A highway high-level assisted driving system based on a true value system

Abstract

The application relates to a highway high-level auxiliary driving system based on a true value system, which comprises an ADAS domain controller, wherein a perception module is used for receiving point cloud data information of a driving road of a vehicle, image data information of the driving road of the vehicle, data information of a position and an attitude of the vehicle, and outputting data information of a perception result of vehicle auxiliary driving; and a rule control module is connected with the perception module, used for receiving the data information of the perception result of the vehicle auxiliary driving, adopting a rule control algorithm to represent vehicle auxiliary driving decision, and obtaining data information of a decision of the vehicle auxiliary driving. The application not only reduces high vehicle high-level auxiliary driving cost, improves high-level auxiliary driving system use efficiency, but also relieves driver fatigue caused by long-distance highway driving and reduces traffic accident sending.

Description

Technical Field

[0001] This invention relates to the field of vehicle driver assistance technology, and in particular to a high-level driver assistance system for highways based on a truth system. Background Technology

[0002] A truth value system is a data acquisition system composed of vehicle-mounted sensors such as millimeter-wave radar, lidar, and high-precision combined inertial navigation, along with efficient data recording equipment. Because it can process data to produce data (truth values) with higher reliability than the sensors being tested, truth value systems are often used to evaluate the performance of the sensors under test. Furthermore, based on the accuracy of the data acquisition, after cleaning, labeling, and data mining the truth value data, a natural driving scenario dataset can be formed, thereby building a natural driving scenario library.

[0003] With the continuous development of autonomous driving technology, more and more vehicles are being equipped with Advanced Driver Assistance Systems (ADAS). These systems help drivers better control the vehicle in complex traffic environments, improving driving safety and comfort. However, existing ADAS systems still have some problems in practical applications, such as insufficient perception accuracy and imperfect decision-making algorithms. Summary of the Invention

[0004] In view of the above problems, the present invention provides a highway advanced driver assistance system based on a truth value system, which not only reduces the overall cost of advanced driver assistance systems and improves the efficiency of advanced driver assistance systems, but also reduces driver fatigue caused by long-distance highway driving and reduces the occurrence of traffic accidents.

[0005] To achieve the above and other related objectives, the present invention provides the following technical solution:

[0006] A high-level advanced driver assistance system for highways based on a truth system, the system comprising:

[0007] The system includes a lidar, a camera, and a combined navigation system. The lidar is used to acquire point cloud data of the road the vehicle is traveling on in real time. The camera is used to acquire image data of the road the vehicle is traveling on in real time. The combined navigation system is used to acquire the vehicle's position and attitude data in real time.

[0008] The ADAS domain controller includes a perception module and a planning and control module. The perception module is used to receive point cloud data information of the road where the vehicle is driving, image data information of the road where the vehicle is driving, and data information of the vehicle's position and attitude, and outputs data information of the perception results of vehicle assisted driving. The planning and control module is connected to the perception module and is used to receive data information of the perception results of vehicle assisted driving, and to use a planning and control algorithm to represent the vehicle assisted driving decision to obtain data information of the vehicle assisted driving decision.

[0009] The upper part has a control signal interface, which is connected to the ADAS domain controller to transmit data information on vehicle assisted driving decisions to the vehicle.

[0010] Furthermore, the system also includes a vehicle-side receiving interface, which is connected to the upper structure control signal interface, for receiving data information on vehicle assisted driving decisions.

[0011] Furthermore, the system also includes a drive-by-wire chassis connected to the vehicle-side receiving interface, used to control and dynamically adjust the vehicle's chassis based on data information from the vehicle's assisted driving decisions.

[0012] Furthermore, the drive-by-wire chassis communicates and transmits data with the vehicle-side receiving interface via a chassis signal protocol.

[0013] Furthermore, the characterization of vehicle assisted driving decisions using the regulatory control algorithm includes:

[0014] M1. Based on the data information of the perception results of the vehicle assisted driving, construct a perception result dataset of the vehicle assisted driving, and divide it into a training set and a detection set of perception result data of the vehicle assisted driving.

[0015] M2. Input the training set of the perception results data of the vehicle assisted driving into the vehicle assisted driving decision model for training and learning, and obtain the trained vehicle assisted driving decision model;

[0016] M3. Based on the trained vehicle assisted driving decision model, input the vehicle assisted driving perception result dataset, represent the vehicle assisted driving decision, and obtain the data information of the vehicle assisted driving decision.

[0017] Furthermore, in step M3, the perception result data detection set of the vehicle assisted driving is input into the trained vehicle assisted driving decision model for detection, the parameters of the model are fine-tuned, and then the perception result dataset of the vehicle assisted driving is input to represent the vehicle assisted driving decision and obtain the data information of the vehicle assisted driving decision.

[0018] Furthermore, the data information for the vehicle assisted driving decision includes data information on the vehicle's desired steering angle, vehicle acceleration, vehicle braking torque, vehicle lateral offset, and vehicle longitudinal offset.

[0019] Furthermore, the upper structure control signal interface is used for the rapid loading, unloading, calibration, and debugging functions of advanced driver assistance systems, enabling point-to-point advanced driver assistance in highway scenarios before and after entering and exiting the highway.

[0020] Furthermore, the perception module is used to receive point cloud data information of the road the vehicle is traveling on, image data information of the road the vehicle is traveling on, and data information of the vehicle's position and attitude, and outputs the perception results of the vehicle's assisted driving, including:

[0021] Q1. Based on the point cloud data information of the vehicle driving road, the image data information of the vehicle driving road, and the data information of the vehicle's position and attitude, noise reduction processing is performed to obtain the processed point cloud data information of the vehicle driving road, the image data information of the vehicle driving road, and the data information of the vehicle's position and attitude.

[0022] Q2. Based on the processed point cloud data information of the vehicle's driving road, the image data information of the vehicle's driving road, and the data information of the vehicle's position and attitude, a weighted average algorithm is used to fuse the multi-sensor data of the vehicle to obtain the fused multi-sensor data information of the vehicle.

[0023] Q3. Based on the fused multi-sensor data of the vehicle, construct a perception result model for vehicle assisted driving, characterize the perception results of vehicle assisted driving, and obtain the data information of the perception results of vehicle assisted driving.

[0024] Furthermore, in step Q3, the fused multi-sensor data information of the vehicle is input into the perception result model of the vehicle assisted driving for training and learning. The weights and biases of the model are optimized to obtain the trained perception result model of the vehicle assisted driving.

[0025] The present invention has the following positive effects:

[0026] This invention forms a complete high-level driver assistance system hardware by employing sensors of appropriate precision, adding an ADAS domain controller, and reserving upper-mounted control signal interfaces. It fully utilizes the data acquisition and annotation functions of the truth system to comprehensively improve the training volume of large model data for the perception module and enhance the stability of perception and recognition. Combined with the control algorithm and chassis signal protocol, it achieves the goal of controlling the vehicle's high-level driver assistance system. This not only reduces the overall cost of high-level driver assistance systems and improves the efficiency of high-level driver assistance system use, but also reduces driver fatigue caused by long-distance highway driving and reduces the occurrence of traffic accidents. Attached Figure Description

[0027] Figure 1 This is a schematic diagram of the system framework of the present invention;

[0028] Figure 2 This is a flowchart illustrating the control algorithm of the present invention;

[0029] Figure 3 This is a schematic diagram illustrating the workflow of the sensing module of the present invention. Detailed Implementation

[0030] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0031] Example 1: As Figure 1 As shown, a high-level advanced driver assistance system for highways based on a truth-based system is disclosed, the system comprising:

[0032] The system includes a lidar, a camera, and a combined navigation system. The lidar is used to acquire point cloud data of the road the vehicle is traveling on in real time. The camera is used to acquire image data of the road the vehicle is traveling on in real time. The combined navigation system is used to acquire the vehicle's position and attitude data in real time.

[0033] The ADAS domain controller includes a perception module and a planning and control module. The perception module is used to receive point cloud data information of the road where the vehicle is driving, image data information of the road where the vehicle is driving, and data information of the vehicle's position and attitude, and outputs data information of the perception results of vehicle assisted driving. The planning and control module is connected to the perception module and is used to receive data information of the perception results of vehicle assisted driving, and to use a planning and control algorithm to represent the vehicle assisted driving decision to obtain data information of the vehicle assisted driving decision.

[0034] The upper part has a control signal interface, which is connected to the ADAS domain controller to transmit data information on vehicle assisted driving decisions to the vehicle.

[0035] In this embodiment, the system further includes a vehicle-side receiving interface connected to the upper structure control signal interface, used to receive data information for vehicle assisted driving decisions.

[0036] In this embodiment, the system further includes a drive-by-wire chassis connected to the vehicle-side receiving interface, used to control and dynamically adjust the vehicle chassis based on data information from the vehicle's assisted driving decisions.

[0037] In this embodiment, the drive-by-wire chassis communicates and transmits data with the vehicle-side receiving interface via a chassis signal protocol.

[0038] In this embodiment, the characterization of vehicle assisted driving decisions using a regulatory algorithm includes:

[0039] M1. Based on the data information of the perception results of the vehicle assisted driving, construct a perception result dataset of the vehicle assisted driving, and divide it into a training set and a detection set of perception result data of the vehicle assisted driving.

[0040] M2. Input the training set of the perception results data of the vehicle assisted driving into the vehicle assisted driving decision model for training and learning, and obtain the trained vehicle assisted driving decision model;

[0041] M3. Based on the trained vehicle assisted driving decision model, input the vehicle assisted driving perception result dataset, represent the vehicle assisted driving decision, and obtain the data information of the vehicle assisted driving decision.

[0042] In this embodiment, in step M3, the perception result data detection set of the vehicle assisted driving is input into the trained vehicle assisted driving decision model for detection, the parameters of the model are fine-tuned, and then the perception result dataset of the vehicle assisted driving is input to represent the vehicle assisted driving decision and obtain the data information of the vehicle assisted driving decision.

[0043] In this embodiment, the data information for the vehicle assisted driving decision includes data information on the vehicle's desired turning angle, vehicle acceleration, vehicle braking torque, vehicle lateral offset, and vehicle longitudinal offset.

[0044] In this embodiment, the upper structure control signal interface is used for the rapid loading, unloading, calibration, and debugging functions of advanced driver assistance systems, enabling point-to-point advanced driver assistance in highway scenarios before and after entering and exiting the highway.

[0045] In this embodiment, the perception module is used to receive point cloud data information of the road the vehicle is traveling on, image data information of the road the vehicle is traveling on, and data information of the vehicle's position and attitude. The data information outputting the perception results of the vehicle's assisted driving includes:

[0046] Q1. Based on the point cloud data information of the vehicle driving road, the image data information of the vehicle driving road, and the data information of the vehicle's position and attitude, noise reduction processing is performed to obtain the processed point cloud data information of the vehicle driving road, the image data information of the vehicle driving road, and the data information of the vehicle's position and attitude.

[0047] Q2. Based on the processed point cloud data information of the vehicle's driving road, the image data information of the vehicle's driving road, and the data information of the vehicle's position and attitude, a weighted average algorithm is used to fuse the multi-sensor data of the vehicle to obtain the fused multi-sensor data information of the vehicle.

[0048] Q3. Based on the fused multi-sensor data of the vehicle, construct a perception result model for vehicle assisted driving, characterize the perception results of vehicle assisted driving, and obtain the data information of the perception results of vehicle assisted driving.

[0049] In this embodiment, in step Q3, the fused multi-sensor data information of the vehicle is input into the perception result model of the vehicle assisted driving for training and learning. The weights and biases of the model are optimized to obtain the trained perception result model of the vehicle assisted driving.

[0050] Example 2: Based on the highway advanced driver assistance system based on the truth system in Example 1, the present invention will be further described and explained below.

[0051] A high-level advanced driver assistance system for highways based on a truth system, the system comprising:

[0052] The system includes a lidar, a camera, and a combined navigation system. The lidar is used to acquire point cloud data of the road the vehicle is traveling on in real time. The camera is used to acquire image data of the road the vehicle is traveling on in real time. The combined navigation system is used to acquire the vehicle's position and attitude data in real time.

[0053] The ADAS domain controller includes a perception module and a planning and control module. The perception module is used to receive point cloud data information of the road where the vehicle is driving, image data information of the road where the vehicle is driving, and data information of the vehicle's position and attitude, and outputs data information of the perception results of vehicle assisted driving. The planning and control module is connected to the perception module and is used to receive data information of the perception results of vehicle assisted driving, and to use a planning and control algorithm to represent the vehicle assisted driving decision to obtain data information of the vehicle assisted driving decision.

[0054] The upper part has a control signal interface, which is connected to the ADAS domain controller to transmit data information on vehicle assisted driving decisions to the vehicle.

[0055] In this embodiment, the truth system collects environmental and motion data through multiple sensors (LiDAR, camera, and integrated navigation). After the data is collected by an industrial control computer, it is cleaned (noise and redundancy are removed) and labeled (semantic information is assigned to the data) in sequence. Finally, it is used for perception training to build an accurate environmental perception model, providing reliable truth data support for scenarios such as advanced driver assistance systems, and realizing a closed-loop process from multi-source collection to intelligent training.

[0056] In this embodiment, the advanced driver assistance system (ADAS) constructs a complete closed loop of "perception-decision-execution". The front end deploys multiple source sensors: n lidars emit laser beams to generate 3D point clouds, accurately capturing the spatial structure of surrounding objects; n cameras acquire visual images, providing texture and semantic information to assist in recognizing traffic signs and other elements; and a combined navigation system integrates GNSS and IMU to output vehicle pose, solving the problem of positioning continuity in scenarios with obstructed satellite signals. The multiple sensors complement each other, covering the environmental and self-state perception needs.

[0057] Data is aggregated to the ADAS domain controller, where the perception module first fuses and processes the multi-source data. Algorithms are used to achieve feature matching and spatiotemporal alignment, constructing a unified environmental perception model to identify obstacles, lanes, and traffic participants, outputting high-precision perception results. Next, the planning and control module, combined with preset strategies such as adaptive cruise control and lane keeping, plans the driving path and translates it into precise control commands for throttle, brakes, and steering. Finally, through the vehicle interface, it connects to the vehicle execution layer, instructing the chassis and powertrain to perform actions while simultaneously providing feedback on vehicle status. This ensures dynamic optimization of control strategies and safety redundancy, supporting the collaborative operation of L2+ level advanced driver assistance functions.

[0058] In this embodiment, data acquisition involves LiDAR, camera, and integrated navigation acquiring point cloud data, image data, and position and attitude data around the vehicle, respectively.

[0059] Data preprocessing: Preprocessing the collected data, such as noise reduction and filtering.

[0060] Data fusion: The preprocessed data is input into the perception module, and the perception results of the vehicle's surrounding environment are generated through the data fusion algorithm.

[0061] 4. Decision generation: Based on the perception results, the regulation and control module uses a regulation and control algorithm to generate assisted driving decisions for the vehicle.

[0062] Control signal transmission: The generated decision data is transmitted to the vehicle control system through the upper structure control signal interface to realize vehicle control.

[0063] In this embodiment, the perception module is one of the core components of the invention. Its main function is to fuse data from multiple sensors to generate a perception result of the vehicle's surrounding environment. The design of the perception module is as follows:

[0064] Data fusion algorithm: The Kalman filter algorithm is used to fuse data from LiDAR, cameras, and integrated navigation. The Kalman filter algorithm can effectively process multi-source data and improve the accuracy of perception results.

[0065] Object detection: Using deep learning algorithms to detect objects in image data captured by cameras, identifying targets such as vehicles, pedestrians, and obstacles.

[0066] Lane detection: Lane detection algorithms based on the Sobel and Roberts operators are used to extract lane information from image data.

[0067] The present invention also provides a computer-readable storage medium storing a computer program programmed or configured to perform any of the truth-based advanced driver assistance methods for highways.

[0068] Any references to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0069] In summary, this invention not only reduces the high cost of advanced driver assistance systems (ADAS) and improves the efficiency of ADAS, but also reduces driver fatigue caused by long-distance highway driving and decreases the occurrence of traffic accidents.

[0070] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A high-level advanced driver assistance system for highways based on a truth-based system, characterized in that, The system includes: The system includes a lidar, a camera, and a combined navigation system. The lidar is used to acquire point cloud data of the road the vehicle is traveling on in real time. The camera is used to acquire image data of the road the vehicle is traveling on in real time. The combined navigation system is used to acquire the vehicle's position and attitude data in real time. The ADAS domain controller includes a perception module and a planning and control module. The perception module is used to receive point cloud data information of the road where the vehicle is driving, image data information of the road where the vehicle is driving, and data information of the vehicle's position and attitude, and outputs data information of the perception results of vehicle assisted driving. The planning and control module is connected to the perception module and is used to receive data information of the perception results of vehicle assisted driving, and to use a planning and control algorithm to represent the vehicle assisted driving decision to obtain data information of the vehicle assisted driving decision. The upper part has a control signal interface, which is connected to the ADAS domain controller to transmit data information on vehicle assisted driving decisions to the vehicle. The characterization of vehicle assisted driving decisions using the rule control algorithm includes: M1. Based on the data information of the perception results of the vehicle assisted driving, construct a perception result dataset of the vehicle assisted driving, and divide it into a training set and a detection set of perception result data of the vehicle assisted driving. M2. Input the training set of the perception results data of the vehicle assisted driving into the vehicle assisted driving decision model for training and learning, and obtain the trained vehicle assisted driving decision model; M3. Based on the trained vehicle assisted driving decision model, input the vehicle assisted driving perception result dataset, represent the vehicle assisted driving decision, and obtain the data information of the vehicle assisted driving decision.

2. The highway high-level assisted driving system based on a truth system according to claim 1, characterized in that, The system also includes a vehicle-side receiving interface, which is connected to the upper structure control signal interface, for receiving data information on vehicle assisted driving decisions.

3. The highway advanced driver assistance system based on a truth system according to claim 2, characterized in that, The system also includes a drive-by-wire chassis connected to the vehicle-side receiving interface, used to control and dynamically adjust the vehicle's chassis based on data information from the vehicle's assisted driving decisions.

4. The highway advanced driver assistance system based on a truth system according to claim 3, characterized in that: The drive-by-wire chassis communicates and transmits data with the vehicle-side receiving interface via a chassis signal protocol.

5. The highway high-level driver assistance system based on a truth system according to claim 1, characterized in that, In step M3, the perception result data detection set of the vehicle assisted driving is input into the trained vehicle assisted driving decision model for detection, the parameters of the model are fine-tuned, and then the perception result dataset of the vehicle assisted driving is input to represent the vehicle assisted driving decision and obtain the data information of the vehicle assisted driving decision.

6. The highway advanced driver assistance system based on a truth system according to claim 1, characterized in that: The data information for vehicle-assisted driving decision-making includes data information on the vehicle's desired steering angle, vehicle acceleration, vehicle braking torque, vehicle lateral offset, and vehicle longitudinal offset.

7. The highway advanced driver assistance system based on a truth system according to claim 1, characterized in that: The upper structure control signal interface is used for the rapid loading, unloading, calibration, and debugging of advanced driver assistance systems, enabling point-to-point advanced driver assistance in highway scenarios before and after entering and exiting the highway.

8. The high-level advanced driver assistance system for highways based on a truth system according to claim 1, characterized in that, The perception module is used to receive point cloud data information of the road where the vehicle is traveling, image data information of the road where the vehicle is traveling, and data information of the vehicle's position and attitude. The data information outputting the perception results of the vehicle's assisted driving includes: Q1. Based on the point cloud data information of the vehicle driving road, the image data information of the vehicle driving road, and the data information of the vehicle's position and attitude, noise reduction processing is performed to obtain the processed point cloud data information of the vehicle driving road, the image data information of the vehicle driving road, and the data information of the vehicle's position and attitude. Q2. Based on the processed point cloud data information of the vehicle's driving road, the image data information of the vehicle's driving road, and the data information of the vehicle's position and attitude, a weighted average algorithm is used to fuse the multi-sensor data of the vehicle to obtain the fused multi-sensor data information of the vehicle. Q3. Based on the fused multi-sensor data of the vehicle, construct a perception result model for vehicle assisted driving, characterize the perception results of vehicle assisted driving, and obtain the data information of the perception results of vehicle assisted driving.

9. The highway advanced driver assistance system based on a truth system according to claim 8, characterized in that, In step Q3, the fused multi-sensor data information of the vehicle is input into the perception result model of vehicle assisted driving for training and learning. The weights and biases of the model are optimized to obtain the trained perception result model of vehicle assisted driving.

Images