Prediction of Human Full-Body Movements with Motion Optimization and Recurrent Neural Networks

TL;DR

This paper introduces a hybrid prediction framework combining recurrent neural networks for short-term human movement dynamics and gradient-based optimization for environmental constraints, improving accuracy and enabling robot trajectory planning.

Contribution

It presents a novel decoupled approach for human movement prediction that integrates neural networks with trajectory optimization to handle complex environments.

Findings

Outperforms existing motion prediction methods on real data.

Effectively accounts for unseen environmental structures.

Enables robot trajectory planning coordinated with humans.

Abstract

Human movement prediction is difficult as humans naturally exhibit complex behaviors that can change drastically from one environment to the next. In order to alleviate this issue, we propose a prediction framework that decouples short-term prediction, linked to internal body dynamics, and long-term prediction, linked to the environment and task constraints. In this work we investigate encoding short-term dynamics in a recurrent neural network, while we account for environmental constraints, such as obstacle avoidance, using gradient-based trajectory optimization. Experiments on real motion data demonstrate that our framework improves the prediction with respect to state-of-the-art motion prediction methods, as it accounts to beforehand unseen environmental structures. Moreover we demonstrate on an example, how this framework can be used to plan robot trajectories that are optimized to coordinate with a human partner.