Collision prevention for rehabilitation robots with mapped virtual reality

Abstract

In service robotics safe prevention of unsanctioned collisions with humans or other objects in the workspace is significantly important. That can be done by a real time distance observation. But immediate in the work space this task is technical and is very difficult to implement at the moment. The proposed solution is to use a virtual world which maps the real spatial situation in extreme simplified form, but at the same time reflects the main spatial correlations. In contrast to common VR, which task is to reflect the real world as exactly as possible, we propose a mapped virtual reality (MVR). The obstacles from the real world are mapped into this virtual reality as simple shapes, covering the real objects. The robot configuration is transferred from the real robot and is permanently updated. So the virtual world reflects the real macro-situation, and the distance can be calculated now without difficulty instead of it needing to be measured. The task of external sensors (e.g. cameras) can be reduced to the detection of new objects, which have to be mapped into the MVR, instead of observing all obstacles in the workspace and measuring distances. Such task distribution increases the safety of manipulation by reduction of technical complexity.