Experiments in vision-guided robot walking in a structured scenario

Locomotion of a biped robot in a scenario with obstacles requires a high degree of coordination between perception and walking. This article presents key ideas of a vision-based strategy for guidance of walking robots in structured scenarios. Computer vision techniques are employed for reactive adaptation of step sequences allowing a robot to step over or upon or walk around obstacles. A highly accurate visual feedback is achieved by a combination of line-based scene analysis and real-time feature tracking. The proposed vision-based approach was evaluated by experiments with a real humanoid robot.