# Learning Models for Shared Control of Human-Machine Systems with Unknown Dynamics

arXiv: https://arxiv.org/abs/1808.08268 · HTML: https://mlsanity.com/paper/1808.08268/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2018.

## Built on by (most cited first, 11 of 11)

- [ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning](https://mlsanity.com/paper/2202.02465/) (2022)
- [First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization](https://mlsanity.com/paper/2205.12381/) (2022)
- [Dreaming to Assist: Learning to Align with Human Objectives for Shared Control in High-Speed Racing](https://mlsanity.com/paper/2410.10062/) (2024)
- [Conformalized Teleoperation: Confidently Mapping Human Inputs to High-Dimensional Robot Actions](https://mlsanity.com/paper/2406.07767/) (2024)
- [X2T: Training an X-to-Text Typing Interface with Online Learning from User Feedback](https://mlsanity.com/paper/2203.02072/) (2022)
- [A Framework for Learning from Demonstration with Minimal Human Effort](https://mlsanity.com/paper/2306.09211/) (2023)
- [Shared Control with Black Box Agents using Oracle Queries](https://mlsanity.com/paper/2410.19612/) (2024)
- [Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models](https://mlsanity.com/paper/2506.14727/) (2025)
- [Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning](https://mlsanity.com/paper/2309.03839/) (2023)
- [Improving through Interaction: Searching Behavioral Representation Spaces with CMA-ES-IG](https://mlsanity.com/paper/2603.09011/) (2026)
- [HITL-D: Human In The Loop Diffusion Assisted Shared Control](https://mlsanity.com/paper/2605.21460/) (2026)

## Abstract (arXiv)

We present a novel approach to shared control of human-machine systems. Our method assumes no a priori knowledge of the system dynamics. Instead, we learn both the dynamics and information about the user's interaction from observation through the use of the Koopman operator. Using the learned model, we define an optimization problem to compute the optimal policy for a given task, and compare the user input to the optimal input. We demonstrate the efficacy of our approach with a user study. We also analyze the individual nature of the learned models by comparing the effectiveness of our approach when the demonstration data comes from a user's own interactions, from the interactions of a group of users and from a domain expert. Positive results include statistically significant improvements on task metrics when comparing a user-only control paradigm with our shared control paradigm. Surprising results include findings that suggest that individualizing the model based on a user's own data does not effect the ability to learn a useful dynamic system. We explore this tension as it relates to developing human-in-the-loop systems further in the discussion.