CHOMP: Covariant Hamiltonian Optimization for Motion Planning - Robotics Institute Carnegie Mellon University

CHOMP: Covariant Hamiltonian Optimization for Motion Planning

Journal Article, International Journal of Robotics Research, Vol. 32, No. 9, pp. 1164 - 1193, August, 2013

Abstract

In this paper, we present CHOMP (Covariant Hamiltonian Optimization for Motion Planning), a method for trajectory optimization invariant to reparametrization. CHOMP uses functional gradient techniques to iteratively improve the quality of an initial trajectory, optimizing a functional that trades off between a smoothness and an obstacle avoidance component. CHOMP can be used to locally optimize feasible trajectories, as well as to solve motion planning queries, converging to low- cost trajectories even when initialized with infeasible ones. It uses Hamiltonian Monte Carlo to alleviate the problem of convergence to high-cost local minima (and for probabilistic completeness), and is capable of respecting hard constraints along the trajectory. We present extensive experiments with CHOMP on manipulation and locomotion tasks, using 7-DOF manipulators and a rough-terrain quadruped robot.

BibTeX

@article{Zucker-2013-7700,
author = {Matthew Zucker and Nathan Ratliff and Anca Dragan and Mikhail Pivtoraiko and Matthew Klingensmith and Christopher Dellin and J. Andrew (Drew) Bagnell and Siddhartha Srinivasa},
title = {CHOMP: Covariant Hamiltonian Optimization for Motion Planning},
journal = {International Journal of Robotics Research},
year = {2013},
month = {August},
volume = {32},
number = {9},
pages = {1164 - 1193},
keywords = {trajectory optimization, motion planning},
}