A modularized sensitive skin for motion planning in uncertain environments

Abstract

One way to avoid obstacles without modeling the environment is to use a sensor-based sensitive skin covering the body of the robot along with proper sensor-based motion planning algorithms. Compared to prior attempts, the system developed at the UW-Madison Robotics Lab and discussed here presents a system that can be easily reconfigured for a variety of applications. This is accomplished via modularized sensitive skin patches that can be connected in various ways, and a hierarchical control architecture that can be easily modified for various system configurations. In the implemented version, the skin contains about 1000 infrared sensors; it can be easily expanded, with minor changes. The system has been successfully tested in preliminary trials.