Abstract: In a multilegged walking robot several legs usually have ground contact and thereby form a closed kinematic chain. The control of such a system is generally assumed to require the explicit calculation of the body kinematics. Such a computation requires knowledge concerning all relevant joint angles as well as the segment lengths. Here, we propose a biologically inspired solution that does not need such a body model. This is done by using implicit communication through the body mechanics (embodiment) and a local positive velocity feedback strategy (LPVF) on the single joint level. In this control scheme the locally measured joint velocity of an elastic joint is fed into the same joint during the next time step to maintain the movement. At the same time, an additional part of this joint controller observes the mechanical joint power to confine the positive feedback. This solution does not depend on changes of the geometry, e.g. length of individual segments, and allows for a simple solution of negotiation of curves. The principle is tested in a dynamics simulation on a six-legged walker and, for the first time, also on a real robot.
