Humanoid robots learn to walk on loose sand and gravel terrain
Learning Terrain-Adaptive Humanoid Locomotion on Granular Terrain
Robotics
Summary
Walking on loose materials like sand and gravel is hard for robots because the ground changes shape when stepped on. The authors created a new computer model that better predicts how feet push into and move through these loose surfaces. They trained robots in simulations using this realistic model, allowing the robots to learn how to walk steadily on these tricky grounds. The robots then successfully walked on real sand and gravel without needing extra adjustments. This is the first time humanoid robots have done this well on real loose materials.
What this means in practice
- •For robotics engineers: Enable humanoid robots to walk reliably over sandy and loose ground by using a physics-based contact model that generalizes to new terrain types.
- •For field robotics operators: Operate humanoid robots in outdoor environments with loose soils like beaches or deserts thanks to adaptive locomotion trained with realistic terrain simulations.
Authors
Junnosuke Kamohara, Feiyang Wu, Andy Ningan Zong, Daniel I. Goldman, Yashwanth Nakka, Seth Hutchinson, Ye Zhao
Abstract
Humanoid locomotion on granular terrain remains a significant challenge due to its complex foot-terrain interaction dynamics that are difficult to model. Existing approaches either ignore granular contact dynamics or incorporate simplified normal force models with heuristic tangential components. In this work, we present a physics-grounded granular contact model based on three-dimensional resistive force theory (3D RFT) and efficiently simulate granular terrain for reinforcement learning (RL) training. Unlike traditional rigid contact models and simplified granular contact models with ad-hoc heuristics, our contact solver produces physically accurate granular intrusion dynamics without resorting to heuristics. It captures realistic penetration and tangential drag during training, enabling the policy to learn behaviors that transfer reliably to real-world granular terrain where rigid contact models fail. To adapt to varying terrain conditions, we train a terrain-adaptive locomotion controller via teacher-student RL, using a variational autoencoder to encode terrain information into a compact latent representation. Simulation studies using material point method (MPM) with NVIDIA Newton demonstrate that our method generalizes to unseen granular terrains, achieves a significantly higher success rate than baselines, and demonstrates zero-shot terrain identification and adaptation. We further validate our approach through extensive hardware experiments across diverse real-world granular terrains including basalt, dry sand, and beach sand. To the best of our knowledge, this is the first demonstration of agile humanoid locomotion on real-world granular terrain. Project page: https://humanoid-gm-locomotion.github.io/HUMANOID-GM/