Bony robots have achieved impressive feats of dynamic locomotion in challenging unstructured terrain. However, in entertainment applications, the design and control of these robots face additional challenges in engaging human audiences. This work aims to unite expressive artist-driven movements and robust dynamic mobility for legged robots. To this end, we introduce a novel bipedal robot, designed with an emphasis on character-driven mechanical features. We present a reinforcement learning-based control architecture to robustly execute artistic movements depending on command signals. At runtime, these command signals are generated by an animation engine that composes and combines multiple animation sources. Finally, an intuitive operator interface enables real-time show performances with the robot. The complete system results in a believable robot character and paves the way for improved human-robot engagement in various contexts, in entertainment robotics and beyond.

Please take the opportunity to connect and share this video with your friends and family if you find it helpful.