PAMoR: Parameterized Affective Motion Generation in Real Time for Humanoid Robots
Robotics
Summary
The authors created a system called PAMoR that lets a humanoid robot show emotions through its movements by controlling how the robot moves using numbers for feelings like happiness or excitement. Instead of using words or example videos, their method calculates emotion directly from the robot's posture and energy. They combined this emotional control with the action the robot is doing to make motion that matches both. In tests, people were better at recognizing the robot's intended emotion than with previous methods and close to how well they recognize emotions in human movements.
Authors
Yan Pan, Lingfan Bao, Tianhu Peng, Chengxu Zhou
Abstract
People read a humanoid robot's motion in social settings not only for the action performed but for the affect conveyed. Motion carrying that affect has so far been generated for human avatars, where style is taken from a reference clip or an emotion word, neither of which can be quantitatively parameterized. We present PAMoR, which turns affect into a measured control parameter: a valence-arousal (V-A) coordinate computed natively on robot kinematics. It is obtained in closed form from postural expansion and movement energy, and these measurements serve directly as generation conditions, with no human annotation. An action prior and two affect priors, trained in a shared latent space, are composed at each denoising step: the action prior fixes what is performed, the affect priors modulate how. Whole-body motion rolls out autoregressively on a 29-DoF Unitree G1 in real time, with action and affect both editable. Generated motion tracks the commanded V-A over its full range while text-to-motion fidelity still matches text-only baselines. In a perceptual study, raters identify the commanded emotion on 0.38 of trials, above both baselines and approaching the 0.44 reported for acted human bodies.