Action/perception-oriented robot software design: An application in off-road terrain

Abstract

In this paper a combined action/perception-oriented approach for behavior-based robot software design is proposed. Action-oriented in that context denotes that the requirements for sensor information are directly derived from the navigational tasks on the control level. Perception-oriented design on the other hand determines further supporting behaviors from the data available. Taking into account the diversity of sensors and perception algorithms on the one hand and the need for a thorough control methodology on the other, the authors introduce a generic concept for sensor data abstraction through virtual sensors. Virtual sensors are standardized data representations which offer a clear interface for behavior-based robot control systems. The design method presented accounts for both, flexibility on the sensor processing layer and consistent structures on the control layer supporting reusability, extensibility, and traceability. Results documenting the applicability to complex robotic systems are shown in a case study about the off-road platform RAVON.