Towards Total Coverage in Autonomous Exploration for UGV in 2.5D Dense Clutter Environment

Recent developments in 3D reconstruction systems enable to capture an environment in great detail. Several studies have provided algorithms that deal with a path-planning problem of total coverage of observable space in time-efficient manner. However, not much work was done in the area of globally optimal solutions in dense clutter environments. This paper presents a novel solution for autonomous exploration of a cluttered 2.5D environment using an unmanned ground mobile vehicle, where robot locomotion is limited to a 2D plane, while obstacles have a 3D shape. Our exploration algorithm increases coverage of 3D environment mapping comparatively to other currently available algorithms. The algorithm was implemented and tested in randomly generated dense clutter environments in MATLAB.