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最適化フレームワーク(第I部)
A Nonlinear Constrained Optimization Framework for Comfortable and Customizable Motion Planning of Nonholonomic Mobile Robots - Part I
人間を運ぶ移動ロボットの乗り心地を重み付きコスト関数でモデル化し、境界条件・連続性・動力学・障害物回避の制約下で軌道を求める非線形最適化問題として定式化した論文。有限要素で離散化し、ユーザーごとの快適さのカスタマイズ手法も示す。
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 this first one we present the mathematical foundation of our framework. The motion of a mobile robot that transports a human should be comfortable and customizable. We identify several properties that a trajectory must have for comfort. 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. The optimization problem is infinite-dimensional and we discretize it using conforming finite elements. We also outline a method by which different users may customize the motion to achieve personal comfort. There exists significant past work in kinodynamic motion planning, to the best of our knowledge, our work is the first comprehensive formulation of kinodynamic motion planning for a nonholonomic mobile robot as a nonlinear optimization problem that includes all of the following - a careful analysis of boundary conditions, continuity requirements on trajectory, dynamic constraints, obstacle avoidance constraints, and a robust numerical implementation. In this paper, we present the mathematical foundation of the motion planning framework and formulate the full nonlinear constrained optimization problem. We describe, in brief, the discretization method using finite elements and the process of computing initial guesses for the optimization problem. Details of the above two are presented in Part II of the series.
