PrediFlow: A Flow-Based Prediction-Refinement Framework for Real-Time Human Motion Prediction in Human-Robot Collaboration

TL;DR

PrediFlow is a real-time, interaction-aware human motion prediction framework that refines initial predictions by integrating robot motion, significantly improving accuracy while maintaining uncertainty and multi-modality in collaborative settings.

Contribution

The paper introduces a novel flow-based prediction-refinement framework that incorporates robot motion to enhance the realism and accuracy of human motion predictions in real-time HRC scenarios.

Findings

Significantly improved prediction accuracy on HRC datasets.

Maintains real-time inference within time constraints.

Effectively models uncertainty and multi-modal human behaviors.

Abstract

Stochastic human motion prediction is critical for safe and effective human-robot collaboration (HRC) in industrial remanufacturing, as it captures human motion uncertainties and multi-modal behaviors that deterministic methods cannot handle. While earlier works emphasize highly diverse predictions, they often generate unrealistic human motions. More recent methods focus on accuracy and real-time performance, yet there remains potential to improve prediction quality further without exceeding time budgets. Additionally, current research on stochastic human motion prediction in HRC typically considers human motion in isolation, neglecting the influence of robot motion on human behavior. To address these research gaps and enable real-time, realistic, and interaction-aware human motion prediction, we propose a novel prediction-refinement framework that integrates both human and robot observed motion to refine the initial predictions produced by a pretrained state-of-the-art predictor. The refinement module employs a Flow Matching structure to account for uncertainty. Experimental studies on the HRC desktop disassembly dataset demonstrate that our method significantly improves prediction accuracy while preserving the uncertainties and multi-modalities of human motion. Moreover, the total inference time of the proposed framework remains within the time budget, highlighting the effectiveness and practicality of our approach.