to improve the accuracy of the fusion. As shown in the calculation formula of the above-mentioned fusion output image, the application scenarios are divided into several categories, and the fusion weight distribution of the visual image data of each category of application scenarios is different. The illumination factor is determined by the illumination intensity and the level is determined by the photosensitive sensor. It can be divided into three levels: low illumination, medium illumination and high illumination. The visual image data of the low illumination level application scene needs to be integrated with more point cloud data to overcome the influence of the illumination factor on the object color recognition. That is, the higher the illumination intensity, the less the visual image data is affected. Therefore, the weight coefficient W1 of the visual image data of the three levels of low illumination, medium illumination and high illumination application scenes increases. The road marking line factor is determined by the recognition rate of the road marking line in the visual image data. If the road marking line information obtained through the visual image data is unclear, specifically, the recognition rate of the road marking line is lower than 80%, it is necessary to integrate the deep radar image data to obtain more complete road marking line information. That is to say, the higher the recognition rate of the road marking line, the less the visual image data is affected. Therefore, the weight coefficient W2 of the road marking line factor can be positively correlated with the recognition rate of the road marking line. The road sign factor is determined by the recognition rate of the road sign. In the process of road sign identification, it is mainly determined by visual image data. The higher the recognition rate of the road sign, the higher the completeness of the fused road sign information. Therefore, the weight coefficient W3 of the road sign factor can also be positively correlated with the recognition rate of the road sign. The road obstacle factor is determined by the size of the obstacle distance. The obstacle is detected by visual image data, but the approximate distance of the obstacle is determined by the close-range image data collected by the ultrasonic radar. If the obstacle distance is determined to be medium or short, the depth radar image data collected by the millimeter wave radar can also be integrated to determine the position and speed of the obstacle. In other words, the closer the obstacle distance, the higher the reliability of the visual image data. Therefore, the weight coefficient W4 of the road obstacle factor is negatively correlated with the size of the obstacle distance.

[0063] In the calculation of the lidar u(y), the full-view information obtained by the lidar is the information of the three-dimensional space coordinates represented by the point cloud. Therefore, the data fusion of the lidar and the camera is actually the combination of the depth formed by the projection of the lidar point cloud on the camera image plane and the depth estimated by the image. The calibration of the lidar and the camera is completed synchronously, so the lidar point cloud can be calibrated and projected onto the camera's image plane to form a relatively sparse depth map. In this process, the point cloud data needs to be projected to form a bird's-eye view and a front view, etc. After that, CNN (Convolutional Neural Networks) in 2D is used for feature extraction, and then the point cloud is converted into RGBMap (RGB color map, specified as a c×3 numerical matrix composed of values ​​in the range [0,1]) by projection to complete the feature output.

[0064] The centralized central computing platform 1 of the present application can achieve hardware and software decoupling through the setting of the data center module 5, which is beneficial to improving the platform versatility of engineering development. The isolated software used by the central computing platform 1 has exclusive hardware resources, and in the software isolation type, the operating system does not have exclusive hardware resources, and its hardware resources are dynamically allocated by the Hypervisor layer.

[0065] The physical functional area of ​​the electronic and electrical architecture of the present application is divided into four areas, namely, the left front area control module 6, the left rear area control module 7, the right front area control module 8, and the right rear area control module 9, which are respectively connected to the central computing platform 1. The left front area control module 6 is used for the left front physical area control of the intelligent networked car, the left rear area control module 7 is used for the left rear physical area control of the intelligent networked car, the right front area control module 8 is used for the right front physical area control of the intelligent networked car, and the right rear area control module 9 is used for the right rear physical area control of the intelligent networked car. The physical functional area adopts a redundant solution. In detail, the left front area control module 6 is connected to the right front area control module 8, and the left rear area control module 7 is connected to the right rear area control module 9. The regional control module integrates ECU (Electronic Control Unit), sensors and actuators, and has regional I / O interface, regional power distribution and regional data I / O functions. Regional power distribution provides intelligent management services for the power consumption of equipment in smart connected vehicles, including strategies such as power collection and power management, and also provides functions such as overcurrent and overvoltage detection and high-voltage power management. As a small-scale integrated data transceiver conversion interface, regional data I / O can complete regional data processing, and then interact with the processed data with the central computing platform 1 and the data center module 5. The ECUs in the physical area can achieve functional decoupling and cross-domain sharing. Through the setting of regional controllers, the integration and integration of ECUs can be achieved, reducing the number of ECUs in the whole vehicle. The regional control module also integrates intelligent power distribution technology, which can realize local power distribution and intelligent power management of equipment. It can also perform device abstraction and atomic service definition to support software and hardware separation and decoupling, and realize communication gateway functions, supporting CAN / LIN (Local Interconnect Network) / Ethernet message conversion and routing forwarding. In detail, the left front area control module 6 is also used for the low-voltage power supply control, intelligent fuse box control and pedal control of the intelligent connected vehicle; the left rear area control module 7 is also used for the charging control, cabin ventilation control and body accessory control of the intelligent connected vehicle; the right front area control module 8 is also used for the intelligent power distribution, motor control, battery management system control and thermal management system control of the intelligent connected vehicle; the right rear area control module 9 is also used for the air conditioning control, lighting control and door and window control of the intelligent connected vehicle.

[0066] To summarize, the present application discloses an electronic and electrical architecture applied to intelligent connected vehicles. Compared with the traditional five domains of intelligent driving, intelligent cockpit, body, chassis, and power, this electronic and electrical architecture deploys a data center on a central computing platform, which can uniformly manage the massive data generated under the current Ethernet transmission, standardize the interaction of data of each functional module, and adopt a high-efficiency redundancy solution to solve the communication redundancy problem caused by centralized control in the prior art. It greatly improves the efficiency of the overall operation of the vehicle and the realization of the overall function, and is safer and more reliable. The design meets the technical requirements of intelligent driving, new energy vehicle control, intelligent cockpit and cloud interaction.

[0067] Those skilled in the art will understand that the accompanying drawings are only schematic diagrams of an embodiment, and the modules or processes in the accompanying drawings are not necessarily necessary for implementing the present application. In addition, the modules in the devices in the embodiments may be distributed in the devices in the embodiments according to the description of the embodiments, or may be changed accordingly and located in one or more devices different from the present embodiments. The modules in the above embodiments may be combined into one module, or may be further split into multiple sub-modules.

[0068] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An electronic and electrical architecture applied to an intelligent connected vehicle, characterized in that: The electronic and electrical architecture includes a central computing platform and a regional control module. The central computing platform is integrated with an autonomous driving module, a vehicle control center module, an interactive center module and a data center module which are interconnected in pairs; the autonomous driving module is used for the intelligent driving control of the intelligent connected vehicle; the vehicle control center module is used for the power control, chassis control, body control and redundancy control of the intelligent connected vehicle; the interactive center module is used for the human-computer interaction of the intelligent connected vehicle, and for the communication and interactive control of the intelligent connected vehicle; the data center module is used for data customization processing and data storage of multi-source heterogeneous data of the intelligent connected vehicle, and is used for cloud interaction of the intelligent connected vehicle; The regional control module includes a left front regional control module, a left rear regional control module, a right front regional control module, and a right rear regional control module, which are respectively connected to the central computing platform, and the left front regional control module is connected to the right front regional control module, and the left rear regional control module is connected to the right rear regional control module; the left front regional control module is used for the left front physical area control of the intelligent connected vehicle; the left rear regional control module is used for the left rear physical area control of the intelligent connected vehicle; the right front regional control module is used for the right front physical area control of the intelligent connected vehicle; and the right rear regional control module is used for the right rear physical area control of the intelligent connected vehicle.

2. The electronic and electrical architecture for intelligent connected vehicles according to claim 1, characterized in that: The autonomous driving module includes a vehicle decision-making unit, a path planning unit and an AI training unit; the vehicle decision-making unit is used to make driving decisions based on vehicle perception signals and based on the autonomous driving model, and output decision execution instructions; the path planning unit is used to perform travel planning based on the path planning algorithm according to the cloud data interacting with the cloud control platform, and output a transportation travel plan; the AI ​​training unit is used to iteratively train the autonomous driving model and update the model parameters according to user driving data.

3. The electronic and electrical architecture for intelligent connected vehicles according to claim 2, characterized in that: The path planning algorithm includes: In the initialization phase of the random rapid search tree RRT, the node set and edge set of the RRT tree are initialized, the initialized node set is the initial state of the tree node, and the initialized edge set is empty; In the growth stage of the RRT tree, the random sampling and expansion step is repeatedly performed until the expanded new node is the travel destination, wherein the random sampling and expansion step includes: randomly sampling the map of the environment in which the intelligent connected vehicle is located, and when the sampling point falls in the safe area of ​​the map, selecting the node closest to the sampling point in the current RRT tree, and expanding the node toward the sampling point, and if the trajectory generated after adding the node does not collide with the obstacle, then the trajectory is added to the edge set, and the node is added to the node set.

4. The electronic and electrical architecture for intelligent connected vehicles according to claim 1, characterized in that: The vehicle control center module includes a power control unit, a chassis control unit, a body control unit and a redundant control unit; the power control unit is used for the whole vehicle control, drive shaft control, engine control, transmission control, whole vehicle mode control and cruise control of the intelligent connected vehicle; the chassis control unit is used for the steering control and braking control of the intelligent connected vehicle; the body control unit is used for the physical area control and whole vehicle wake-up and sleep control of the intelligent connected vehicle; the redundant control unit is used for the redundant control between the left front area control module and the right front area control module, the redundant control between the left rear area control module and the right rear area control module, and for the redundant control between the automatic driving module, the vehicle control center module, the interactive center module and the data center module.

5. The electronic and electrical architecture for intelligent connected vehicles according to claim 1, characterized in that: The interactive center module includes an intelligent gateway unit, an intelligent cockpit unit, a remote interaction unit and a communication control unit; the intelligent gateway unit is used to make vehicle driving decisions for the intelligent connected vehicle and is used for wireless communication control of the intelligent connected vehicle; the intelligent cockpit unit is used for human-machine interface HMI control and multimedia control of the intelligent connected vehicle, and performs driving behavior simulation based on multimodal data in the cockpit; the remote interaction unit is used for OTA system control of the intelligent connected vehicle; and the communication control unit is used for in-vehicle communication control and network control of the intelligent connected vehicle.

6. The electronic and electrical architecture for intelligent connected vehicles according to claim 1, characterized in that: The data center module includes a customized processing unit, a data storage unit and a cloud interaction unit; the customized processing unit is used to perform standardized customized processing on the multi-source heterogeneous data to obtain processed standardized data; The data storage unit is used to store the standardized data and the cached data during the interaction between the intelligent connected vehicle and the cloud control platform; the cloud interaction unit is used for data transmission between the customized processing unit and the cloud control platform.

7. The electronic and electrical architecture for intelligent connected vehicles according to claim 6, characterized in that: The standardized customization processing includes data preprocessing, preset format conversion processing, feature extraction processing, data fusion processing and data compression processing; The data preprocessing includes: performing data enhancement, filtering and normalization processing on the multi-source heterogeneous data, and converting the data storage format of the multi-source heterogeneous data; The preset format conversion process includes: classifying the multi-source heterogeneous data according to the customized data type, and converting each type of the multi-source heterogeneous data after the data classification into a standardized data format, wherein the customized data type includes a visual information data type, a vehicle behavior data type, a communication data type, a positioning and radar data type, a fault alarm data type, a cloud interaction data type, and a driver behavior data type; The feature extraction process includes: extracting HOG features, LBP features, and Haar features from the multi-source heterogeneous data based on the OpenCV algorithm library and convolutional neural network, and / or extracting targets from the multi-source heterogeneous data using a target detection extraction algorithm; The data fusion processing includes: performing multi-sensor fusion on the multi-source heterogeneous data based on a random fusion algorithm and an artificial intelligence fusion algorithm, wherein the random fusion algorithm includes a weighted average method, a Kalman filter method, a multi-Bayesian estimation method, a D-S evidence reasoning method and a production rule, and the artificial intelligence fusion algorithm includes a fuzzy logic thrust algorithm and an artificial neural network algorithm; The data compression processing includes: performing PCA dimensionality reduction processing on the multi-source heterogeneous data, or acquiring and reconstructing sparse signals based on compressed sensing technology; at the same time, using an image reconstruction algorithm to restore and enhance the multi-source heterogeneous data of the visual information data class.

8. The electronic and electrical architecture for intelligent connected vehicles according to claim 7, characterized in that: The multi-source heterogeneous data of the visual information data class is subjected to data fusion processing, including: Obtain visual image data collected by the camera, point cloud data collected by the laser radar, depth radar image data collected by the millimeter wave radar, and close-range image data collected by the ultrasonic radar; According to the weights of different environmental background influencing factors of the visual image data in the application scenario, the visual image data of different environments are weightedly fused to obtain visual fusion data, and the visual fusion data is fused with the point cloud data, the depth radar image data, and the close-range image data to obtain a fused output image; wherein the environmental background influencing factors include illumination factors, road marking line factors, road sign factors, and road obstacle factors, and the calculation formula of the fused output image is: Among them, A represents the fusion output image; u(x) represents visual image data; u(y) represents point cloud data; u(z) represents depth radar image data; u(l) represents close-range image data; n represents the total number of environmental background influencing factors, n=4; W1 represents the weight coefficient of the illumination factor, and its value is determined by the illumination level; W2 represents the weight coefficient of the road marking line factor, and its value is determined by the recognition rate of the road marking line; W3 represents the weight coefficient of the road sign factor, and its value is determined by the recognition rate of the road sign; W4 represents the weight coefficient of the road obstacle factor, and its value is determined by the distance of the obstacle.

9. The electronic and electrical architecture for intelligent connected vehicles according to claim 1, characterized in that: The left front area control module is also used for the low-voltage power supply control, intelligent fuse box control and pedal control of the intelligent connected vehicle; the left rear area control module is also used for the charging control, cabin ventilation control and body accessory control of the intelligent connected vehicle; the right front area control module is also used for the intelligent power distribution, motor control, battery management system control and thermal management system control of the intelligent connected vehicle; the right rear area control module is also used for the air conditioning control, lighting control and door and window control of the intelligent connected vehicle.

10. The electronic and electrical architecture for intelligent connected vehicles according to claim 1, characterized in that: The communication modes of the automatic driving module and the interactive center module are both Ethernet, and the communication mode of the vehicle control center module is CAN bus or CAN FD bus.

Citation Information

Cited By

  • Information interaction method of autonomous vehicle

    CN119389229A

  • An information interaction method for an autonomous driving vehicle

    CN119389229B