BiRoDiff: Diffusion policies for bipedal robot locomotion on unseen terrains
This work addresses the problem of enabling bipedal robots to navigate unknown terrains for applications like disaster response and exploration, representing an incremental improvement in robot control methods.
The authors tackled bipedal robot locomotion on unseen terrains by introducing a lightweight diffusion model-based controller that learns from offline data, achieving generalization to multiple terrains and high-frequency control steps with reduced computational requirements compared to typical generative models.
Locomotion on unknown terrains is essential for bipedal robots to handle novel real-world challenges, thus expanding their utility in disaster response and exploration. In this work, we introduce a lightweight framework that learns a single walking controller that yields locomotion on multiple terrains. We have designed a real-time robot controller based on diffusion models, which not only captures multiple behaviours with different velocities in a single policy but also generalizes well for unseen terrains. Our controller learns with offline data, which is better than online learning in aspects like scalability, simplicity in training scheme etc. We have designed and implemented a diffusion model-based policy controller in simulation on our custom-made Bipedal Robot model named Stoch BiRo. We have demonstrated its generalization capability and high frequency control step generation relative to typical generative models, which require huge onboarding compute.