MASc Seminar Notice: Path Planning Framework for Unmanned Ground Vehicles on Uneven Terrains

Candidate: Olzhas Adiyatov
Title: Path Planning Framework for Unmanned Ground Vehicles on Uneven Terrains
Date: August 9, 2022
Time: 14:00
Place: online
Supervisor(s): Smith, Stephen L. - Fidan, Baris

Abstract:
In this thesis, I address the problem of long-range path planning on uneven terrain for non-holonomic wheeled mobile robots (WMR). Uneven terrain path planning is essential for search-and-rescue, m surveillance, military, humanitarian, agricultural, constructing missions, etc. These missions necessitate generation of a feasible sequence of waypoints, or reference states, to navigate a wheeled mobile robot (WMR) from the initial location to the final target location through the uneven terrain. Feasibility of navigating through a given path over an uneven terrain can be undermined by various terrain features. Examples of such features are loose soil, vegetation, boulders, steeply sloped terrain, or a combination of all these elements. I propose a three-stage framework that solves the problem of rapid path planning on a long range. These stages improve the solution quality at each stage of the path planning framework. RRT-Connect is used for rapid discovery of the feasible solution. Followed by the Informed RRT* that improves the feasible solution. Finally, shortcut heuristics locally improves solution. The PCA-based accelerated version of the traversability estimation on point cloud was proposed to improve the computational speed of the path planning algorithms employed in the path planning framework. The benchmarks demonstrated the efficacy of the approach.