Learning to Walk by Steering: Perceptive Quadrupedal Locomotion in Dynamic Environments
This work addresses robust and agile walking for quadrupedal robots in cluttered and moving obstacle settings, representing an incremental improvement in hierarchical control methods.
The paper tackles perceptive locomotion for quadrupedal robots in dynamic environments by introducing PRELUDE, a hierarchical learning framework that combines imitation learning for navigation and reinforcement learning for gait generation, demonstrating effectiveness in simulation and hardware experiments.
We tackle the problem of perceptive locomotion in dynamic environments. In this problem, a quadrupedal robot must exhibit robust and agile walking behaviors in response to environmental clutter and moving obstacles. We present a hierarchical learning framework, named PRELUDE, which decomposes the problem of perceptive locomotion into high-level decision-making to predict navigation commands and low-level gait generation to realize the target commands. In this framework, we train the high-level navigation controller with imitation learning on human demonstrations collected on a steerable cart and the low-level gait controller with reinforcement learning (RL). Therefore, our method can acquire complex navigation behaviors from human supervision and discover versatile gaits from trial and error. We demonstrate the effectiveness of our approach in simulation and with hardware experiments. Videos and code can be found at the project page: https://ut-austin-rpl.github.io/PRELUDE.