Biorobotics Laboratory BioRob

Hybrid Learning procedure for one asymmetric arbitrary robot shape

Unfortunately this movie is not yet available in a format compatible with recent browsers, and Flash Player is not available or is disabled.. You can try enabling Flash Player in your browser, or as an alternative, you can download the movie (see below) for local viewing with your favorite video player.

Download

Description

In this video, you can see how the hybrid framework of optimizer-controller is working on one asymmetric arbitrary robot shape built by Roombots. The robot is using CPG-based control; a network of phase oscillators, one oscillator per DoF. The main idea here is not to optimize only the CPG parameters, but also the structure of the CPG. Different structures are defined by using different movement patterns in the degrees of freedom (including Oscillation, Rotation (clockwise and counter-clockwise, and Lock modes). The robot experiences different configurations of movement patterns in the first phase of optimization. In the second phase, the best configuration is kept fixed and the open parameters for its movement patterns are optimized.