未知の水中空間における即時計画・制御・安全性の確保
Instantaneous Planning, Control and Safety for Navigation in Unknown Underwater Spaces
水中ロボットの未知環境での航行を、リアルタイムセンサデータとフィードバック制御を統合した枠組みで実現し、障害物回避と狭所での機動性を向上させる手法を提案した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Veejay Karthik, Udit Ekansh, Tejal Bedmutha, Shivam Vishwakarma, Rohan Deshpande, Leena Vachhani
分類: cs.RO
原文アブストラクト
Navigating autonomous underwater vehicles (AUVs) in unknown environments is significantly challenging due to poor visibility, weak signal transmission, and dynamic water currents. These factors pose challenges in accurate global localization, reliable communication, and obstacle avoidance. Local sensing provides critical real time environmental data to enable online decision making. However, the inherent noise in underwater sensor measurements introduces uncertainty, complicating planning and control. To address these challenges, we propose an integrated planning and control framework that leverages real time sensor data to dynamically induce closed loop AUV trajectories, ensuring robust obstacle avoidance and enhanced maneuverability in tight spaces. By planning motion based on pre designed feedback controllers, the approach reduces the computational complexity needed for carrying out online optimizations and enhances operational safety in complex underwater spaces. The proposed method is validated through ROS Gazebo simulations on the RexRov AUV, demonstrating its efficacy. Its performance is evaluated by comparison against PID based tracking methods, and quantifying localization errors in dead reckoning as the AUV transitions into the target communication range.
