日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

マルチロボット計画arXiv:2204.11783

時相論理タスクと不確実ダイナミクス下における複数ロボット・物体システムの計画と制御

Planning and Control of Multi-Robot-Object Systems under Temporal Logic Tasks and Uncertain Dynamics

シェア:XThreadsFacebookLINEはてブBluesky

複数ロボットと非駆動物体からなる系に対し、LTLで表されたタスクを満たす動作計画アルゴリズムを提案し、下層の適応制御で不確実性を補償しつつ安全な物体搬送を実現する。

著者: Christos K. Verginis, Yiannis Kantaros, Dimos V. Dimarogonas

分類: eess.SY, cs.RO, cs.SY

原文アブストラクト

We develop an algorithm for the motion and task planning of a system comprised of multiple robots and unactuated objects under tasks expressed as Linear Temporal Logic (LTL) constraints. The robots and objects evolve subject to uncertain dynamics in an obstacle-cluttered environment. The key part of the proposed solution is the intelligent construction of a coupled transition system that encodes the motion and tasks of the robots and the objects. We achieve such a construction by designing appropriate adaptive control protocols in the lower level, which guarantee the safe robot navigation/object transportation in the environment while compensating for the dynamic uncertainties. The transition system is efficiently interfaced with the temporal logic specification via a sampling-based algorithm to output a discrete path as a sequence of synchronized actions of the robots; such actions satisfy the robots' as well as the objects' specifications. The robots execute this discrete path by using the derived low level control protocol. Simulation results verify the proposed framework.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmo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
  3. 3GXO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
  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

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI