Humanoid Motion Scripting with Postural Synergies

TL;DR

This paper introduces SynSculptor, a framework that uses postural synergies and motion-language transformers to generate and adapt human-like motions for humanoid robots without training, based on motion capture data and PCA analysis.

Contribution

It presents a novel, training-free motion scripting method leveraging postural synergies and a style-conditioned library for humanoid robots.

Findings

Effective motion generation with low foot-sliding ratio

Motion smoothness comparable to reference motions

Successful adaptation of postures via motion-language transformer

Abstract

Generating sequences of human-like motions for humanoid robots presents challenges in collecting and analyzing reference human motions, synthesizing new motions based on these reference motions, and mapping the generated motion onto humanoid robots. To address these issues, we introduce SynSculptor, a humanoid motion analysis and editing framework that leverages postural synergies for training-free human-like motion scripting. To analyze human motion, we collect 3+ hours of motion capture data across 20 individuals where a real-time operational space controller mimics human motion on a simulated humanoid robot. The major postural synergies are extracted using principal component analysis (PCA) for velocity trajectories segmented by changes in robot momentum, constructing a style-conditioned synergy library for free-space motion generation. To evaluate generated motions using the synergy library, the foot-sliding ratio and proposed metrics for motion smoothness involving total momentum and kinetic energy deviations are computed for each generated motion, and compared with reference motions. Finally, we leverage the synergies with a motion-language transformer, where the humanoid, during execution of motion tasks with its end-effectors, adapts its posture based on the chosen synergy. Supplementary material, code, and videos are available at https://rhea-mal.github.io/humanoidsynergies.io.