Navigation Among Movable Obstacles with learned dynamic constraints
Jonathan Scholz, Nehchal Jindal, Martin Levihn, Charles L. Isbell, Henrik I. Christensen
Abstract
In this paper we present the first planner for the problem of Navigation Among Movable Obstacles (NAMO) on a real robot that can handle environments with under-specified object dynamics. This result makes use of recent progress from two threads of the Reinforcement Learning literature. The first is a hierarchical Markov-Decision Process formulation of the NAMO problem designed to handle dynamics uncertainty. The second is a physics-based Reinforcement Learning framework which offers a way to ground this uncertainty in a compact model space that can be efficiently updated from data received by the robot online. Our results demonstrate the ability of a robot to adapt to unexpected object behavior in a real office scenario.
BibTeX
@inproceedings{iros2016_navigationamongm,
title = {Navigation Among Movable Obstacles with learned dynamic constraints},
author = {Jonathan Scholz and Nehchal Jindal and Martin Levihn and Charles L. Isbell and Henrik I. Christensen},
booktitle = {IROS 2016},
year = {2016}
}