A study on smooth automatic vehicle stopping control for suddenly-appeared obstacles

Abstract

Various studies have been conducted regarding road obstacle detection and avoidance, but very few studies deal with the detection and avoidance of obstacles that suddenly and unexpectedly appear during vehicle operation. Therefore, we have been conducting studies on problem of detecting suddenly and unexpectedly appear obstacles. As an extension stage of those studies, this paper presents about automatic smooth stopping of vehicle using a fuzzy control system. The proposed system conducts stopping control of the vehicle depending on the distance to the obstacle and vehicle speed when obstacle is detected. The simulation experiments and actual experiments using a mobile robot on behalf of a vehicle were conducted regarding the proposal.

Research on forklift obstacle detection and distance warning method based on deep learning

“…The existing light problem; Guo Zhengliang [2] systematically designed the safety supervision system from the Internet of Things architecture and network communication method, and designed the forklift data acquisition hardware and supervision software, mainly from the perspective of personnel collision prevention and reverse collision prevention. Early warning measures; Gohara R et al [3] used visual sensors to detect targets within the field of view, calculated the depth information of obstacles, and combined with vehicle speed information to achieve anti-collision design for sudden obstacles; Kong Weiyu [4] aimed at agricultural tractors In the working environment, the fusion of lidar and computer vision is used to realize the identification of obstacles and distance detection. A tractor safety early warning level division model is proposed to realize the hierarchical early warning and obstacle avoidance strategy of distance; Hu Dandan et al [5] proposed a An unmanned obstacle detection method that improves YOLOv3 and stereo vision, obtains the depth information of the center point of the predicted bounding box through the stereo vision camera, and determines the distance between the obstacle and the unmanned vehicle; At present, there is no systematic management method and early warning system in the field of vehicle operation environment monitoring in China, and there are successful cases in vehicle management.…”