Enhanced detection and guidance with side angle constraints based on 2D target

Aiming at the specific target search and controllable angle guidance of unmanned surface ships in uncertain waters, this paper explores the target detection method based on YOLO and the guidance control method based on side angle constraint. On the basis of analyzing the uncertain conditions such as sea fog, the paper designs the correlation filter with improved YOLOv5 algorithm to extract the target features, combines depth information to realize the detection and positioning of water surface targets, sliding mode variable structure guidance control to achieve the high maneuverability target side angle constraint guidance. TCP/IP combined with ROS is used to create a corner constrained terminal guidance system for information processing. Two-dimensional simulation experiment is completed with Autolabor platform, and the result of target guidance error is 1.54%, which proves the effectiveness of the method proposed.