改良型EGO-Plannerに基づく自律UAV捜索救助システムの研究
Research on an Autonomous UAV Search and Rescue System Based on the Improved
モータ逆バックステッピング制御と双方向A*で改良したEGO-Plannerを組み合わせ、複雑未知環境で自律的に障害物回避と捜索救助を行うUAVシステムを提案・検証した。
著者: Haobin Chen, Junyu Tao, Bize Zhou, Xiaoyan Liu
分類: cs.RO, cs.AI
原文アブストラクト
The demand is to solve the issue of UAV (unmanned aerial vehicle) operating autonomously and implementing practical functions such as search and rescue in complex unknown environments. This paper proposes an autonomous search and rescue UAV system based on an EGO-Planner algorithm, which is improved by innovative UAV body application and takes the methods of inverse motor backstepping to enhance the overall flight efficiency of the UAV and miniaturization of the whole machine. At the same time, the system introduced the EGO-Planner planning tool, which is optimized by a bidirectional A* algorithm along with an object detection algorithm. It solves the issue of intelligent obstacle avoidance and search and rescue. Through the simulation and field verification work, and compared with traditional algorithms, this method shows more efficiency and reliability in the task. In addition, due to the existing algorithm's improved robustness, this application shows good prospection.
