日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

軌道計画arXiv:1908.08493

混雑環境における移動ロボットのオンライン軌道計画のハイブリッド手法

A Hybrid Method for Online Trajectory Planning of Mobile Robots in Cluttered Environments

シェア:XThreadsFacebookLINEはてブBluesky

サンプリングベース探索と二次計画法によるモデルベース最適化を融合し、障害物の多い既知環境でロボットの動的制約を考慮した実行可能な軌道をオンライン生成する手法を提案した。

著者: Leobardo Campos-Macías, David Gómez-Gutiérrez, Rodrigo Aldana-López, Rafael de la Guardia, José I. Parra-Vilchis

分類: cs.RO

原文アブストラクト

This paper presents a method for online trajectory planning in known environments. The proposed algorithm is a fusion of sampling-based techniques and model-based optimization via quadratic programming. The former is used to efficiently generate an obstacle-free path while the latter takes into account the robot dynamical constraints to generate a time-dependent trajectory. The main contribution of this work lies on the formulation of a convex optimization problem over the generated obstacle-free path that is guaranteed to be feasible. Thus, in contrast with previously proposed methods, iterative formulations are not required. The proposed method has been compared with state-of-the-art approaches showing a significant improvement in success rate and computation time. To illustrate the effectiveness of this approach for online planning, the proposed method was applied to the fluid autonomous navigation of a quadcopter in multiple environments consisting of up to two hundred obstacles. The scenarios hereinafter presented are some of the most densely cluttered experiments for online planning and navigation reported to date. See video at https://youtu.be/DJ1IZRL5t1Q

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. 3Google DeepMind、ロボット向けAIを発表新製品・発表
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5GXO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

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