Self-adaptive obstacle avoidance walking control device in complex scene

CN224766717UActive Publication Date: 2026-09-18TAIYUAN UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202522401812.3
Authority / Receiving Office
CN · China
Patent Type
Utility models(China)
Current Assignee / Owner
Filing Date
2025-11-12
Publication Date
2026-09-18
Estimated Expiration
2035-11-12

AI Technical Summary

Technical Problem

[0002]随着人工智能与智能感知技术的发展,行走设备在自动驾驶、无人巡检、安防监控等领域得到广泛应用;目前在复杂的动态环境下,为实现实时目标检测与路径规划控制,通常在行走设备上设置集成度较高的控制模块,并依赖远程云端对实时采集的数据进行分析和处理,一方面由于行走设备运行环境复杂且恶劣(如坡地、砂石地或潮湿环境),如果不具备相应的越障能力和抗震性能,将可能导致控制模块工作出现故障甚至损坏,且由于控制模块中各功能芯片没有在电路板上分布设置,导致数据处理性能差,芯片散热能力差,另一方面采用远程数据交互将使得目标检测时间出现延迟,将使得行走设备不能实现快速目标检测并及时做出障碍规避动作

Benefits of technology

[0009] The advantages of this invention compared to existing technologies are as follows: The adaptive obstacle avoidance walking control device provided by this invention adopts a frame with an optimized structure, and the drive and steering motors and the sensing control device are mounted on the frame. Specifically, the functional control modules in the sensing control device are set as a distributed structure, realizing unified scheduling and high-speed interaction of data between the image acquisition, preprocessing, target detection, trajectory prediction and path planning control chips, which improves the overall data processing performance. At the same time, the stability of the entire frame is ensured by installing shock absorbers on the frame. The drive actuator adopts a wheel-mounted height-response motor design, which has strong obstacle-crossing ability, flexibility and load-bearing capacity, enabling the device to operate stably in different indoor and outdoor scenarios, providing hardware support for the application of intelligent devices in multiple scenarios, and improving the adaptability and safety in complex environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN224766717U_ABST
    Figure CN224766717U_ABST
Patent Text Reader

Abstract

The utility model provides a kind of self-adapting obstacle avoidance walking control device under complex scene belongs to self-adapting obstacle avoidance walking control device technical field;In order to solve the control module of current walking device to be easily damaged, the technical problem that cloud data transmission exists delay, the technical scheme for being adopted is as follows: the front and rear end of car frame is equipped with tire through axle, shock absorber and steering device are also installed on front and rear axle;The middle part of car frame is also provided with sensing control device, visual camera, power motor, steering motor, the output shaft of power motor is connected with driving shaft transmission by driving gear, the both ends of driving shaft are connected with axle transmission by axle transmission gear, the output shaft of steering motor is connected with steering device transmission by steering gear;Central processing unit is provided on sensing control device;The utility model is applied to self-adapting obstacle avoidance walking control device.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This utility model provides an adaptive obstacle avoidance walking control device for complex scenarios, belonging to the technical field of adaptive obstacle avoidance walking control devices. Background Technology

[0002] With the development of artificial intelligence and intelligent sensing technology, mobile devices are widely used in fields such as autonomous driving, unmanned inspection, and security monitoring. Currently, in complex dynamic environments, in order to achieve real-time target detection and path planning control, highly integrated control modules are usually set up on mobile devices, and the data collected in real time is analyzed and processed remotely by the cloud. On the one hand, because the operating environment of mobile devices is complex and harsh (such as slopes, gravel, or humid environments), if they do not have the corresponding obstacle-crossing ability and shock resistance, the control module may malfunction or even be damaged. Moreover, because the functional chips in the control module are not distributed on the circuit board, the data processing performance is poor and the chip heat dissipation is poor. On the other hand, the use of remote data interaction will delay the target detection time, which will prevent the mobile device from achieving rapid target detection and timely obstacle avoidance actions. Utility Model Content

[0003] In order to solve the technical problems existing in the background art, the present invention adopts the following technical solution: providing an adaptive obstacle avoidance walking control device in complex scenarios, including a frame, wherein tires are mounted on the front and rear ends of the frame via axles, and shock absorbers and steering devices are also mounted on the front and rear axles. The vehicle frame is also equipped with a sensor control device, a vision camera, a power motor, and a steering motor. The output shaft of the power motor is connected to the drive shaft via a drive gear. The two ends of the drive shaft are connected to the axle via axle drive gears. The output shaft of the steering motor is connected to the steering device via a steering gear. The sensing and control device is equipped with an image acquisition module, an image preprocessing module, a trajectory prediction module, a target detection module, a path planning module, and a central processing unit, wherein: The output of the visual camera is connected to the image acquisition module; The output of the image acquisition module is connected to the image preprocessing module; The output of the image preprocessing module is connected to the target detection module; The output of the target detection module is connected to the trajectory prediction module and the central processing unit, respectively. The trajectory prediction module is connected to the central processing unit via a wire; The central processing unit is connected to the path planning module via wires; The output of the path planning module is connected to the power motor and the directional motor, respectively.

[0004] The sensing and control device is also equipped with a data transmission interface.

[0005] The vehicle frame is also equipped with a power module, and the power input terminal of the sensing and control device is connected to the power module.

[0006] An emergency circuit fuse is also provided at the output end of the power module.

[0007] The model of the central processing unit is BCM2837B0; The image acquisition module specifically uses a CMOS image sensor of model OV5647; The image preprocessing module is model BCM2837B0.

[0008] The circuit board used inside the sensing and control device is specifically a Raspberry Pi 3B+ motherboard.

[0009] The advantages of this invention compared to existing technologies are as follows: The adaptive obstacle avoidance walking control device provided by this invention adopts a frame with an optimized structure, and the drive and steering motors and the sensing control device are mounted on the frame. Specifically, the functional control modules in the sensing control device are set as a distributed structure, realizing unified scheduling and high-speed interaction of data between the image acquisition, preprocessing, target detection, trajectory prediction and path planning control chips, which improves the overall data processing performance. At the same time, the stability of the entire frame is ensured by installing shock absorbers on the frame. The drive actuator adopts a wheel-mounted height-response motor design, which has strong obstacle-crossing ability, flexibility and load-bearing capacity, enabling the device to operate stably in different indoor and outdoor scenarios, providing hardware support for the application of intelligent devices in multiple scenarios, and improving the adaptability and safety in complex environments. Attached Figure Description

[0010] The present invention will be further described below with reference to the accompanying drawings: Figure 1 This is a schematic diagram of the structure of this utility model; Figure 2 for Figure 1 Top view; Figure 3 This is a schematic diagram of the structure of the sensing and control device of this utility model; Figure 4 This is a schematic diagram of the circuit structure of this utility model; In the diagram: 1 is the sensor control device, 2 is the vision camera, 3 is the shock absorber, 4 is the tire, 5 is the frame, 6 is the drive motor, and 7 is the steering motor. 101 is the image acquisition module, 102 is the image preprocessing module, 103 is the trajectory prediction module, 104 is the target detection module, 105 is the circuit emergency fuse, 106 is the path planning module, 107 is the data transmission interface, and 108 is the central processing unit. Detailed Implementation

[0011] like Figures 1 to 4 As shown, this utility model provides an adaptive obstacle avoidance walking control device for complex scenarios to solve the problems of large detection delay, insufficient detection performance, and poor obstacle avoidance effect in complex environments in existing technologies. The device distributes the corresponding detection function modules in the sensing and control device, and works with the drive actuator set on the frame to enable the walking device to achieve real-time multi-target detection, dynamic trajectory prediction and path planning linkage in complex dynamic environments, thereby improving the stability and real-time performance of data transmission when the walking device is performing obstacle avoidance control.

[0012] Furthermore, this utility model independently mounts the sensing and control device on the vehicle frame, and internally houses a central processing unit 108, an image acquisition module 101, an image preprocessing module 102, a trajectory prediction module 103, a target detection module 104, and a path planning module 106. Each module is an independent control chip integrated onto a single circuit board. The central processing unit 108 is installed inside the main body of the device. It has a built-in high-performance data processing chip and a high-speed data bus. It is used to comprehensively process the detection data, prediction results and path planning instructions from various modules, and realize efficient interaction between multiple modules through real-time coordination mechanism and closed-loop control. The image acquisition module 101 receives image information from the wide-angle and low-light adaptive vision camera 2 in real time, and can obtain clear and low-noise image data in situations such as wide field of view, backlight, haze, or night, providing stable visual input for subsequent recognition. Image preprocessing module 102 performs sharpening processing on the acquired images to generate high-quality feature maps; Based on the obtained feature map, the target detection module 104 identifies and locates multiple targets in the environment in real time, and outputs the spatial location information and feature parameters of the targets. The target detection module 104 has a short-term motion estimation function, which can input the motion information of continuous frames to the trajectory prediction module 103. The trajectory prediction module 103 predicts the target's movement trend, generates the walking trajectory distribution for future time periods, and transmits the prediction data to the central processing unit 108. After receiving the detection and prediction information integrated by the central processing unit 108, the path planning module 106 generates real-time path and obstacle avoidance motion commands, and sends control signals to the power motor 6 and the steering motor 7 to control the tire speed adjustment or steering, so as to realize autonomous navigation and dynamic obstacle avoidance. A power module is also installed on the frame 5. The power input terminal of the sensing and control device 1 is connected to the power module, and an emergency circuit fuse 105 is installed on the output terminal of the power module. The emergency circuit fuse 105 is installed between the output terminal of the power module and each functional module to prevent electrical damage caused by overcurrent, short circuit and voltage fluctuation. The fuse is connected in series with the power supply lines of the central processing unit 108, the drive actuator and the image acquisition module 101. When an abnormal current is detected, the circuit can be automatically disconnected to realize module-level power failure protection and avoid local faults from affecting the operation of the overall system.

[0013] The drive actuator provided by the present invention includes tires 4 mounted on the front and rear ends of the frame 5 via axles, shock absorbers 3 and steering devices mounted on the front and rear axles; a sensing and control device 1, a vision camera 2, a power motor 6 and a steering motor 7 are also provided in the middle of the frame 5. The output shaft of the power motor 6 is connected to the drive shaft via a drive gear, and the two ends of the drive shaft are connected to the axle via axle drive gears. The output shaft of the steering motor 7 is connected to the steering device via a steering gear. The power motor 6 and the directional motor 7 are high-response motors. Together with the current control circuit in the sensing and control device, the device not only has strong obstacle-crossing ability and shock resistance, but also can adjust the driving torque through real-time current feedback control. It can achieve low power consumption and high precision motion execution in complex road conditions (such as slopes, gravel roads or wet environments), and has strong obstacle-crossing ability and stability, providing hardware support for the application of intelligent devices in multiple scenarios.

[0014] Furthermore, the central processing unit 108 interacts with the image acquisition module 101, image preprocessing module 102, target detection module 104, trajectory prediction module 103, and path planning module 106 via a high-speed bus, enabling information acquisition, feature extraction, detection recognition, and prediction calculation to be completed in milliseconds, thereby ensuring the system's real-time response capability in complex environments.

[0015] The adaptive obstacle avoidance walking control device provided by this utility model has strong obstacle crossing ability and load-bearing capacity. It can achieve flexible turning and precise positioning in complex indoor and outdoor environments, efficiently execute motion commands, and complete the autonomous navigation and dynamic obstacle avoidance operation of the intelligent device. The central processor 108 set in the device can realize unified scheduling and high-speed interaction of various modules through real-time coordination mechanism and closed-loop control, combined with the environmental perception assistance of the sensor control device. The shock absorber set can continuously ensure the stability of the device operation, greatly improve the real-time performance and overall reliability of the system, and ensure the stable operation of the device in complex scenarios.

[0016] Regarding the specific structure of this utility model, it should be noted that the connection relationships between the various component modules adopted in this utility model are definite and achievable. Except as specifically described in the embodiments, their specific connection relationships can bring about corresponding technical effects and solve the technical problems proposed by this utility model without relying on the execution of corresponding software programs. The models of the components, modules, and specific components appearing in this utility model, the connection methods between them, and the conventional usage methods and expected technical effects brought about by the above-mentioned technical features, unless specifically described, are all publicly disclosed content in patents, journal articles, technical manuals, technical dictionaries, and textbooks that can be obtained by those skilled in the art before the application date, or belong to conventional technology, common knowledge, and other existing technologies in this field. There is no need to elaborate, which makes the technical solution provided in this case clear, complete, and achievable, and can reproduce or obtain corresponding physical products based on this technical means.

[0017] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this utility model, and are not intended to limit it. Although the utility model has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this utility model.

Claims

1. An adaptive obstacle avoidance walking control device for complex scenarios, comprising a frame (5), characterized in that: The front and rear ends of the frame (5) are equipped with tires (4) via axles, and shock absorbers (3) and steering devices are also installed on the front and rear axles; A sensing control device (1), a vision camera (2), a power motor (6), and a steering motor (7) are also provided in the middle of the frame (5). The output shaft of the power motor (6) is connected to the drive shaft through a drive gear. The two ends of the drive shaft are connected to the axle through axle drive gears. The output shaft of the steering motor (7) is connected to the steering device through a steering gear. The sensing and control device (1) is equipped with an image acquisition module (101), an image preprocessing module (102), a trajectory prediction module (103), a target detection module (104), a path planning module (106), and a central processing unit (108), wherein: The output of the visual camera (2) is connected to the image acquisition module (101); The output of the image acquisition module (101) is connected to the image preprocessing module (102); The output of the image preprocessing module (102) is connected to the target detection module (104); The output of the target detection module (104) is connected to the trajectory prediction module (103) and the central processing unit (108) respectively; The trajectory prediction module (103) is connected to the central processing unit (108) via a wire; The central processing unit (108) is connected to the path planning module (106) via wires; The output of the path planning module (106) is connected to the power motor (6) and the steering motor (7) respectively.

2. The adaptive obstacle avoidance walking control device in complex scenarios according to claim 1, characterized in that: The sensing control device (1) is also provided with a data transmission interface (107).

3. The adaptive obstacle avoidance walking control device in complex scenarios according to claim 2, characterized in that: The frame (5) is also equipped with a power module, and the power input terminal of the sensing and control device (1) is connected to the power module.

4. The adaptive obstacle avoidance walking control device in complex scenarios according to claim 3, characterized in that: An emergency circuit fuse (105) is also provided at the output of the power module.

5. The adaptive obstacle avoidance walking control device in complex scenarios according to claim 4, characterized in that: The central processing unit (108) is model BCM2837B0; The image acquisition module (101) specifically adopts a CMOS image sensor of model OV5647; The image preprocessing module (102) is model BCM2837B0.

6. The adaptive obstacle avoidance walking control device in complex scenarios according to claim 5, characterized in that: The circuit board used inside the sensing control device (1) is specifically a Raspberry Pi 3B+ motherboard.