A Kung Fu Athlete Bot That Can Do It All Day: Highly Dynamic, Balance-Challenging Motion Dataset and Autonomous Fall-Resilient Tracking

TL;DR

This paper introduces KungFuAthlete, a high-dynamic martial arts motion dataset, and proposes a unified policy for high-dynamic motion tracking and fall recovery to enhance humanoid robustness.

Contribution

The paper presents a new martial arts motion dataset and a unified learning framework for dynamic motion tracking and fall recovery in humanoid robots.

Findings

Jump subset shows higher velocities than existing datasets.

The unified policy improves stability during high-dynamic motions.

Robots can recover autonomously from falls during complex movements.

Abstract

Current humanoid motion tracking systems can execute routine and moderately dynamic behaviors, yet significant gaps remain near hardware performance limits and algorithmic robustness boundaries. Martial arts represent an extreme case of highly dynamic human motion, characterized by rapid center-of-mass shifts, complex coordination, and abrupt posture transitions. However, datasets tailored to such high-intensity scenarios remain scarce. To address this gap, we construct KungFuAthlete, a high-dynamic martial arts motion dataset derived from professional athletes' daily training videos. The dataset includes ground and jump subsets covering representative complex motion patterns. The jump subset exhibits substantially higher joint, linear, and angular velocities compared to commonly used datasets such as LAFAN1, PHUMA, and AMASS, indicating significantly increased motion intensity and complexity. Importantly, even professional athletes may fail during highly dynamic movements. Similarly, humanoid robots are prone to instability and falls under external disturbances or execution errors. Most prior work assumes motion execution remains within safe states and lacks a unified strategy for modeling unsafe states and enabling reliable autonomous recovery. We propose a novel training paradigm that enables a single policy to jointly learn high-dynamic motion tracking and fall recovery, unifying agile execution and stabilization within one framework. This framework expands robotic capability from pure motion tracking to recovery-enabled execution, promoting more robust and autonomous humanoid performance in real-world high-dynamic scenarios.