日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

USV経路計画arXiv:2202.04494

円グリッドに基づく無人水上艇の障害物回避運動計画手法

A Circle Grid-based Approach for Obstacle Avoidance Motion Planning of Unmanned Surface Vehicles

シェア:XThreadsFacebookLINEはてブBluesky

円グリッド軌道セル(CGTC)を用いて、USVの運動学的・動学的制約を満たしつつ静的・動的障害物を回避する滑らかな経路をオンライン生成する手法を提案した。

著者: Man Zhu, Changshi Xiao, Shangding Gu, Zhe Du, Yuanqiao Wen

分類: cs.RO

原文アブストラクト

Aiming at an obstacle avoidance problem with dynamic constraints for Unmanned Surface Vehicle (USV), a method based on Circle Grid Trajectory Cell (CGTC) is proposed. Firstly, the ship model and standardization rules are constructed to develop and constrain the trajectory, respectively. Secondly, by analyzing the properties of the circle grid, the circle grid tree is produced to guide the motion of the USV. Then, the kinematics and dynamics of the USV are considered through the on-line trajectory generator by designing a relational function that links the rudder angle, heading angle, and the central angle of the circle grid. Finally, obstacle avoidance is achieved by leveraging the on-line trajectory generator to choose a safe, smooth, and efficient path for the USV. The experimental results indicate that the proposed method can avoid both static and dynamic obstacles, have better performance in terms of distance cost and steering cost comparing with the related methods, and our method only takes 50% steering cost of the grid-based method; the collision avoidance path not only conforms to the USV dynamic characteristic but also provides a reference of steering command.

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  3. 3newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI