Adaptable Human Intention and Trajectory Prediction for Human-Robot Collaboration
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.
BibTeX
@conference{Abuduweili-2019-119897,author = {A. Abuduweili and S. Li and C. Liu},
title = {Adaptable Human Intention and Trajectory Prediction for Human-Robot Collaboration},
booktitle = {Proceedings of AAAI '19 Fall Symposium on Artificial Intelligence and Human-Robot Interaction for Service Robots in Human Environments},
year = {2019},
month = {November},
}