Robot Motion Planning with Dynamics as Hybrid Search

Authors

  • Erion Plaku Catholic University of America

DOI:

https://doi.org/10.1609/aaai.v27i1.8544

Keywords:

Motion planning, discrete search, dynamics

Abstract

This paper presents a framework for motion planning with dynamics as hybrid search over the continuous space of feasible motions and the discrete space of a low-dimensional workspace decomposition. Each step of the hybrid search consists of expanding a frontier of regions in the discrete space using cost heuristics as guide followed by sampling-based motion planning to expand a tree of feasible motions in the continuous space to reach the frontier. The approach is geared towards robots with many degrees-of-freedom (DOFs), nonlinear dynamics, and nonholonomic constraints, which make it difficult to follow discrete-search paths to the goal, and hence require a tight coupling of motion planning and discrete search. Comparisons to related work show significant computational speedups.

Downloads

Published

2013-06-29

How to Cite

Plaku, E. (2013). Robot Motion Planning with Dynamics as Hybrid Search. Proceedings of the AAAI Conference on Artificial Intelligence, 27(1), 1415-1421. https://doi.org/10.1609/aaai.v27i1.8544