evoBOT – Design and Learning-Based Control of a Two-Wheeled Compound Inverted Pendulum Robot
Patrick Klokowski, Julian Eßer, Nils Gramse, Benedikt Pschera, Marc Plitt, Frido Feldmeier, Shubham Bajpai, Christian Jestel, Nicolas Bach, Oliver Urbann, Sören Kerner
Abstract
This paper introduces evoBOT, a novel robot platform for research on highly dynamic locomotion and human-machine interaction. evoBOT is capable of performing complex tasks such as handovers or manipulation while moving at high speeds. We provide an overview of the robot's core features and the underlying design decisions on both the mechanical and the electronic level. Moreover, we propose a reinforcement learning (RL) based control approach for training highly dynamic motions that is evaluated on a first set of robotic tasks, including robust balancing and dynamic locomotion. Lastly, we conduct extensive benchmarking on the adopted sim-to-real methods and present an initial sim-to-real pipeline for first transfer of the trained policies to the real robot. To accelerate robotics research in this direction, the full simulation model of the robot is released as open-source.