Learning Motion Skills with Adaptive Assistive Curriculum Force in Humanoid Robots

TL;DR

This paper introduces A2CF, a dual-agent learning framework that uses adaptive assistive forces to accelerate humanoid robot skill acquisition, achieving faster convergence and more robust, support-free policies.

Contribution

The paper presents a novel adaptive assistive curriculum force method that improves learning efficiency and robustness in humanoid robot motion skills.

Findings

Achieves 30% faster convergence than baseline methods.

Reduces failure rates by over 40%.

Produces robust, support-free policies in real-world experiments.

Abstract

Learning policies for complex humanoid tasks remains both challenging and compelling. Inspired by how infants and athletes rely on external support--such as parental walkers or coach-applied guidance--to acquire skills like walking, dancing, and performing acrobatic flips, we propose A2CF: Adaptive Assistive Curriculum Force for humanoid motion learning. A2CF trains a dual-agent system, in which a dedicated assistive force agent applies state-dependent forces to guide the robot through difficult initial motions and gradually reduces assistance as the robot's proficiency improves. Across three benchmarks--bipedal walking, choreographed dancing, and backflip--A2CF achieves convergence 30% faster than baseline methods, lowers failure rates by over 40%, and ultimately produces robust, support-free policies. Real-world experiments further demonstrate that adaptively applied assistive forces significantly accelerate the acquisition of complex skills in high-dimensional robotic control.