Hierarchical Freespace Planning for Navigation in Unfamiliar Worlds

Authors

  • Raj Korpan The Graduate Center of The City University of New York
  • Susan L. Epstein Hunter College of The City University of New York The Graduate Center of The City University of New York

DOI:

https://doi.org/10.1609/icaps.v31i1.16015

Keywords:

Learning Methods For Robot Planning, Planning With Uncertainty In Robotics, Representation And Acquisition Of Planning Models, Plan Execution, Failure Detection And Recovery

Abstract

Autonomous navigation in a large, complex space requires a spatial model, but the construction of a detailed map is costly. This paper demonstrates how two kinds of exploration support an alternative to metric mapping, one that facilitates robust hierarchical path planning. High-level exploration builds a global spatial model whose connectivity supports an effective, efficient, freespace planner, while low-level, target-driven exploration addresses areas where the global model lacks knowledge. Empirical results demonstrate successful and efficient travel in three challenging worlds.
ICAPS-21 Proceedings Cover

Downloads

Published

2021-05-17

How to Cite

Korpan, R., & Epstein, S. L. (2021). Hierarchical Freespace Planning for Navigation in Unfamiliar Worlds. Proceedings of the International Conference on Automated Planning and Scheduling, 31(1), 663-672. https://doi.org/10.1609/icaps.v31i1.16015

Issue

Vol. 31 (2021): Proceedings of the Thirty-First International Conference on Automated Planning and Scheduling

Section

Special Track on Robotics