Using Passages to Support Off-Road Robot Navigation

Abstract

Abstract:In this paper an approach for the detection of passages and their use in autonomous off-road robot navigation is presented. The authors argue that many two-layered architectures of robot navigation systems suffer from the gap between the typically coarse-grained high-level path-planning and the basically reactive low-level collision avoidance. In this context, passages shall be defined as paths leading through obstacles. The proposed approach is based on the idea that passages in the proximity to the robot should be evaluated with respect to their relevance for reaching the target area in order to avoid local detours by following suitable passages. The detection and assessment of passages is based on virtual sensors, a standardized data representation offering a unified, straightforward, and flexible retrieval mechanism for accessing the data provided by different sensor systems. For the evaluation of passages the authors introduce the concept of virtual sensor probes which can move independently from the robot. That way the point of view on the environment information can be tailored to support the detection and evaluation strategy. The proposed approach was deployed on the mobile off-road platform RAVON which serves as a testbed for the experiments carried out in the context of this work.