Learning to Play Like a Pro: Adaptive Motion Planning and Tracking for Humanoid Robots
This White Paper provides roboticists and control engineers with a comprehensive overview of how motion planning and motion tracking can be decoupled to preserve professional athletic style in humanoid robots, and why adaptive, speed-aware control is essential for closing the gap between simulation and real-world deployment. What you will learn about: Why combining a professional athlete’s motion…
This white paper offers roboticists and control engineers an in-depth look at how motion planning and tracking can be separated to maintain professional athlete-level movements in humanoid robots. It explains why merging a high-level planner with a low-level tracker is a challenge in humanoid ball sports robotics, and how dividing these functions helps achieve this goal.
The paper also explains how motion data captured from video and motion capture can be recreated, retargeted, and physically adjusted to fit reference motions that a humanoid robot can safely follow. It discusses how the transition from simulation to real-world use can cause tracking errors to build up, and how training a tracker on randomly varied execution speeds, combined with a learned speed adapter in the planner, can enhance reliability on actual hardware.
The adaptive framework's effectiveness is demonstrated on two humanoid platforms, with one example being full-size, real-world serving performed without any motion capture system.
Written by urgent.news from IEEE Spectrum's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
