日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

経路計画arXiv:1608.05931

離散調和ポテンシャル場による計画手法

Planning With Discrete Harmonic Potential Fields

シェア:XThreadsFacebookLINEはてブBluesky

連続的な調和ポテンシャル場を離散グラフに拡張し、M*アルゴリズムやA*の下界問題の解決、動的ルーティングへの応用を示した論文。

著者: Ahmad A. Masoud

分類: cs.RO, cs.DM

原文アブストラクト

In this work a discrete counterpart to the continuous harmonic potential field approach is suggested. The extension to the discrete case makes use of the strong relation HPF-based planning has to connectionist artificial intelligence (AI). Connectionist AI systems are networks of simple, interconnected processors running in parallel within the confines of the environment in which the planning action is to be synthesized. It is not hard to see that such a paradigm naturally lends itself to planning on weighted graphs where the processors may be seen as the vertices of the graph and the relations among them as its edges. Electrical networks are an effective realization of connectionist AI. The utility of the discrete HPF (DHPF) approach is demonstrated in three ways. First, the capability of the DHPF approach to generate new, abstract, planning techniques is demonstrated by constructing a novel, efficient, optimal, discrete planning method called the M* algorithm. Also, its ability to augment the capabilities of existing planners is demonstrated by suggesting a generic solution to the lower bound problem faced by the A* algorithm. The DHPF approach is shown to be useful in solving specific planning problems in communication. It is demonstrated that the discrete HPF paradigm can support routing on-the-fly while the network is still in a transient state. It is shown by simulation that if a path to the target always exist and the switching delays in the routers are negligible, a packet will reach its destination despite the changes in the network which may simultaneously take place while the packet is being routed.

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. 2Google DeepMind、ロボット向けAIを発表新製品・発表
  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. 4SoftBank主導、Agile Robotsが5億ドル調達 NVIDIAと日立も参加資金調達
  5. 5NTT、ロボットの行動前に荷崩れを予測研究・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