Robot models human body movements with uncertainty and physics
Toward Uncertainty-Aware, Physics-Grounded Human World Models
Robotics
Summary
Robots that work near people need to understand how human bodies move and how certain or uncertain those predictions are. The authors point out that two existing methods together can provide this understanding: one that reconstructs 3D body shapes while estimating uncertainty, and another that predicts future movements by applying physics principles. They explain how to connect these two methods and suggest ways to include uncertainty in future predictions. This lays groundwork for better robot awareness of human movement, but no new experiments are shown here.
What this means in practice
- •For robotics engineers: Build robots that predict human body motions more accurately by integrating uncertainty-informed observations with physics-driven dynamics.
- •For virtual reality developers: Enhance avatar motion prediction and interaction by combining uncertain body state estimates with physics-based motion models.
A position paper. It proposes an approach and reports no results.
Authors
Yufei Zhang, Zijun Cui
Abstract
A robot that acts around people needs a world model of the human: a belief over the person's body state and a dynamics model that predicts where that state goes next. This abstract argues that two published components form exactly these two halves, and specifies how to couple them. KNOWN [1] reconstructs the 3D human body while estimating both aleatoric and epistemic uncertainty in real time (11.6 ms per frame); its aleatoric term identifies unreliable observations, its epistemic term identifies inputs from low-density regions of the training data, and refinement driven by the epistemic term reduces the error on such inputs from 81.3 to 70.3 mm. PhysMoP [2] predicts future body configuration by solving the Euler-Lagrange equations of the body with learned dynamics terms, reducing the 80 ms prediction error from 9.6 to 2.1 mm on Human3.6M and from 12.1 to 0.7 mm on 3DPW. We define the interface between the two, propose three mechanisms by which KNOWN's uncertainty enters PhysMoP, and specify an evaluation protocol on in-the-wild video. No new experimental results are reported here.