日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

群制御arXiv:2004.10920

欲求階層に基づく協調マルチロボットの自己適応フレームワーク

Hierarchical Needs Based Self-Adaptive Framework For Cooperative Multi-Robot System

シェア:XThreadsFacebookLINEはてブBluesky

マズローの欲求階層に着想を得たロボット欲求階層と分散交渉・合意機構を組み合わせ、複雑なタスクを原子操作に分解して未知環境に適応する群ロボットシステムSASSを提案・評価した論文。

著者: Qin Yang, Ramviyas Parasuraman

分類: cs.RO

原文アブストラクト

Research in multi-robot and swarm systems has seen significant interest in cooperation of agents in complex and dynamic environments. To effectively adapt to unknown environments and maximize the utility of the group, robots need to cooperate, share information, and make a suitable plan according to the specific scenario. Inspired by Maslow's hierarchy of human needs and systems theory, we introduce Robot's Need Hierarchy and propose a new solution called Self-Adaptive Swarm System (SASS). It combines multi-robot perception, communication, planning, and execution with the cooperative management of conflicts through a distributed Negotiation-Agreement Mechanism that prioritizes robot's needs. We also decompose the complex tasks into simple executable behaviors through several Atomic Operations, such as selection, formation, and routing. We evaluate SASS through simulating static and dynamic tasks and comparing them with the state-of-the-art collision-aware task assignment method integrated into our 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

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI