Obstacle Avoidance for the Segway Robotic Mobility Platform

This paper presents an obstacle avoidance system for the Segway Robotic Mobility Platform (RMP). The system consists of four main modules: terrain mapping, terrain traversability analysis, path planning, and motion control. The main sensor in our system is a forward/downward-looking 2-D Sick laser rangefinder. The terrain mapping module registers realtime laser range data into a grid-type elevation map. The traversal property of the elevation map is then analyzed by the traversability analysis module, which transforms the elevation map into a traversability map.The paper introduces a new concept called “traversability field histogram,” which is used to transform the traversability map into a one-dimensional polar histogram. Finally, the path planning module determines the steering and velocity commands and sends them to the motion control module.