Adaptable Human Intention and Trajectory Prediction for Human-Robot Collaboration

TL;DR

This paper presents an adaptable multi-task model for human trajectory and intention prediction in human-robot collaboration, utilizing an online adaptation algorithm to improve accuracy and generalizability across different users.

Contribution

It introduces a novel nonlinear recursive least squares parameter adaptation algorithm for online adaptation in human prediction models, enhancing flexibility and data efficiency.

Findings

Online adaptation reduces trajectory prediction error by over 28%.

The method demonstrates high flexibility and generalizability across different human subjects.

The approach supports fast integration into human-robot collaboration systems.

Abstract

To engender safe and efficient human-robot collaboration, it is critical to generate high-fidelity predictions of human behavior. The challenges in making accurate predictions lie in the stochasticity and heterogeneity in human behaviors. This paper introduces a method for human trajectory and intention prediction through a multi-task model that is adaptable across different human subjects. We develop a nonlinear recursive least square parameter adaptation algorithm (NRLS-PAA) to achieve online adaptation. The effectiveness and flexibility of the proposed method has been validated in experiments. In particular, online adaptation can reduce the trajectory prediction error by more than 28% for a new human subject. The proposed human prediction method has high flexibility, data efficiency, and generalizability, which can support fast integration of HRC systems for user-specified tasks.