Proceedings:
Book One
Volume
Issue:
Proceedings of the International Conference on Automated Planning and Scheduling, 31
Track:
Special Track on Robotics
Downloads:
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.
DOI:
10.1609/icaps.v31i1.16015
ICAPS
Proceedings of the International Conference on Automated Planning and Scheduling, 31