EG
A humanoid robot performing a soccer kick in a laboratory environment
ResearchJune 12, 2026Embodied Global Team

RoboNaldo: Humanoid Robot Achieves Human-Level Soccer Shooting via Motion-Guided Reinforcement Learning

Researchers introduce RoboNaldo, a three-stage motion-guided curriculum RL framework enabling humanoid robots to perform high-impulse whole-body interactions. On Unitree G1, the system achieves 0.73m average shooting error from 3m distance with ball velocities reaching 13.10 m/s, representing 59-71% of professional human shot speed.

Reading in English

A research team has developed RoboNaldo, a groundbreaking reinforcement learning framework that enables humanoid robots to perform accurate soccer shooting comparable to professional human athletes.

The Innovation

RoboNaldo employs a three-stage motion-guided curriculum reinforcement learning approach. The framework first learns a stable whole-body kicking prior, then adapts to free-kick settings with stationary balls at random positions, and finally extends to moving-ball shooting through a locomotion-command and kick-trigger interface.

Key Results

On a real Unitree G1 humanoid robot with onboard perception, RoboNaldo achieved remarkable results:

  • Free-kick error: 48.6% lower than prior work baselines
  • Shoot velocity: 2.96x faster than previous methods
  • Average target shooting error: 0.73m (free-kick) and 0.86m (moving-ball) from 3m distance
  • Ball velocity: 13.10 m/s, representing 59-71% of reported professional open-play shot speed

Technical Approach

The system uses a single human-kick reference as a scaffold and progressively shifts optimization towards shooting performance. A high-level heuristic planner controls the interface during training, while alternative controllers can drive the same low-level policy at inference.

This research demonstrates that with proper curriculum design, humanoid robots can master complex dynamic interactions that require coordination across the entire body.