This paper presents an online intention prediction framework for estimating the goal state of autonomous systems in real time, even when intention is time-varying, and system dynamics or objectives include unknown parameters. The problem is formulated as an inverse optimal control / inverse reinforcement learning task, with the intention treated as a parameter in the objective. A shifting horizon strategy discounts outdated information, while online control-informed learning enables efficient gradient computation and online parameter updates. Simulations under varying noise levels and hardware experiments on a quadrotor drone demonstrate that the proposed approach achieves accurate, adaptive intention prediction in complex environments.
@article{arxiv.2604.09303,
title = {Online Intention Prediction via Control-Informed Learning},
author = {Tianyu Zhou and Zihao Liang and Zehui Lu and Shaoshuai Mou},
journal= {arXiv preprint arXiv:2604.09303},
year = {2026}
}