DTRT: Enhancing Human Intent Estimation and Role Allocation for Physical Human-Robot Collaboration

TL;DR

This paper introduces DTRT, a hierarchical Transformer-based model that improves human intent estimation and role allocation in physical human-robot collaboration by integrating multi-step prediction and human dynamics.

Contribution

The paper presents a novel hierarchical Transformer architecture with CVAEs and DCGT for enhanced multi-step intent prediction and dynamic role allocation in pHRC.

Findings

DTRT outperforms state-of-the-art methods in intent estimation accuracy.

The model enables adaptive role allocation based on real-time human intent.

Experiments show improved safety and efficiency in human-robot collaboration.

Abstract

In physical Human-Robot Collaboration (pHRC), accurate human intent estimation and rational human-robot role allocation are crucial for safe and efficient assistance. Existing methods that rely on short-term motion data for intention estimation lack multi-step prediction capabilities, hindering their ability to sense intent changes and adjust human-robot assignments autonomously, resulting in potential discrepancies. To address these issues, we propose a Dual Transformer-based Robot Trajectron (DTRT) featuring a hierarchical architecture, which harnesses human-guided motion and force data to rapidly capture human intent changes, enabling accurate trajectory predictions and dynamic robot behavior adjustments for effective collaboration. Specifically, human intent estimation in DTRT uses two Transformer-based Conditional Variational Autoencoders (CVAEs), incorporating robot motion data in obstacle-free case with human-guided trajectory and force for obstacle avoidance. Additionally, Differential Cooperative Game Theory (DCGT) is employed to synthesize predictions based on human-applied forces, ensuring robot behavior align with human intention. Compared to state-of-the-art (SOTA) methods, DTRT incorporates human dynamics into long-term prediction, providing an accurate understanding of intention and enabling rational role allocation, achieving robot autonomy and maneuverability. Experiments demonstrate DTRT's accurate intent estimation and superior collaboration performance.