Humanoid robots learn flexible multi-directional kicking and walking skills
Locomotion-Grounded Humanoid Soccer: Task-Gated Reinforcement Learning of a Multi-Directional Kicking Library
Robotics
Summary
Humanoid robots usually learn to kick balls by following specific motions tied to approaching the ball in one way. This paper trains the robot to first move around flexibly and then add different kicking moves on top, letting it kick in many directions including sideways and backwards. The researchers tested this on a real robot with seven different kicks and showed it could kick accurately while keeping balance. Their approach helps the robot smoothly combine walking and kicking without rigid motion scripts.
What this means in practice
- •For robotics engineers: Create humanoid robots that move flexibly and skillfully kick balls in multiple directions for tasks like robot soccer or dynamic interaction.
- •For robotics platform developers: Develop modular robot control systems where locomotion supports a wide range of task-specific skills, simplifying transitions and recovery.
- •For entertainment robotics companies: Build humanoid robots capable of diverse, realistic kicking motions for shows and interactive games.$Commercial implications: This library enables robots to perform multiple omni-directional kicks fluidly, improving entertainment value for robotics products.
Authors
Abu Hanif Muhammad Syarubany, Jaehyun Jang, Hwanhee Kim, Kyuwon Kim, Seungyeon Ryu, Chang D. Yoo
Abstract
Recent humanoid soccer systems make motion tracking the substrate and derive locomotion from it, typically by steering a motion-reference anchor toward the ball. This yields strong shooting results, but locomotion is trained only on the narrow, deterministic command distribution ball approach induces, never evaluated as a capability in its own right. We invert the stack: a general, command-conditioned locomotion policy is trained first as the substrate, and N motion-guided kicking skills are added on top as task-gated layers, so the reachable gait space is set by the locomotion curriculum rather than any reference clip. Because every skill starts from and returns to this same commandable state, locomotion also becomes a composition hub (O(N) transitions rather than O(N^2)), and post-strike stabilisation is handed back to the trained controller rather than scripted per clip. We instantiate this on a 29-DoF Unitree G1 with seven retargeted kicking skills spanning 259.5 degrees of nominal aim direction, including lateral, rearward and weak-foot strikes a single forward-facing reference cannot express, and report shooting accuracy alongside command-tracking, terrain and push-recovery results with the full skill library attached, an axis prior humanoid soccer systems do not report. The library is validated on hardware across forward, lateral, rearward and commanded approaches.