Intelligent Behaviors in Outdoor Environments

A. Birk, K. Pathak, J. Poppinga, S. Schwertfeger, and W. Chonnaparamutt (Germany)

Keywords

Robot Sensing, Artificial Intelligence, Motion Planning

Abstract

The Jacobs Rugbots - derived from ”rugged robot” - are capable of intelligent behaviors up to full autonomy in out door environments. One crucial aspect for the according intelligent behaviors is the capability to detect negotiable terrain in a very fast and robust manner. Our approach uses range data from 3D sensors like a time-of-flight Swis sranger, respectively a stereo camera. The range data is processed by a Hough transform with a special 3D param eter space, which is chosen such that its bins correspond to planes that can be negotiated by the robot. Extensive experiments with different prototypical indoor and outdoor ground types are presented, which can be clearly classified with respect to drivability. Seven datasets, two recorded indoor and five outdoor under very varying conditions, are used for testing. Drivability is robustly detected with suc cess rates ranging between 83% and 100% for the Swiss ranger and between 98% and 100% for the stereo camera. The complete processing time per snapshot is in the order of 5 to 50 msec.

Important Links:



Go Back