Unmanned tricycle intelligent driving bag system based on visual navigation

Abstract

The invention discloses an unmanned tricycle intelligent driving bag system based on visual navigation, and particularly relates to the technical field of intelligent driving, the unmanned tricycle intelligent driving bag system comprises a visual perception unit, a central control module and an execution control interface, and the central control module comprises an environment perception module, a positioning and mapping module and a path planning and decision module. According to the invention, by integrating the visual perception module, the central control module and the precise execution module, autonomous reverse driving of the tricycle in a complex environment is realized. By means of a high-precision vision and inertial measurement unit fusion technology, the system can complete three-dimensional environment perception, accurate positioning and mapping, accurate obstacle recognition and collision-free path planning, especially can perform look-ahead avoidance on dynamic obstacles, and remarkably improves operation safety and operation accuracy.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, and in particular to an intelligent driving package system for an unmanned tricycle based on vision navigation. Background Technology

[0002] With the rapid development of technology, autonomous driving technology has become one of the current research hotspots, showing significant potential in freeing drivers' hands, reducing traffic accidents caused by human fatigue, and minimizing injuries in special scenarios. However, current autonomous vehicles on the market still face problems such as high production costs, low resource utilization, and susceptibility to human error. Bottlenecks also exist in key technologies such as environmental perception and autonomous decision-making, making it difficult for their cost and reliability to meet practical application needs. On the other hand, traditional electric tricycles are difficult to operate and have low safety in complex road conditions, especially when precise reversing or driving in the opposite direction is required. While most current autonomous driving robots possess advantages such as high control precision, good repeatability, and strong fatigue resistance, they are generally limited in function and difficult to adapt to diverse application scenarios.

[0003] Chinese Patent Publication No. CN111775941A discloses an automated unmanned vehicle and control system, comprising a vehicle body, a conversion device, a data acquisition device, a main control device, and a driving device. This system, through improvements to existing vehicles by incorporating the conversion device, data acquisition device, main control device, and driving device, achieves seamless switching between unmanned and active driving, solving the problems of high cost and significant safety hazards associated with unmanned vehicles. Chinese Patent Publication No. CN113147752A discloses an automated unmanned vehicle and control system, and an unmanned driving method and system, which includes acquiring images containing information about the vehicle's surrounding environment, using the acquired images to identify obstacles based on image recognition methods, determining whether the obstacles are static or dynamic, and executing corresponding driving strategies. This invention improves the safety of unmanned driving by determining the type of obstacle and then executing the corresponding driving strategy.

[0004] While existing autonomous driving robots possess advantages such as high-precision control, good repeatability, and strong fatigue durability, most are limited to simple control of single-function operations and cannot meet multi-functional needs. Therefore, there is an urgent need for an autonomous driving solution that can adapt to various road conditions and improve operational convenience and safety. This solution should be characterized by high intelligence and strong applicability, enabling safe operation in both open and closed areas, while also possessing good practical value and market prospects. Summary of the Invention

[0005] The main objective of this invention is to provide a vision-based navigation-based intelligent driving package system for unmanned tricycles, which can effectively solve the problems mentioned in the background.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A vision-based navigation-based intelligent driving package system for an unmanned tricycle includes: (1) A visual perception unit, configured at the rear of the tricycle, for real-time acquisition of image data of the environment behind the tricycle; (2) A central control module, whose input terminal is electrically connected to the visual perception unit, for receiving the image data; (3) Execution control interface, whose input end is electrically connected to the central control module, and whose output end is suitable for connection to the steering system and drive system of the tricycle; The central control module includes: a. An environmental perception module, used to process the image data to identify obstacles and drivable areas in the rear environment; b. A positioning and mapping module, used to estimate the pose of the tricycle in real time based on the image data, and to build or update a map of the rear environment; c. Path planning and decision-making module, used to plan a collision-free reverse driving path based on a preset reverse driving target point and the processing results of the environment perception module and the positioning and mapping module, and generate corresponding steering control commands and drive control commands. The central control module sends the steering control command and drive control command to the steering system and drive system respectively via the execution control interface to control the tricycle to drive autonomously along the reverse driving path.

[0007] Furthermore, it also includes an inertial measurement unit, which is connected to the central control module. The positioning and mapping module is also used to fuse the acceleration and angular velocity data output by the inertial measurement unit to improve the accuracy and stability of the tricycle pose estimation.

[0008] Furthermore, the visual perception unit includes a binocular stereo camera, and the environment perception module is also used to obtain the depth information of the rear environment by calculating the parallax of the left and right views acquired by the binocular stereo camera, so as to realize three-dimensional obstacle detection.

[0009] Furthermore, it also includes a human-machine interaction module, which is connected to the central control module. The human-machine interaction module includes a display unit and an emergency stop unit. The display unit is used to visually display the reverse driving path and the obstacles identified by the environmental perception module. The emergency stop unit is used to receive user operations to immediately stop the autonomous reverse driving in an emergency.

[0010] Furthermore, the system also supports a path teaching mode. In this mode, the central control module records the trajectory data when the user manually operates the tricycle to drive forward into a target area. Based on the trajectory data, the path planning and decision-making module automatically generates a reverse trajectory as the preset reverse driving target path.

[0011] Furthermore, the execution control interface includes: a. A steering motor controller, used to receive the steering control command and to control the steering angle of the steering system in a closed loop; b. A drive motor controller, used to receive the drive control commands and to perform closed-loop control of the driving speed and direction of the drive system.

[0012] Furthermore, it also includes a wireless communication module, which is connected to the central control module. The central control module communicates with a remote monitoring platform through the wireless communication module to report the real-time position and driving status of the tricycle and the processing results of the environmental perception module, and is adapted to receive remote takeover commands issued by the remote monitoring platform.

[0013] Furthermore, the path planning and decision-making module is also used for: a. Steering motor controller, which monitors dynamic obstacles identified by the environmental perception module in real time; b. When it is predicted that the trajectory of the dynamic obstacle will conflict with the reverse driving path, the path planning and decision-making module will generate a braking command first to make the tricycle slow down or stop and wait for the dynamic obstacle to pass.

[0014] Compared with the prior art, the present invention has the following beneficial effects: This invention integrates visual perception, central control, and precise execution to enable tricycles to autonomously reverse in complex environments. Its beneficial effects are mainly reflected in significantly improved operational safety, operational accuracy, and user convenience. Specifically, the system utilizes high-precision visual perception and inertial measurement unit fusion technology to achieve three-dimensional environmental perception, accurate self-positioning, and map construction. This allows for precise obstacle identification and collision-free path planning, especially for dynamic obstacles, enabling proactive avoidance and greatly reducing the risk of accidents during reverse driving. Simultaneously, the human-machine interface module and emergency stop function enhance the driver's control and confidence in the system. Furthermore, the path teaching mode simplifies the setup process for complex paths, improving deployment efficiency; the closed-loop control steering and drive system ensures the accuracy of path execution; and wireless communication and remote monitoring functions further expand the system's manageability and ability to respond to emergencies, making the reverse operation of the tricycle in confined spaces or specific work scenarios more intelligent, safe, and efficient. Attached Figure Description

[0015] Figure 1 This is a flowchart of the system's main control and reverse driving process according to the present invention; Figure 2 This is a flowchart of the real-time dynamic obstacle response in this invention; Figure 3 This is a flowchart of the remote monitoring and emergency response process in this invention. Detailed Implementation

[0016] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0017] Example 1, see Figure 1-3 A vision-based navigation-based intelligent driving package system for unmanned tricycles includes: (1) A visual perception unit, located at the rear of the tricycle, is used to collect image data of the environment behind the tricycle in real time; (2) The central control module, whose input terminal is electrically connected to the visual perception unit, is used to receive image data; (3) Execution control interface, whose input end is electrically connected to the central control module, and whose output end is suitable for connection to the steering system and drive system of the tricycle; The central control module includes: a. Environmental perception module, used to process image data to identify obstacles and drivable areas in the rear environment; b. The localization and mapping module is used to estimate the pose of the tricycle in real time based on image data and to build or update the rear environment map; c. The path planning and decision-making module is used to plan a collision-free reverse driving path based on a preset reverse driving target point and the processing results of the environmental perception module and the positioning and mapping module, and to generate corresponding steering control commands and drive control commands. The central control module sends steering control commands and drive control commands to the steering system and drive system respectively via the execution control interface to control the tricycle to drive autonomously along the reverse driving path. The vision perception unit uses a vision camera to monitor the road conditions behind the vehicle in real time, providing visual support for reverse driving. The central control module uses the RK3576 chip as the core control unit, based on 6TOPs computing power, and integrates image recognition, deep learning and decision-making functions to realize the recognition and avoidance of common objects during driving. The execution control interface is connected to the chassis platform via CAN bus, converting driving control commands into CAN format bus commands and outputting them to the vehicle control unit.

[0018] It also includes an inertial measurement unit (IMU), which is connected to the central control module. The positioning and mapping module is also used to fuse the acceleration and angular velocity data output by the IMU to improve the accuracy and stability of the tricycle's pose estimation. The IMU, connected to the central control module, provides acceleration and angular velocity data to assist the positioning and mapping module in accurate positioning and path planning. Combined with RTK positioning sensors, it enables the vehicle to drive stably in both open and closed areas.

[0019] The visual perception unit includes a binocular stereo camera. The environmental perception module is also used to obtain depth information of the rear environment by calculating the parallax of the left and right views acquired by the binocular stereo camera, so as to realize three-dimensional obstacle detection. The binocular stereo camera adopts a dual-lens design with a resolution of 20 million pixels and has low latency characteristics. It transmits image data to the central control module in real time and obtains depth information by calculating the parallax of the left and right views, thereby realizing the detection of three-dimensional obstacles.

[0020] It also includes a human-machine interaction module, which is connected to the central control module. The human-machine interaction module includes a display unit and an emergency stop unit. The display unit is used to visually display the reverse driving path and obstacles identified by the environmental perception module. The emergency stop unit is used to receive user operations to immediately stop autonomous reverse driving in an emergency. The human-machine interaction module is located on the front side of the vehicle and includes a touch screen as the display unit and multiple operation buttons. The emergency stop unit is used to immediately stop autonomous reverse driving in an emergency. The operator can select manual driving mode or automatic driving mode through the operation buttons.

[0021] The system also supports a path teaching mode. In this mode, the central control module records the trajectory data of the tricycle when the user manually operates it to travel forward into a target area. Based on the trajectory data, the path planning and decision-making module automatically generates a reverse trajectory as the preset reverse driving target path. In the path teaching mode, the central control module records the trajectory data of the tricycle when the user manually operates it to travel forward into the target area, and automatically generates a reverse trajectory as the reverse driving target path based on the trajectory data, thus achieving precise reverse driving control.

[0022] The execution control interface includes: a. Steering motor controller, used to receive steering control commands and control the steering angle of the steering system in a closed loop; b. Drive motor controller, used to receive drive control commands and control the driving speed and direction of the drive system in a closed loop. The steering motor controller adopts a stepper motor controller to control the rope drive motor module to achieve precise control of the vehicle's direction; the drive motor controller adopts an electric actuator controller to control the high-torque electric actuator module to achieve precise control of the vehicle's braking.

[0023] It also includes a wireless communication module, which is connected to the central control module. The central control module communicates with a remote monitoring platform through the wireless communication module to report the real-time position, driving status and environmental perception results of the tricycle, and is also suitable for receiving remote takeover commands issued by the remote monitoring platform. The wireless communication module is connected to the central control module to report the real-time position, driving status and environmental perception results of the tricycle to the remote monitoring platform, and to receive remote takeover commands, so as to realize remote monitoring and intervention.

[0024] The path planning and decision-making module is also used for: a. Steering motor controller, which monitors dynamic obstacles identified by the environmental perception module in real time; b. When it is predicted that the trajectory of a dynamic obstacle will conflict with the reverse driving path, the path planning and decision-making module will prioritize generating a braking command to slow down or stop the tricycle and wait for the dynamic obstacle to pass. During the reverse driving process, the path planning and decision-making module will monitor the dynamic obstacles identified by the environmental perception module in real time. When a trajectory conflict is predicted, it will prioritize generating a braking command to slow down or stop the tricycle and wait for the dynamic obstacle to pass, thus ensuring driving safety.

[0025] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A vision-based navigation-based intelligent driving package system for an unmanned tricycle, characterized in that, include: (1) A visual perception unit, configured at the rear of the tricycle, for real-time acquisition of image data of the environment behind the tricycle; (2) A central control module, whose input terminal is electrically connected to the visual perception unit, for receiving the image data; (3) Execution control interface, whose input end is electrically connected to the central control module, and whose output end is suitable for connection to the steering system and drive system of the tricycle; The central control module includes: a. An environmental perception module, used to process the image data to identify obstacles and drivable areas in the rear environment; b. A positioning and mapping module, used to estimate the pose of the tricycle in real time based on the image data, and to build or update a map of the rear environment; c. The path planning and decision-making module is used to plan a collision-free reverse driving path based on a preset reverse driving target point and the processing results of the environment perception module and the positioning and mapping module, and to generate corresponding steering control commands and drive control commands. The central control module sends the steering control command and drive control command to the steering system and drive system respectively via the execution control interface to control the tricycle to drive autonomously along the reverse driving path.

2. The intelligent driving package system for an unmanned tricycle based on vision navigation according to claim 1, characterized in that: It also includes an inertial measurement unit, which is connected to the central control module. The positioning and mapping module is also used to fuse the acceleration and angular velocity data output by the inertial measurement unit to improve the accuracy and stability of the tricycle pose estimation.

3. The intelligent driving package system for an unmanned tricycle based on vision navigation according to claim 1, characterized in that: The visual perception unit includes a binocular stereo camera, and the environment perception module is further used to obtain the depth information of the rear environment by calculating the parallax of the left and right views acquired by the binocular stereo camera, so as to realize three-dimensional obstacle detection.

4. The intelligent driving package system for an unmanned tricycle based on vision navigation according to claim 1, characterized in that: It also includes a human-machine interaction module, which is connected to the central control module. The human-machine interaction module includes a display unit and an emergency stop unit. The display unit is used to visually display the reverse driving path and the obstacles identified by the environmental perception module. The emergency stop unit is used to receive user operations to immediately stop the autonomous reverse driving in an emergency.

5. The intelligent driving package system for an unmanned tricycle based on vision navigation according to claim 1, characterized in that: The system also supports a path teaching mode. In this mode, the central control module records the trajectory data of the tricycle when it is manually driven forward into a target area. Based on the trajectory data, the path planning and decision-making module automatically generates a reverse trajectory as the preset reverse driving target path.

6. The intelligent driving package system for an unmanned tricycle based on vision navigation according to claim 1, characterized in that: The execution control interface includes: a. A steering motor controller, used to receive the steering control command and to control the steering angle of the steering system in a closed loop; b. A drive motor controller, used to receive the drive control commands and to perform closed-loop control of the driving speed and direction of the drive system.

7. The intelligent driving package system for an unmanned tricycle based on vision navigation according to claim 1, characterized in that: It also includes a wireless communication module, which is connected to the central control module. The central control module communicates with a remote monitoring platform through the wireless communication module to report the real-time position and driving status of the tricycle and the processing results of the environmental perception module, and is adapted to receive remote takeover commands issued by the remote monitoring platform.

8. The intelligent driving package system for an unmanned tricycle based on vision navigation according to claim 1, characterized in that: The path planning and decision-making module is also used for: a. Steering motor controller, which monitors dynamic obstacles identified by the environmental perception module in real time; b. When it is predicted that the trajectory of the dynamic obstacle will conflict with the reverse driving path, the path planning and decision-making module will generate a braking command first to make the tricycle slow down or stop and wait for the dynamic obstacle to pass.

Images