Reinforcement Learning from Wild Animal Videos

We propose to learn legged robot locomotion skills by watching thousands of wild animal videos from the internet, such as those featured in nature documentaries. Indeed, such videos offer a rich and diverse collection of plausible motion examples, which could inform how robots should move. To achieve this, we introduce Reinforcement Learning from Wild Animal Videos (RLWAV), a method to ground these motions into physical robots. We first train a video classifier on a large-scale animal video dataset to recognize actions from RGB clips of animals in their natural habitats. We then train a multi-skill policy to control a robot in a physics simulator, using the classification score of a third-person camera capturing videos of the robot's movements as a reward for reinforcement learning. Finally, we directly transfer the learned policy to a real quadruped Solo. Remarkably, despite the extreme gap in both domain and embodiment between animals in the wild and robots, our approach enables the policy to learn diverse skills such as walking, jumping, and keeping still, without relying on reference trajectories nor skill-specific rewards.

Whole-body MPC and sensitivity analysis of a real time foot step sequencer for a biped robot Bolt

This paper presents a novel controller for the bipedal robot Bolt. Our approach leverages a whole-body model predictive controller in conjunction with a footstep sequencer to achieve robust locomotion. Simulation results demonstrate effective velocity tracking as well as push and slippage recovery abilities. In addition to that, we provide a theoretical sensitivity analysis of the footstep sequencing problem to enhance the understanding of the results.