Abstract:
Actively exploring and mapping an unknown environment requires integration of both simultaneous localization and mapping (SLAM) and path planning methods. Path planning relies on a map that contains free and occupied space information and is efficient to query, while the role of SLAM is to keep the map consistent as new measurements are continuously added. A key challenge lies in ensuring a map representation compatible with both these objectives: that is, a map that maintains free space information for planning but can also adapt efficiently to dynamically changing pose estimates from a graph-based SLAM system.

In this talk, I will discuss methods ranging from purely local to global occupancy mapping. We present an online mapping approach that can be corrected for accumulated drift efficiently based on incremental solutions from a sparse graph-based SLAM optimization. We’ll demonstrate use of such a representation for implementing an underwater SLAM system in which the robot actively plans paths to generate accurate 3D scene reconstructions. We evaluate performance for both simulated and real-world datasets.

Committee:
Michael Kaess (advisor)
David Wettergreen
Martial Hebert
Kumar Shaurya Shankar