Chassis electronic and electrical architecture of vehicle and environment sensing method of chassis electronic and electrical architecture

Abstract

The invention discloses a chassis electronic and electrical architecture of a vehicle and an environment sensing method of the chassis electronic and electrical architecture, and relates to the technical field of automatic driving. The chassis electronic and electrical architecture comprises a central computing platform, an Ethernet switch, an intelligent antenna layer, a sensor layer and an area controller layer, the central computing platform is connected with the Ethernet switch; the Ethernet switch is connected with the regional controller layer; the front area controller is connected with the first-class perception sensing module; the middle area controller is connected with the second type of perception sensing module; the rear area controller is connected with the third-class perception sensing module; the central computing platform comprises a data initialization thread, an algorithm thread and a control thread; the regional controller layer obtains various control instructions through the Ethernet switch; various control instructions and initial sensor data are mutually transmitted through the intelligent antenna layer, and the chassis electronic and electrical architecture design of the vehicle is optimized.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a chassis electronic and electrical architecture of a vehicle and an environmental perception method for the chassis electronic and electrical architecture. Background Art

[0002] In the field of intelligent driving or outdoor mobile robots, the development of environmental perception technology is crucial. In existing technologies, common environmental perception systems usually rely on multiple sensors, such as cameras, lidars, and IMUs, which are connected to a central computing platform through wiring harnesses.

[0003] However, with the development of intelligent driving technology, higher requirements are put forward for the real-time transmission of sensor data, the reliability of the system and the complexity of wiring. Therefore, the current technical problems mainly include: First: the complexity and reliability of the wiring harness. The traditional wired connection method makes the system wiring complicated, which not only increases the difficulty of installation and maintenance, but also reduces the reliability of the system. Problems such as broken wiring harnesses or poor contact can easily lead to data transmission interruptions and affect system performance. Second, data transmission efficiency. With the increase in the number of sensors, the existing data transmission methods have gradually shown bottlenecks in bandwidth and real-time performance, and cannot meet the requirements of efficient multi-sensor data fusion and processing. Third, the hardware integration is low. In the existing chassis electronic and electrical architecture, various sensors and controllers are installed in a scattered manner, lacking a unified management and coordination mechanism, resulting in low system integration and difficulty in achieving collaborative work and unified scheduling.

[0004] Based on the above problems, how to optimize the chassis electronic and electrical architecture so that it can avoid low operating efficiency when performing complex environmental perception and data fusion and ultimately improve the environmental perception capability of the chassis electronic and electrical architecture is a problem that needs to be solved urgently. Summary of the invention

[0005] The purpose of this application is to provide a chassis electronic and electrical architecture of a vehicle and an environmental perception method for the chassis electronic and electrical architecture, which can solve the problem of low operating efficiency caused by low integration of the chassis electronic and electrical architecture in complex environments, and thus low environmental perception ability of the chassis electronic and electrical architecture.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In the first aspect, the present application provides a chassis electronic and electrical architecture of a vehicle, including: a central computing platform, an Ethernet switch, a smart antenna layer, a sensor layer and a regional controller layer; the central computing platform is connected to the Ethernet switch; the sensor layer includes a first type of perception sensor module, a second type of perception sensor module and a third type of perception sensor module; the sensor layer is used to output initial sensor data; the Ethernet switch is connected to the regional controller layer; the regional controller layer is used to filter, compress and analyze the initial sensor data, generate sensor data, and send it to the central computing platform through the Ethernet switch; the regional controller layer includes a front regional controller, a middle regional controller and a rear regional controller; the front regional controller is connected to the first type of perception sensor module; the middle regional controller is connected to the second type of perception sensor module; the rear regional controller is connected to the third type of perception sensor module; the central computing platform The platform includes a data initialization thread, an algorithm thread and a control thread, wherein the data initialization thread is used to preprocess and calibrate the sensor data to obtain initial data; the algorithm thread is used to perform environmental semantic segmentation, dynamic feature extraction, and synchronous positioning and mapping on the initial data in real time to generate an environmental map, and the environmental map is used to locate the vehicle; the control thread is used to generate various control instructions based on the environmental map and the sensor data; the regional controller layer obtains the various control instructions through the Ethernet switch; the various control instructions and the initial sensor data are transmitted to each other through the smart antenna layer; the various control instructions are used to control the working modes of various sensors in the sensor layer, so that the chassis electronic and electrical architecture of the vehicle can obtain the newly perceived initial sensor data in real time by controlling the working modes of various sensors in the sensor layer, and send the newly perceived initial sensor data to the central computing platform based on the smart antenna layer to output new control instructions.

[0008] In a second aspect, a method for environmental perception of a chassis electronic and electrical architecture of a vehicle is provided, comprising:

[0009] Based on the smart antenna layer, the initial sensor data of the acquired sensor layer is optimized to obtain the optimized initial sensor data, and the optimized initial sensor data is sent to the regional control layer; the optimized initial sensor data is filtered, compressed and analyzed by the regional control layer to generate sensor data, and the sensor data is transmitted to the central computing platform through the Ethernet switch; the sensor data is calculated by the central computing platform to generate various control instructions, and the various control instructions are sent to the regional controller layer through the Ethernet switch; based on the various control instructions, the working modes of various sensors of the sensor layer are controlled; by controlling the working modes of various sensors of the sensor layer, the newly perceived initial sensor data is acquired in real time, and based on the smart antenna layer, the newly perceived initial sensor data is sent to the central computing platform to output new various control instructions.

[0010] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0011] The present application provides a chassis electronic and electrical architecture of a vehicle and an environmental perception method of the chassis electronic and electrical architecture. The present application first integrates initial sensor data based on the sensor layer to provide support for intelligent driving perception functions. Then, the regional controller layer processes the initial sensor data through an Ethernet switch and transmits it to the central computing platform. The initial sensor is then processed in parallel through the three threads of the data initialization thread, algorithm thread and control thread of the central computing platform, so as to improve the computing power and processing efficiency of the computing unit. Among them, the regional controller layer includes three parts: the front regional controller, the middle regional controller and the rear regional controller, so as to realize the centralized installation and unified management of the controller, and optimize the integration of the entire chassis electronic and electrical architecture. Among them, the various control instructions output by the control thread are sent to the regional controller layer; the regional controller layer and the perception sensor module layer interact with each other through the intelligent antenna layer to realize the wireless beam chassis architecture, further optimize the electronic and electrical architecture design, and reduce the use of wiring harnesses and the workload of chassis layout. Furthermore, through the various control instructions output by the central computing platform, the regional controller layer controls the working modes of various sensors in the sensor layer to obtain the newly perceived initial sensor data in real time, and then output new control instructions, ultimately improving the computing efficiency of the chassis electronic and electrical architecture, and thus improving the environmental perception capabilities of the entire chassis electronic and electrical architecture.

[0012] In addition, by connecting the front area controller to the first type of perception sensor module, the middle area controller to the second type of perception sensor module, and the rear area controller to the third type of perception sensor module, this design effectively avoids the allocation of computing resources being concentrated on a single module, which in turn easily leads to computing bottlenecks and low operating efficiency. Ultimately, it improves the computing power and processing efficiency of the computing unit, ensuring the efficient operation and stable performance of the system in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, 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.

[0014] Figure 1 A schematic diagram of the chassis electronic and electrical architecture of a vehicle provided in an embodiment of the present application.

[0015] Figure 2 It is a schematic diagram of the overall structure of the chassis electronic and electrical architecture of a vehicle provided in an embodiment of the present application.

[0016] Figure 3 A schematic flow chart of a method for sensing the environment of a chassis electronic and electrical architecture of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] 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.

[0018] 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 in conjunction with the accompanying drawings and specific implementation methods.

[0019] like Figure 1 and Figure 2 As shown, the present application provides a chassis electronic and electrical architecture of a vehicle, including:

[0020] Central computing platform 1, Ethernet switch 2, smart antenna layer 3, sensor layer 4 and regional controller layer 5; the central computing platform 1 is connected to the Ethernet switch 2; the sensor layer 4 includes a first type of perception sensor module 41, a second type of perception sensor module 42 and a third type of perception sensor module 43; the sensor layer 4 is used to output initial sensor data; the Ethernet switch 2 is connected to the regional controller layer 5; the regional controller layer 5 is used to filter, compress and analyze the initial sensor data, generate sensor data, and send it to the central computing platform 1 through the Ethernet switch 2; the regional controller layer 5 includes a front regional controller 51, a middle regional controller 52 and a rear regional controller 53; the front regional controller 51 is connected to the first type of perception sensor module 41; the middle regional controller 52 is connected to the second type of perception sensor module 42; the rear regional controller 53 is connected to the third type of perception sensor module 43; the central computing Platform 1 includes a data initialization thread, an algorithm thread and a control thread, wherein the data initialization thread is used to preprocess and calibrate the sensor data to obtain initial data; the algorithm thread is used to perform environmental semantic segmentation, dynamic feature extraction, and synchronous positioning and mapping on the initial data in real time to generate an environmental map, and the environmental map is used to locate the vehicle; the control thread is used to generate various control instructions based on the environmental map and the sensor data; the regional controller layer 5 obtains the various control instructions through the Ethernet switch 2; the various control instructions and the initial sensor data are transmitted to each other through the smart antenna layer 3; the various control instructions are used to control the working modes of various sensors in the sensor layer 4, so that the chassis electronic and electrical architecture of the vehicle can obtain the newly perceived initial sensor data in real time by controlling the working modes of various sensors in the sensor layer 4, and send the newly perceived initial sensor data to the central computing platform 1 based on the smart antenna layer 3 to output new control instructions.

[0021] Among them, the central computing platform 1, as the core of the operation of the intelligent environmental perception algorithm, mainly completes the preprocessing and calibration of sensor information, data fusion, environmental perception and decision-making, and result output and control. This application is developed based on the vehicle chassis or outdoor mobile robot chassis, involving a large amount of processing data, a large computing load, and complex control logic. The Jetson Orin processor is used as the main control. The Jetson Orin processor is a high-performance, low-power 32-bit microprocessor automotive-grade MCU, equipped with a 2048-core NVIDIA Ampere architecture GPU with 64 Tensor Cores, which is widely used in the automotive control industry.

[0022] Specifically, the central computing platform contains three main threads, each of which is responsible for different data processing processes and functions.

[0023] First, the data initialization thread (running on the CPU) is responsible for acquiring and processing initial sensor data from various sensors, including surround view image fusion, lidar point cloud processing, and inertial measurement unit (IMU) data integration. The surround view image fusion strategy uses multi-sensor data fusion technology to fuse multiple sensor data into a unified environmental view. LiDAR point cloud data processing uses a time-varying weight strategy to ensure the accuracy of data in different environments. The IMU is used to accurately measure the vehicle's posture and acceleration.

[0024] Secondly, the algorithm thread (running on the GPU) is responsible for high-level data processing, including environmental semantic segmentation, dynamic feature extraction, and simultaneous localization and mapping (SLAM). Environmental semantic segmentation uses a deep learning model to classify and identify different environmental elements. Dynamic feature extraction uses machine learning algorithms to identify moving objects and their trajectories. Among them, the SLAM algorithm generates an environmental map in real time through sensor data and locates the vehicle. The algorithm thread uses the high-performance computing capabilities of the GPU to achieve real-time processing of complex algorithms.

[0025] Finally, the control thread processes the environment view and sensor data obtained after the algorithm thread processing to generate various control signals. Among them, each control signal includes dynamically adjusting the working mode of various sensors in the sensor layer 4 according to environmental changes to optimize data collection. The control thread communicates with the vehicle's actuator through the physical interface of the regional controller layer 5 to ensure the accurate execution of various control instructions.

[0026] The three threads transmit the sensor data obtained from the regional controller layer 5 to the central computing platform 1 through the Ethernet switch, and the central computing platform 1 then performs further comprehensive analysis and decision support to form a complete data processing and control closed loop to ensure the safe and efficient operation of the vehicle in complex environments.

[0027] The regional controller layer 5 is composed of front, middle and rear regional controllers, each of which is connected to the Ethernet switch 2 and is provided with 12V power by the vehicle power supply module 6. These controllers communicate with the Ethernet switch 2 via the MAC interface.

[0028] Specifically, the main function of the regional controller layer 5 is to pre-process the initial sensor data to prepare for the processing of the central computing platform 1, but not to duplicate the processing of the central computing platform. Specifically, the regional controller layer 5 needs to filter, compress and preliminarily analyze the data to reduce the amount of data transmission, improve transmission efficiency, and provide simplified data for subsequent in-depth analysis.

[0029] The data processing process of the regional controller layer 5 is specifically as follows:

[0030] aData filtering: Use a low-pass filtering algorithm to remove noise from the initial sensor data.

[0031] b Data compression: Apply data compression algorithms Huffman coding and downsampling to reduce the volume of initial sensor data.

[0032] cPreliminary analysis: Implement a simple edge detection algorithm to identify the outlines of objects in the image and estimate the object velocity using basic kinematic equations.

[0033] The zone controller layer 5 obtains initial sensor data from the connected sensor layer 4 (such as image, radar, IMU, etc.). Initial sensor data filtering is first performed to remove obvious noise and erroneous data. Then, the initial sensor data is compressed to reduce the data volume through effective coding techniques. On this basis, preliminary analysis is performed, such as identifying basic object contours, speed estimation, etc.

[0034] The regional controller layer 5 can ensure that the initial sensor data has been preliminarily processed before being transmitted to the central computing platform 1, reducing the computing burden of the central computing platform 1 and optimizing the overall system performance. This includes cleaning and compressing the initial sensor data to reduce bandwidth requirements and performing preliminary analysis to provide concise and useful information for in-depth processing by the central computing platform 1.

[0035] The above processing is performed on the embedded processor of the zone controller, ensuring that the initial sensor data is optimized and simplified before being transmitted to the central computing platform, thereby improving the efficiency and performance of the entire chassis electronic and electrical architecture.

[0036] In some embodiments, the first type of perception sensing module 41 includes multiple cameras; the multiple cameras are used to collect environmental image data around the vehicle; the second type of perception sensing module 42 includes a lidar; the lidar is used to collect spatial environmental data of the vehicle; the third type of perception sensing module 43 includes an inertial measurement unit; the inertial measurement unit is used to measure and report the vehicle's posture and acceleration data; the initial sensor data includes the environmental image data, the spatial environment data, and the vehicle's posture and acceleration data.

[0037] Among them, the perception sensor in the first type of perception sensing module 41 can be 6 monocular cameras with a 360° surround at the front, which are used to capture environmental image data; the second type of perception sensing module 42 has a laser radar to collect three-dimensional environmental data; the third type of perception sensing module 43 has an on-board IMU, which is used to obtain the vehicle's posture and acceleration data.

[0038] Specifically, the front area controller is connected to 6 monocular cameras, which mainly transmit high-resolution visual image data. These image data are used for environmental perception, such as pedestrian detection, lane keeping and traffic sign recognition. The lidar of the central area controller is used to transmit high-precision three-dimensional spatial data, mapping the surrounding environment in detail, and helping with obstacle detection and navigation. The inertial measurement unit in the rear area controller is used to transmit data about vehicle acceleration and direction, supporting vehicle stability and dynamic monitoring. These wirelessly transmitted data are of a wide variety, covering everything from basic mechanical control to advanced environmental perception and navigation, and are an integral part of the normal operation of autonomous vehicles. The smart antenna layer 3 plays a vital role in this process, not only ensuring the real-time transmission of initial sensor data, but also optimizing the transmission efficiency and security of data through its advanced signal processing capabilities.

[0039] In some embodiments, it also includes: an on-board power supply module 6; the on-board power supply module is used to convert high voltage into low voltage.

[0040] First, the central computing platform 1 uses 24V power supply due to its high-performance computing requirements to ensure stability and sufficient power. Second, the Ethernet switch 2 requires 12V power supply, so it can be powered directly from the 12V output of the on-board power supply module 6. The smart antenna layer 3 includes a smart antenna controller and an antenna array, which are powered by 12V.

[0041] For sensor layer 3, different sensors have different voltage requirements, but all operate between 5V and 24V. To simplify the design, 12V power supply is selected. The zone controller is usually powered between 5V and 12V, and also uses 12V power supply.

[0042] Specifically, to ensure the safety and reliability of the entire architecture, a centralized on-board power supply module 6 is designed to convert high voltage into the low voltage required by each module, and fuses and relays are used to protect each branch circuit from overload and short circuit. In addition, electromagnetic compatibility issues should be considered to ensure that all power lines are well shielded and grounded, and include voltage and current monitoring functions to monitor the system status in real time and perform fault diagnosis. Such a design can not only ensure that each component is properly powered, but also enhance the overall performance of the system.

[0043] In some embodiments, the second type of perception sensing module also includes a wire-controlled steering and braking control unit; the wire-controlled steering and braking control unit is used to generate a current operating status signal of the vehicle based on the spatial environment data; the current operating status signal includes a steering angle and a braking force; the third type of perception sensing module also includes a battery control unit and a motor control unit; the battery control unit is used to generate battery status information based on the posture and acceleration data of the vehicle; the battery status information includes a battery charge and a battery temperature; the motor control unit is used to generate motor operating data based on the posture and acceleration data of the vehicle; the initial sensor data also includes the current operating status signal, the battery status information and the motor operating data.

[0044] Among them, the functions of the wire-controlled steering unit and the brake control unit are to transmit signals about the current operating status of the vehicle, such as steering angle and braking force, which are used to perform precise vehicle control operations.

[0045] Among them, the function of the battery control unit is to transmit battery status information, such as power level and temperature, to ensure energy management of electric vehicles.

[0046] Among them, the function of the motor control unit is to transmit motor operation data for adjusting motor output to ensure optimal driving performance and energy efficiency.

[0047] The various control instructions also include chassis control and power supply control. Chassis control is used to adjust the direction and speed of the vehicle. Power supply control is used to ensure the stable power supply of the system to prevent system failure due to insufficient power.

[0048] In practical applications, chassis control is generated based on the current operating status signal and the vehicle's posture and acceleration data. The Model Predictive Control (MPC) algorithm is used to achieve precise chassis control. Power supply control is mainly based on battery status information and motor operation data. The Extended Kalman Filter (EKF) is used to estimate the battery health status, and the Power Management Algorithm (PMA) is used to schedule the power of the battery and the motor.

[0049] In some embodiments, the smart antenna layer 3 includes a smart antenna controller and an antenna array; the smart antenna layer is used to optimize the processing of the initial sensor data of the sensor layer based on the smart antenna controller using beamforming technology, generate optimized initial sensor data, and transmit the optimized sensor data to the regional controller layer through the antenna array.

[0050] Among them, the smart antenna layer 3 is used to establish a wireless communication connection. Among them, the role of the smart antenna controller is to adjust the working state of each antenna in the antenna array through an algorithm to optimize signal coverage and transmission effect. Through beamforming technology, the controller can guide the antenna array to transmit a focused signal beam, improve the signal's directionality and transmission distance, and thus improve communication quality in complex environments.

[0051] Among them, the smart antenna controller is mainly used to adjust and optimize the signal reception and transmission functions of the antenna array. The smart antenna layer 3 uses digital signal processing algorithms to enhance the signal reception quality and directional transmission capability. In terms of connection, the smart antenna controller is directly connected to the antenna array through Ethernet, and the efficiency and quality of wireless communication are significantly improved by accurately controlling the transmission and reception direction of the signal. The smart antenna controller uses complex signal processing algorithms to calculate the optimal antenna parameters in real time through adaptive beamforming and pattern optimization. The smart antenna controller adjusts the various units of the antenna array according to environmental changes, and achieves the best signal transmission through electrical phase adjustment and power control. The antenna array is arranged according to a certain geometric layout, so that the system can flexibly respond to signal requirements in different directions. This design not only improves the reliability and quality of the signal, but also effectively reduces interference and improves communication efficiency.

[0052] In some embodiments, the central computing platform 1 is connected to the Ethernet switch 2 via an Ethernet cable; the sensor layer 4, the regional controller layer 5 and the smart antenna layer 3 are all connected to the Ethernet switch 2 via Ethernet cables; the Ethernet switch 2 communicates with the regional controller layer 5 via a media access control interface.

[0053] In actual application, for the central computing platform 1, it is directly connected to the Ethernet switch 2 via a CAT7 Ethernet cable. This cable supports higher bandwidth and can effectively handle high-speed data transmission. When connecting, the IP settings need to be manually configured to ensure stable communication between devices without relying on DHCP.

[0054] In terms of switch configuration, use MGBE (Multi-Gigabit Ethernet) lines to connect the Ethernet switch to Jetson Orin for data transmission, and use MDIO / MDC lines for switch configuration. It is important to turn on the switch and configure the port settings before booting to ensure that the network settings are initialized correctly when the system starts.

[0055] Among them, for the Ethernet switch 2 and the regional controller layer 5, a wired Ethernet connection is used. The Cat 6a network cable can support a transmission speed of 10Gbps, which can not only ensure high-speed and stable data transmission, but also enhance the security and stability of the entire network system. It is crucial to ensure efficient and secure data communication between the regional controller and the Ethernet switch.

[0056] Among them, MAC (Medium Access Control Layer) is part of the data link layer in the OSI (Open Systems Interconnection Model) seven-layer model, which is responsible for managing and controlling how devices access shared transmission media. MAC is located in the lower half of the data link layer, and together with the LLC (Logical Link Control) layer, it constitutes the data link layer. During the MAC connection process, sensor data processing involves several key steps. First, when sending sensor data, MAC encapsulates the data packets of the upper layer protocol into frames, including adding MAC header information such as source address, destination address, and control information. When receiving sensor data, MAC decapsulates the frame, extracts the sensor data and hands it over to the upper layer protocol for processing. Secondly, MAC manages the access of network devices to the shared communication medium through the CSMA / CD or CSMA / CA mechanism to prevent data conflicts. The Ethernet physical layer (PHY) and MAC communicate through MDI to ensure the stability and accuracy of sensor data transmission on the physical medium. In Figure 2 In the connection shown, data is sent from the MAC interface of the central computing platform and transmitted to the PHY layer through the MDI interface. The PHY layer modulates the sensor data into electrical signals and transmits them through the ETH+ and ETH- connectors. The PHY layer on the receiving end transmits the sensor data back to the MAC through the MDI interface to complete the reception and decapsulation of the sensor data. The MAC is also responsible for frame error detection (such as CRC check) to ensure the integrity of the sensor data, and discards the error frame when an error is detected and requests the sensor data to be resent. The MAC manages the sensor data transmission rate and sends pause frames through flow control mechanisms (such as IEEE 802.3x flow control) to control the data flow rate on the sending end. Through these steps, the MAC and PHY layers work together to ensure the reliable transmission and processing of sensor data in the network.

[0057] Reference Figure 3 , provides an environment perception method for a chassis electronic and electrical architecture of a vehicle, comprising:

[0058] Step 101: Based on the smart antenna layer, the initial sensor data acquired from the sensor layer is optimized to obtain optimized initial sensor data, and the optimized initial sensor data is sent to the regional control layer.

[0059] Step 102: filtering, compressing and analyzing the optimized initial sensor data through the regional control layer to generate sensor data, and transmitting the sensor data to the central computing platform through the Ethernet switch;

[0060] Step 103: Calculate the sensor data through the central computing platform to generate various control instructions, and send the various control instructions to the regional controller layer through the Ethernet switch;

[0061] Step 104: Based on the control instructions, control the working modes of various sensors of the sensor layer;

[0062] Step 105: Acquire the newly perceived initial sensor data in real time by controlling the working modes of various sensors of the sensor layer, and send the newly perceived initial sensor data to the central computing platform based on the smart antenna layer to output various new control instructions.

[0063] In some embodiments, step 103 specifically includes:

[0064] Step 201: Preprocess and calibrate the sensor data to obtain initial data through the data initialization thread of the central computing platform.

[0065] Step 202: Perform environmental semantic segmentation, dynamic feature extraction, and synchronous positioning and mapping on the initial data in real time through the algorithm thread of the central computing platform to generate an environmental map.

[0066] Step 203: Generate the various control instructions based on the control thread of the central computing platform, the environmental map and the sensor data.

[0067] In some embodiments, step 201 specifically includes:

[0068] Step 301: adopt a surround view image fusion strategy to fuse the sensor data to generate an environment view.

[0069] Step 302: Use a time-varying weight strategy to process the sensor data to obtain lidar point cloud data; the initial data includes the environment view, the lidar point cloud data, and the vehicle's posture and acceleration data; wherein the vehicle's posture and acceleration data are obtained based on measurements of the inertial measurement unit of the sensor layer.

[0070] Step 202 specifically includes:

[0071] Step 401: Perform environment semantic segmentation on the environment view to obtain a view classification result.

[0072] Step 402: Dynamically extract features of the view classification results, the lidar point cloud data, and the posture and acceleration data of the vehicle through a machine learning algorithm, and obtain the environment map based on a simultaneous positioning and mapping algorithm.

[0073] This application implements a wireless beam chassis architecture through a central computing platform 1, a regional controller layer 5, and a smart antenna layer 3, and integrates various sensors such as cameras, lidars, and inertial measurement units (IMUs) to provide support for intelligent driving perception functions. The Ethernet interfaces of various sensors, regional controller layers 5, and smart antenna layers 3 in this application are connected to the Ethernet switch 2 of the central computing platform 1 through the vehicle Ethernet bus. Sensors in different areas of the chassis are powered by the vehicle power supply according to the principle of proximity. The regional controller layer 5 controls the corresponding sensors according to different working condition instructions, and transmits the initial sensor data to the central computing platform 1 through the vehicle Ethernet through the smart antenna layer 3. The central computing platform 1 receives sensor data and provides services for intelligent driving based on the environmental perception algorithm. At the same time, it separates the data initialization thread, algorithm thread, and control thread, and realizes parallel processing of the three parts, which can improve the computing power and processing efficiency of the computing unit.

[0074] This application optimizes the electronic and electrical architecture design, reduces the use of wiring harnesses and the workload of chassis layout, and further improves the computing power and processing efficiency of the computing unit through innovative parallel processing architecture design, ensuring the efficient operation and stable performance of the system in complex environments.

[0075] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the above method is implemented when the processor executes the computer program.

[0076] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the above method when executed by a processor.

[0077] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the above method when executed by a processor.

[0078] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0079] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRdM), magnetic random access memory (MRdM), ferroelectric random access memory (FRdM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RdM) or external cache memory, etc. By way of illustration and not limitation, RdM may be in various forms, such as static random access memory (SRdM) or dynamic random access memory (DRdM).

[0080] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0081] 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.

[0082] 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. A chassis electronic and electrical architecture of a vehicle, characterized in that: include: Central computing platform, Ethernet switch, smart antenna layer, sensor layer and regional controller layer; The central computing platform is connected to the Ethernet switch; The sensor layer includes a first type of perception sensing module, a second type of perception sensing module and a third type of perception sensing module; the sensor layer is used to output initial sensor data; The Ethernet switch is connected to the regional controller layer; the regional controller layer is used to filter, compress and analyze the initial sensor data, generate sensor data, and send it to the central computing platform through the Ethernet switch; the regional controller layer includes a front regional controller, a middle regional controller and a rear regional controller; the front regional controller is connected to the first type of perception sensor module; the middle regional controller is connected to the second type of perception sensor module; the rear regional controller is connected to the third type of perception sensor module; The central computing platform includes a data initialization thread, an algorithm thread and a control thread, wherein the data initialization thread is used to preprocess and calibrate the sensor data to obtain initial data; The algorithm thread is used to perform environmental semantic segmentation, dynamic feature extraction, and synchronous positioning and mapping on the initial data in real time to generate an environmental map, and the environmental map is used to locate the vehicle; the control thread is used to generate various control instructions based on the environmental map and the sensor data; The regional controller layer obtains the various control instructions through the Ethernet switch; The various control instructions and the initial sensor data are transmitted to each other through the smart antenna layer; the various control instructions are used to control the working modes of various sensors in the sensor layer, so that the chassis electronic and electrical architecture of the vehicle can obtain the newly perceived initial sensor data in real time by controlling the working modes of various sensors in the sensor layer, and send the newly perceived initial sensor data to the central computing platform based on the smart antenna layer to output new control instructions.

2. The chassis electronic and electrical architecture of a vehicle according to claim 1, characterized in that: The first type of perception sensor module includes a plurality of cameras; the plurality of cameras are used to collect environmental image data around the vehicle; the second type of perception sensor module includes a laser radar; the laser radar is used to collect spatial environmental data of the vehicle; the third type of perception sensor module includes an inertial measurement unit; the inertial measurement unit is used to measure and report the posture and acceleration data of the vehicle; The initial sensor data includes the environmental image data, the spatial environment data, and the posture and acceleration data of the vehicle.

3. The chassis electrical and electronic architecture of a vehicle according to claim 2, characterized in that: The second type of perception sensor module also includes a wire-controlled steering and braking control unit; the wire-controlled steering and braking control unit is used to generate a current operating state signal of the vehicle based on the spatial environment data; the current operating state signal includes a steering angle and a braking force; The third type of perception sensor module also includes a battery control unit and a motor control unit; The battery control unit is used to generate battery status information based on the posture and acceleration data of the vehicle; the battery status information includes battery power and battery temperature; The motor control unit is used to generate motor operation data based on the posture and acceleration data of the vehicle; The initial sensor data also includes the current operating state signal, the battery state information and the motor operating data.

4. The chassis electrical and electronic architecture of a vehicle according to claim 1, characterized in that: The smart antenna layer includes a smart antenna controller and an antenna array; The smart antenna layer is used to optimize and process the initial sensor data of the sensor layer based on the smart antenna controller by using beamforming technology, generate optimized initial sensor data, and transmit the optimized sensor data to the regional controller layer through the antenna array.

5. The chassis electrical and electronic architecture of a vehicle according to claim 1, characterized in that: The central computing platform is connected to the Ethernet switch via an Ethernet cable; The sensor layer, the zone controller layer and the smart antenna layer are all connected to the Ethernet switch via Ethernet cables; The Ethernet switch communicates with the zone controller layer via a media access control interface.

6. The chassis electrical and electronic architecture of a vehicle according to claim 1, characterized in that: It also includes: an on-board power supply module; the on-board power supply module is used to convert high voltage into low voltage.

7. A method for environmental perception of a chassis electronic and electrical architecture of a vehicle, characterized in that: include: Based on the smart antenna layer, the initial sensor data acquired from the sensor layer is optimized to obtain optimized initial sensor data, and the optimized initial sensor data is sent to the regional control layer; filtering, compressing and analyzing the optimized initial sensor data through the regional control layer to generate sensor data, and transmitting the sensor data to the central computing platform through an Ethernet switch; Calculate the sensor data through the central computing platform to generate various control instructions, and send the various control instructions to the regional controller layer through the Ethernet switch; Based on the control instructions, control the working modes of various sensors in the sensor layer; By controlling the working modes of various sensors in the sensor layer, the newly perceived initial sensor data is acquired in real time, and based on the smart antenna layer, the newly perceived initial sensor data is sent to the central computing platform to output various new control instructions.

8. The method for environmental perception of chassis electronic and electrical architecture according to claim 7, characterized in that: The sensor data is calculated by the central computing platform to generate various control instructions, including: Preprocessing and calibrating the sensor data to obtain initial data through the data initialization thread of the central computing platform; Through the algorithm thread of the central computing platform, the initial data is subjected to real-time environment semantic segmentation, dynamic feature extraction, and synchronous positioning and mapping to generate an environment map; The various control instructions are generated based on the control thread of the central computing platform, the environmental map and the sensor data.

9. The method for environmental perception of chassis electronic and electrical architecture according to claim 8, characterized in that: Preprocessing and calibrating the sensor data to obtain initial data through the data initialization thread of the central computing platform specifically includes: Using a surround view image fusion strategy to fuse the sensor data to generate an environment view; Processing the sensor data using a time-varying weight strategy to obtain lidar point cloud data; The initial data includes the environment view, the lidar point cloud data, and the vehicle's posture and acceleration data; wherein the vehicle's posture and acceleration data are measured based on the inertial measurement unit of the sensor layer.

10. The environment perception method of chassis electronic and electrical architecture according to claim 9, characterized in that: Through the algorithm thread of the central computing platform, the initial data is subjected to real-time environment semantic segmentation, dynamic feature extraction, and synchronous positioning and mapping to generate an environment map, specifically including: Performing environment semantic segmentation on the environment view to obtain a view classification result; The view classification results, the lidar point cloud data, and the posture and acceleration data of the vehicle are dynamically extracted by a machine learning algorithm, and the environment map is obtained based on a simultaneous positioning and mapping algorithm.

Images