Legged robots adapt quickly to different shoes for better walking
SHOES: Sim-to-real Hardware-adaptation via On-policy Expansion of Skills for Legged Robots
Robotics
Summary
Robots that walk can struggle when their feet change, like when you wear new shoes. The authors designed a method called SHOES that helps robots quickly adjust to these changes without relearning everything from scratch. Their approach tweaks small parts of the robot’s walking control while keeping the original walking style mostly the same. They tested this on real robots wearing human shoes and found it works better than other methods.
What this means in practice
- •For robotics engineers: Enable legged robots to maintain walking performance when hardware foot properties change, such as adding shoes or attachments.
- •For robotics deployment teams: Adapt walking controllers on deployed robots efficiently within defined safe workspaces for real-world terrains and conditions.
Authors
Kota Tsuruhara, Tsung-Yuan Chen, Kento Kawaharazuka
Abstract
Humans expand their locomotion capability by wearing appropriate footwear, such as hiking boots for mountains or skates for ice. Footwear changes the ground-contact interface and enables traversal of otherwise difficult terrain. In contrast, locomotion controllers are typically trained for a fixed morphology, and their performance can degrade when shoes alter foot geometry, mass, and friction. We propose SHOES, a sample-efficient framework for adapting locomotion policies to footwear-induced morphology changes. SHOES freezes a simulation-trained nominal policy and fine-tunes only lightweight, identity-initialized modulation modules on the robot, preserving the initial behavior while enabling efficient hardware adaptation. We also introduce SafeBox, a workspace-aware waypoint sampler that constrains online adaptation within a user-defined workspace. The simulation results with a shoe-equipped Unitree Go2 show that SHOES substantially recovers locomotion performance after footwear-induced morphology changes using limited additional adaptation. Under the same adaptation budget, SHOES outperforms FiLM-only, Linear Adapter-only, and residual-RL baselines. Real-world experiments on a Unitree Go2 fitted with human shoes further evaluate the effectiveness of SHOES for hardware deployment.