日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

動作計画arXiv:1305.5025

非ホロノミック移動ロボットの快適でカスタマイズ可能な動作計画のための非線形制約付き最適化フレームワーク(後編)

A Nonlinear Constrained Optimization Framework for Comfortable and Customizable Motion Planning of Nonholonomic Mobile Robots - Part II

シェア:XThreadsFacebookLINEはてブBluesky

前編で定式化した快適さを重み付きコストとする非線形制約付き最適化問題を、適合有限要素で離散化して解く手法を詳述し、境界条件の扱いや疎なヘッセ行列を得る未知数の選び方、局所解の処理、高品質な初期解の計算法を示した。

著者: Shilpa Gulati, Chetan Jhurani, Benjamin Kuipers

分類: cs.RO, cs.CE, cs.NA, math.NA

原文アブストラクト

In this series of papers, we present a motion planning framework for planning comfortable and customizable motion of nonholonomic mobile robots such as intelligent wheelchairs and autonomous cars. In Part I, we presented the mathematical foundation of our framework, where we model motion discomfort as a weighted cost functional and define comfortable motion planning as a nonlinear constrained optimization problem of computing trajectories that minimize this discomfort given the appropriate boundary conditions and constraints. In this paper, we discretize the infinite-dimensional optimization problem using conforming finite elements. We describe shape functions to handle different kinds of boundary conditions and the choice of unknowns to obtain a sparse Hessian matrix. We also describe in detail how any trajectory computation problem can have infinitely many locally optimal solutions and our method of handling them. Additionally, since we have a nonlinear and constrained problem, computation of high quality initial guesses is crucial for efficient solution. We show how to compute them.

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