Online Intention Prediction via Control-Informed Learning
Tianyu Zhou, Zihao Liang, Zehui Lu, Shaoshuai Mou
TLDR
This paper introduces an online control-informed learning framework for real-time intention prediction in autonomous systems, handling time-varying goals and unknown dynamics.
Key contributions
- Presents an online framework for real-time intention prediction in autonomous systems.
- Handles time-varying intentions and unknown system dynamics/objectives.
- Leverages inverse optimal control and a shifting horizon strategy for updates.
- Demonstrated accurate, adaptive prediction on quadrotor hardware.
Why it matters
This paper is crucial for developing more adaptive and robust autonomous systems. It allows real-time prediction of changing goals and unknown system parameters, enhancing safety and performance in dynamic, uncertain environments.
Original Abstract
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 A shifting horizon strategy discounts outdated information, while online control-informed learning enables efficient gradient computation and online parameter updates.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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.