Humanoid robots navigate cluttered spaces with steerable collision avoidance
SWAP: Test-Time Steerable Humanoid Whole-Body Collision Avoidance
Robotics
Summary
Humanoid robots need to safely move through crowded or tight spaces without bumping into things or falling over. Existing methods often have a hard time handling both balance and avoiding obstacles at the same time, especially when the robot’s sensors provide complex information. The authors propose a new approach called SWAP that splits the problem into two parts: one that plans possible safe paths around obstacles, and another that controls the robot’s movement and balance. Their system learns by practice and can adjust its behavior on the fly to better suit different goals like moving faster or maintaining a certain posture.
What this means in practice
- •For robotics engineers: Enable humanoid robots to safely navigate cluttered human environments by coordinating whole-body motion and balance simultaneously.
- •For logistics automation teams: Improve delivery and inspection robots’ ability to move through dynamic, obstacle-filled warehouses without collisions.
Authors
Zeji Yi, Guanqi He, Xiaofeng Guo, Guannan Qu, Pieter Abbeel, Yan Duan, Karen Liu, Guanya Shi
Abstract
Humanoid robots operating in human-centric environments must coordinate the entire body to traverse tight, cluttered spaces while maintaining balance. Existing methods often struggle to jointly consider dynamic stability and collision avoidance from high-dimensional perceptual inputs. Moreover, for humanoids, safe behavior is inherently multimodal: the same obstacle may admit multiple valid traversals, which is difficult to represent with a single deterministic policy. To address these challenges, we propose SWAP (Steerable Whole-body Avoidance Policy), a hierarchical framework that separates collision-aware decision making from stabilization. A high-level, perception-conditioned diffusion policy generates multimodal, collision-aware motion proposals, while a low-level whole-body RL controller tracks these proposals and maintains dynamic balance. To efficiently train the high-level policy, we obtain scalable supervision via hindsight labeling: we roll out the low-level policy under randomized commands, place obstacles only in the space that each executed motion did not sweep, so the motion is collision-free by construction, and re-render the perception the robot would have seen. At deployment, Monte Carlo sampling with simple cost signals steers the diffusion model toward safe, task-aligned behaviors without heavy reward tuning. Experiments in simulation and on a real Unitree G1 humanoid show reliable avoidance with static and dynamic obstacles. Test-time steering further enables customization, improving targeted rewards (e.g., speed, orientation, or posture) by 34% on average while maintaining a high collision avoidance rate. Together, these results support a practical solution to humanoid whole-body collision avoidance with test-time steerability. Project website: https://iscoyizj.github.io/SWAP-steerable-humanoid-oa-website/