CHOMP: Covariant Hamiltonian Optimization for Motion Planning

Matt Zucker, Nathan Ratliff, Anca D. Dragan, Mihail N. Pivtoraiko, Matthew Klingensmith, Christopher M. Dellin, J. Andrew Bagnell, and Siddhartha S. Srinivasa. CHOMP: Covariant Hamiltonian Optimization for Motion Planning. International Journal of Robotics Research, 2013.
(In print)

Download

(unavailable)

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_etal_ijrr13,
  author = {Matt Zucker and Nathan Ratliff and Anca D. Dragan and Mihail N. Pivtoraiko and Matthew Klingensmith and Christopher M. Dellin and J. Andrew Bagnell and Siddhartha S. Srinivasa},
  title = {CHOMP: Covariant Hamiltonian Optimization for Motion Planning},
  journal = {International Journal of Robotics Research},
  year = {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.  },
  bib2html_pubtype = {Journal Papers},
  bib2html_rescat = {Mobile Manipulation},
  wwwnote = {(In print)}
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed May 15, 2013 18:16:05