Visual navigation and direction control system of automatic driving trolley

Abstract

The invention discloses a visual navigation and direction control system for an autonomous vehicle, and the system comprises a Beidou positioning receiver which is used for receiving a Beidou satellite signal and calculating the position and speed of the vehicle; the camera array comprises a front-view camera, a side-view camera and a rear-view camera and is used for capturing images of the surrounding environment of the vehicle; the laser radar is used for measuring distances and contours of surrounding objects; and the radar system is used for detecting long-distance objects and speed. The high-precision positioning service of the Beidou satellite navigation system is utilized, the centimeter-level positioning precision is provided, and the stable positioning performance can be kept even in a complex environment; an advanced sensor fusion technology is adopted, data of a camera, a laser radar, a radar and an ultrasonic sensor are integrated, and the accuracy and robustness of data processing are improved; in combination with a visual navigation and processing technology, accurate detection, identification, tracking and semantic segmentation of a target in a complex traffic scene are realized, and adaptability and accuracy of visual processing are improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving, and in particular to a visual navigation and direction control system for an autonomous driving vehicle. Background Art

[0002] Autonomous driving technology refers to the technology that allows vehicles to autonomously perceive the environment, make decisions and perform driving tasks without the need for direct human driver operation. The development of autonomous driving technology is of great significance to improving traffic safety, reducing traffic congestion, and reducing energy consumption and environmental pollution.

[0003] At present, autonomous driving technology mainly relies on devices such as global positioning systems, inertial measurement units, cameras, lidar, radar and ultrasonic sensors. However, the existing technology has the following disadvantages:

[0004] GPS positioning accuracy is limited, especially in complex environments such as urban canyons, where signal obstruction and multipath effects can lead to increased positioning errors;

[0005] The sensor data fusion algorithm is complex, requires processing a large amount of data, and has unstable performance under different weather and lighting conditions;

[0006] Visual processing technology is easily affected by occlusion and lighting changes in complex traffic scenes, resulting in reduced accuracy of target detection and recognition;

[0007] Path planning algorithms are difficult to adjust in real time in dynamic environments and are prone to decision-making errors in complex traffic scenarios;

[0008] The vehicle control system lacks response speed and accuracy when performing complex operations such as emergency obstacle avoidance. Summary of the invention

[0009] The purpose of the present invention is to provide a visual navigation and direction control system for an autonomous driving vehicle to solve the problems raised in the above-mentioned background technology.

[0010] To achieve the above object, the present invention provides the following technical solutions:

[0011] The visual navigation and direction control system of the autonomous driving car includes

[0012] Beidou positioning receiver, used to receive Beidou satellite signals and calculate the vehicle's position and speed;

[0013] a camera array, including forward-looking, side-looking, and rear-looking cameras, for capturing images of the vehicle's surroundings;

[0014] LiDAR, which measures the distance and outline of surrounding objects;

[0015] radar systems to detect objects and speed at long distances;

[0016] Ultrasonic sensors for close-range obstacle detection;

[0017] A central processing unit, which processes sensor data and executes control algorithms;

[0018] A storage unit for storing high-precision map data and software programs;

[0019] Communication module, used for data exchange with external systems;

[0020] Actuators, including the steering motor, throttle controller, and brakes, perform the actual control of the vehicle.

[0021] In the present invention, the Beidou positioning receiver also includes a differential receiving unit and a real-time dynamic processing unit, which are used to provide centimeter-level positioning accuracy.

[0022] In the present invention, the camera array also includes an image processing unit for processing captured images and performing target detection, recognition, tracking and semantic segmentation.

[0023] In the present invention, the laser radar also includes a data processing unit for processing measurement data and generating an environment model.

[0024] In the present invention, the radar system further comprises a target tracking unit, which is used to track the detected object and predict its motion trajectory.

[0025] In the present invention, the ultrasonic sensor further includes a distance calculation unit for calculating the distance to the obstacle.

[0026] In the present invention, the central processing unit also includes a sensor data fusion module, a path planning and decision module and a control execution module.

[0027] In the present invention, the storage unit also includes a map data storage unit and a software program storage unit.

[0028] In the present invention, the communication module further includes a data receiving and sending unit for exchanging data with an external system.

[0029] In the present invention, the actuator further comprises a steering control unit, a speed control unit and a braking control unit, which are used to adjust the steering, speed and braking of the vehicle according to control instructions.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] 1. The present invention utilizes the high-precision positioning service of the Beidou satellite navigation system to provide centimeter-level positioning accuracy, and can maintain stable positioning performance even in complex environments; it adopts advanced sensor fusion technology to integrate data from cameras, lidars, radars and ultrasonic sensors to improve the accuracy and robustness of data processing; it combines visual navigation and processing technology to achieve accurate detection, recognition, tracking and semantic segmentation of targets in complex traffic scenes, and improve the adaptability and accuracy of visual processing.

[0032] 2. The present invention can adjust the path in real time in a dynamic environment and make accurate driving decisions by implementing efficient path planning and decision-making algorithms; and through a precise control execution system, it ensures that the vehicle has a fast response speed and high control accuracy when performing complex operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is an overall schematic diagram of the visual navigation and direction control system of the autonomous driving vehicle of the present invention;

[0034] Figure 2 This is a schematic diagram of the connection of the Beidou positioning receiver of the visual navigation and direction control system of the autonomous driving vehicle of the present invention;

[0035] Figure 3 This is a schematic diagram of the camera array connection of the visual navigation and direction control system of the autonomous driving vehicle of the present invention;

[0036] Figure 4 This is a schematic diagram of the laser radar connection of the visual navigation and direction control system of the autonomous driving vehicle of the present invention;

[0037] Figure 5 This is a schematic diagram of the radar system connection of the visual navigation and direction control system of the autonomous driving vehicle of the present invention;

[0038] Figure 6 This is a schematic diagram of the connection of ultrasonic sensors for the visual navigation and direction control system of the autonomous driving vehicle of the present invention;

[0039] Figure 7 This is a schematic diagram of the connection of the central processing unit of the visual navigation and direction control system of the autonomous driving vehicle of the present invention;

[0040] Figure 8 This is a schematic diagram of the storage unit connection of the visual navigation and direction control system of the autonomous driving vehicle of the present invention;

[0041] Fig. 9 This is a schematic diagram of the connection of the communication modules of the visual navigation and direction control system of the autonomous driving vehicle of the present invention;

[0042] Fig.10This is a schematic diagram of the actuator connections of the visual navigation and direction control system of the autonomous driving vehicle of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] like Figure 1-10 As shown, the present invention provides a technical solution:

[0045] The visual navigation and direction control system of the autonomous driving car includes

[0046] Beidou positioning receiver, used to receive Beidou satellite signals and calculate the vehicle's position and speed;

[0047] Preferably, the Beidou positioning receiver further includes a differential receiving unit and a real-time dynamic processing unit, which are used to provide centimeter-level positioning accuracy;

[0048] Specifically, the Beidou positioning receiver receives Beidou satellite signals through an antenna and is connected to the central processing unit through a data line; the receiver parses the satellite signals, calculates the vehicle's position and speed, and transmits the data to the central processing unit for further processing and application.

[0049] In this embodiment, the position calculation formula is as follows:

[0050] p=KalmanFilter(z 1 ,z 2 ,…,z n )

[0051] Where p represents the calculated vehicle position vector. i Represents the measurement value of the i-th satellite, including pseudorange and Doppler frequency. KalmanFilter represents the Kalman filter function, which is used to fuse the measurement values ​​of multiple satellites to improve positioning accuracy.

[0052] a camera array, including forward-looking, side-looking, and rear-looking cameras, for capturing images of the vehicle's surroundings;

[0053] Preferably, the camera array further comprises an image processing unit for processing the captured images and performing target detection, recognition, tracking and semantic segmentation;

[0054] Specifically, the camera is connected to the image processing unit via a video cable, and the image processing unit is connected to the central processing unit via a data cable; the camera captures images of the vehicle's surroundings, the image processing unit performs pre-processing, target detection, recognition, tracking and semantic segmentation on the images, and then transmits the processed data to the central processing unit.

[0055] In this embodiment, the target detection formula is as follows:

[0056] b i =YOLO(I)

[0057] Among them, b i Represents the bounding box of the i-th detected object. I represents the input image. YOLO stands for You Only Look Once object detection algorithm, which is used to detect objects in an image and return the bounding box.

[0058] LiDAR, which measures the distance and outline of surrounding objects;

[0059] Preferably, the laser radar further includes a data processing unit for processing the measurement data and generating an environment model;

[0060] Specifically, the laser radar is connected to the data processing unit via a data cable, and the data processing unit is connected to the central processing unit via a data cable; the laser radar emits a laser beam and receives a reflected signal, measures the distance and contour of surrounding objects, and the data processing unit processes the measured data and generates an environmental model, and then transmits the data to the central processing unit.

[0061] In this implementation, the distance calculation formula is as follows:

[0062] d i =2c·Δt i

[0063] Among them, d i represents the distance of the i-th measurement point. c represents the speed of light. Δt i Indicates the time difference between the emission and reception of a laser beam.

[0064] radar systems to detect objects and speed at long distances;

[0065] Preferably, the radar system further comprises a target tracking unit for tracking the detected object and predicting its motion trajectory;

[0066] Specifically, the radar system is connected to the target tracking unit via a data line, and the target tracking unit is connected to the central processing unit via a data line; the radar system transmits radio waves and receives reflected signals to detect distant objects and speeds, and the target tracking unit tracks the detected objects and predicts their motion trajectory, and then transmits the data to the central processing unit.

[0067] In this embodiment, the speed calculation formula is as follows:

[0068] v i =2λ·Δf i

[0069] Among them, v i represents the speed of the i-th detected target. λ represents the radar wavelength. Δf i Represents the Doppler shift frequency.

[0070] Ultrasonic sensors for close-range obstacle detection;

[0071] Preferably, the ultrasonic sensor further includes a distance calculation unit for calculating the distance to the obstacle;

[0072] Specifically, the ultrasonic sensor is connected to the distance calculation unit via a data line, and the distance calculation unit is connected to the central processing unit via a data line; the ultrasonic sensor transmits ultrasonic waves and receives reflected signals to measure the distance to the obstacle, and the distance calculation unit processes the measured data and then transmits the data to the central processing unit.

[0073] A central processing unit, which processes sensor data and executes control algorithms;

[0074] Preferably, the central processing unit further includes a sensor data fusion module, a path planning and decision module and a control execution module;

[0075] Specifically, the CPU is connected to all sensors, storage units, communication modules and actuators through data lines; the CPU receives data from each sensor, executes software programs, performs data fusion, path planning, decision making and control instruction generation, and then transmits the control instructions to the actuator.

[0076] In this embodiment, the path planning formula

[0077] p=AStar(s,g,M)

[0078] Where p represents the calculated path. s represents the starting point. g represents the ending point. M represents the map data. AStar represents the A* path planning algorithm, which is used to find the optimal path from the starting point to the ending point on the map.

[0079] A storage unit for storing high-precision map data and software programs;

[0080] Preferably, the storage unit further comprises a map data storage unit and a software program storage unit;

[0081] Specifically, the storage unit is connected to the central processing unit via a data line; the storage unit stores high-precision map data and software programs, and the central processing unit reads data and programs from the storage unit as needed.

[0082] Communication module, used for data exchange with external systems;

[0083] Preferably, the communication module further comprises a data receiving and sending unit for exchanging data with an external system;

[0084] Specifically, the communication module is connected to the central processing unit via a data line and is connected to the external system via a wireless network; the communication module receives and sends data, exchanges data with external systems such as the traffic management system, and the central processing unit performs corresponding processing based on the data received by the communication module.

[0085] Actuators, including steering motors, throttle controls, and brakes, perform the actual control of the vehicle;

[0086] Preferably, the actuator further comprises a steering control unit, a speed control unit and a braking control unit, which are used to adjust the steering, speed and braking of the vehicle according to the control instructions;

[0087] Specifically, the actuator is connected to the central processing unit through a control line; the actuator receives control instructions from the central processing unit, adjusts the steering motor, throttle controller and brake, and realizes the steering, speed and braking control of the vehicle.

[0088] The visual navigation and direction control system of the autonomous driving vehicle further includes a software program installed in the central processing unit, and the software program is executed by the central processing unit when the vehicle is running;

[0089] The software program consists of the control software modules of the autonomous driving system, including:

[0090] A positioning and navigation module, which is responsible for processing the signals of the Beidou positioning receiver and high-precision map data;

[0091] A sensor data fusion module, which is responsible for integrating and processing data from cameras, lidar, radar and ultrasonic sensors;

[0092] A path planning and decision-making module, which is responsible for calculating the optimal path and making driving decisions;

[0093] A control execution module, which is responsible for converting the decision into a control instruction for the actuator;

[0094] A user interface module, which is responsible for displaying vehicle status and receiving user input.

[0095] The above software execution sequence includes the following steps:

[0096] Step S1: The Beidou positioning receiver receives satellite signals and calculates the position and speed of the vehicle;

[0097] Step S2: Camera, LiDAR, radar and ultrasonic sensors capture environmental data;

[0098] Step S3: The sensor data fusion module processes and integrates the sensor data;

[0099] Step S4: The positioning and navigation module combines the high-precision map data to update the vehicle position;

[0100] Step S5: The path planning and decision module calculates the optimal path and makes driving decisions;

[0101] Step S6: The control execution module converts the decision into a control instruction and sends it to the actuator;

[0102] Step S7: The actuator adjusts the steering, speed and braking of the vehicle according to the control command;

[0103] Step S8: The user interface module displays the vehicle status and receives user input for emergency takeover.

[0104] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0105] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. The visual navigation and direction control system of the autonomous driving car is characterized by: include Beidou positioning receiver, used to receive Beidou satellite signals and calculate the vehicle's position and speed; a camera array, including forward-looking, side-looking, and rear-looking cameras, for capturing images of the vehicle's surroundings; LiDAR, which measures the distance and outline of surrounding objects; radar systems to detect objects and speed at long distances; Ultrasonic sensors for close-range obstacle detection; A central processing unit, which processes sensor data and executes control algorithms; A storage unit for storing high-precision map data and software programs; Communication module, used for data exchange with external systems; Actuators, including the steering motor, throttle controller, and brakes, perform the actual control of the vehicle.

2. The visual navigation and direction control system of the autonomous driving vehicle according to claim 1 is characterized in that: The Beidou positioning receiver also includes a differential receiving unit and a real-time dynamic processing unit, which are used to provide centimeter-level positioning accuracy.

3. The visual navigation and direction control system of the autonomous driving vehicle according to claim 1 is characterized in that: The camera array also includes an image processing unit for processing captured images and performing target detection, recognition, tracking and semantic segmentation.

4. The visual navigation and direction control system of the autonomous driving vehicle according to claim 1 is characterized in that: The laser radar also includes a data processing unit for processing measurement data and generating an environment model.

5. The visual navigation and direction control system of the autonomous driving vehicle according to claim 1 is characterized in that: The radar system also includes a target tracking unit for tracking detected objects and predicting their motion trajectories.

6. The visual navigation and direction control system of the autonomous driving vehicle according to claim 1 is characterized in that: The ultrasonic sensor further includes a distance calculation unit for calculating the distance to an obstacle.

7. The visual navigation and direction control system of the autonomous driving vehicle according to claim 1 is characterized in that: The central processing unit also includes a sensor data fusion module, a path planning and decision module and a control execution module.

8. The visual navigation and direction control system of the autonomous driving vehicle according to claim 1 is characterized in that: The storage unit also includes a map data storage unit and a software program storage unit.

9. The visual navigation and direction control system of the autonomous driving vehicle according to claim 1, characterized in that: The communication module also includes a data receiving and sending unit for exchanging data with an external system.

10. The visual navigation and direction control system of the autonomous driving vehicle according to claim 1, characterized in that: The actuator further comprises a steering control unit, a speed control unit and a braking control unit, which are used to adjust the steering, speed and braking of the vehicle according to the control instructions.

Images