2018/02/12 by Risto Kojcev, Kojcev, Risto, Nora Etxezarreta +5 · 1 citation
Computer Science · Engineering · #Modular Robots and Swarm Intelligence #Reinforcement Learning in Robotics #Robot Manipulation and Learning #cs.RO
paper · pdf · doi:10.48550/arxiv.1802.04132
arxiv created 2018/02/12 · arxiv updated 2018/02/13
We argue that hierarchical methods can become the key for modular robots achieving reconfigurability. We present a hierarchical approach for modular robots that allows a robot to simultaneously learn multiple tasks. Our evaluation results present an environment composed of two different modular robot configurations, namely 3 degrees-of-freedom (DoF) and 4DoF with two corresponding targets. During the training, we switch between configurations and targets aiming to evaluate the possibility of training a neural network that is able to select appropriate motor primitives and robot configuration to achieve the target. The trained neural network is then transferred and executed on a real robot with 3DoF and 4DoF configurations. We demonstrate how this technique generalizes to robots with different configurations and tasks.