Intelligent low-cost mobility

Autonomous low-cost mobility of robots has been a challenging problem for quite a long time. In this paper the typical problems of sonar based autonomous navigation and the authors´ solutions to overcome them are discussed. The authors have created, robust modules for sonar data fusion and safe steering which significantly improve known methods. There are furthermore robot control behaviors which offer specific competence to solve high-level tasks. These behaviors build a hierarchical architecture but have the ability to assess their respective task and autonomously suggest a different, more competent behavior to continue. Thus, the behaviors work together as distributed competencies. The concept described here is being evaluated in a system on the authors´ experimental robot ROAMER. The available modules already operate robustly in cluttered office environments