Simulated Visually-Guided Paw Placement During Quadruped Locomotion

Autonomous adaptive locomotion over irregular terrain is one important topic in robotics research. In this article, we focus on the development of a quadruped locomotion controller able to generate locomotion and reaching visually acquired markers. The developed controller is modeled as discrete, sensory driven corrections of a basic rhythmic motor pattern for locomotion according to visual information and proprioceptive data, that enables the robot to reach markers and only slightly perturb the locomotion movement. This task involves close-loop control and we will thus particularly focus on the essential issue of modeling the interaction between the central nervous system and the peripheral information in the locomotion context. This issue is crucial for autonomous and adaptive control, and has received little attention so far. Trajectories are online modulated according to these feedback pathways thus achieving paw placement. This modeling is based on the concept of dynamical systems whose intrinsic robustness against perturbations allows for an easy integration of sensory-motor feedback and thus for closed-loop control. The system is demonstrated on a simulated quadruped robot which online acquires the visual markers and achieves paw placement while locomotes.