Title: Topological Path Planning for Mobile Robot Applications

Abstract:

Many path planning problems in mobile robot applications can be solved more efficiently in the topological space. By using the language of topology, the richer spatial information failed to captured by graph/grid-based map representations can be explicitly expressed and exploited. With that, it is possible to solve the path planning problem in lower dimensions without loss of the algorithmic completeness. In this talk, two examples will be given to demonstrate the benefits of topological path planning. In particular, I will first talk about the Crowd Navigation problem, where our algorithm enables the robot to efficiently plan for and navigate in highly cluttered and dynamic environments. The second example will be our entry to the DARPA Subterranean Challenge (SubT), where the Depth-First Search algorithm is realized in a topological manner for the continuous space, enabling our robot to explore large-scale subterranean tunnels much more effectively than using a traditional planner.

Committee:

Howie Choset (Co-advisor)

Matthew J. Travers (Co-advisor)

John M. Dolan

Wenhao Luo