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:1712.06021

一般化Lpノルムを用いた衝突回避付き可撓性直方体ロボットの経路計画

Bendable Cuboid Robot Path Planning with Collision Avoidance using Generalized $L_p$ Norms

シェア:XThreadsFacebookLINEはてブBluesky

一般化Lpノルムでロボットや障害物の表面を近似的に表現し、剛体・可撓性直方体ロボットの最適安全経路計画を非線形計画問題として解く手法を提案した。

著者: Nak-seung P. Hyun, Patricio A. Vela, Erik I. Verriest

分類: math.OC, cs.RO, cs.SY, eess.SY

原文アブストラクト

Optimal path planning problems for rigid and deformable (bendable) cuboid robots are considered by providing an analytic safety constraint using generalized $L_p$ norms. For regular cuboid robots, level sets of weighted $L_p$ norms generate implicit approximations of their surfaces. For bendable cuboid robots a weighted $L_p$ norm in polar coordinates implicitly approximates the surface boundary through a specified level set. Obstacle volumes, in the environment to navigate within, are presumed to be approximately described as sub-level sets of weighted $L_p$ norms. Using these approximate surface models, the optimal safe path planning problem is reformulated as a two stage optimization problem, where the safety constraint depends on a point on the robot which is closest to the obstacle in the obstacle's distance metric. A set of equality and inequality constraints are derived to replace the closest point problem, which is then defines additional analytic constraints on the original path planning problem. Combining all the analytic constraints with logical AND operations leads to a general optimal safe path planning problem. Numerically solving the problem involve conversion to a nonlinear programing problem. Simulations for rigid and bendable cuboid robot verify the proposed method.

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

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