Optimal navigation and object finding without geometric maps or localization

Abstract

In this paper we present a dynamic data structure, useful for robot navigation in an unknown, simplyconnected planar environment. The guiding philosophy in this work is to avoid traditional problems such as complete map building and localization by constructing a minimal representation based entirely on critical events in online sensor measurements made by the robot. Furthermore, this representation provides a sensor-feedback motion strategy that guides the robot along an optimal trajectory between any two environment locations, and allows the search of static targets, even though there is no geometric map of the environment. We present algorithms for building the data structure in an unknown environment, and for using it to perform optimal navigation. We implemented these algorithms on a real mobile robot. Results are presented in which the robot builds the data structure online, and is able to use it without needing a global reference frame. Simulation results are also shown to demonstrate how the robot is able to find interesting objects in the environment.

DOI: 10.1109/ROBOT.2003.1241638

Extracted Key Phrases

9 Figures and Tables

Statistics

01020'04'06'08'10'12'14'16
Citations per Year

71 Citations

Semantic Scholar estimates that this publication has 71 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Tovar2003OptimalNA, title={Optimal navigation and object finding without geometric maps or localization}, author={Benjam{\'i}n Tovar and Steven M. LaValle and Rafael Murrieta-Cid}, booktitle={ICRA}, year={2003} }