To understand and collaborate with humans, robots must account for individual human traits, habits, and activities over time. However, most robotic assistants lack these abilities, as they primarily focus on predefined tasks in structured environments and lack a human model to learn from. This work introduces COOPERA, a novel framework for COntinual, OPen-Ended human-Robot Assistance, where simulated humans, driven by psychological traits and long-term intentions, interact with robots in complex environments. By integrating continuous human feedback, our framework, for the first time, enables the study of long-term, open-ended human-robot collaboration (HRC) in different collaborative tasks across various time-scales. Within COOPERA, we introduce a benchmark and an approach to personalize the robot's collaborative actions by learning human traits and context-dependent intents. Experiments validate the realism of our simulated humans and demonstrate the value of inferring and personalizing to human intents for open-ended and long-term HRC.
Our goal is to enable the study of continual HRC in open-ended tasks. To that end, we investigate how a robotic agent can become more effective in assisting humans by learning from their behavior. Central to COOPERA are LLM-powered simulated humans driven by traits and long-term intentions that the robot can reason for effective collaboration, and a human feedback mechanism for improving collaboration over time. COOPERA offers different collaborative tasks across various time-scales.
We aim to model humans who interact in the environment over long periods of time, act driven by their goals, preferences, and context, and who can react and provide feedback as a robot assists them. To achieve this, we propose a hierarchical model that combines LLMs and 3D human motion to simulate long-term, realistic human behaviors in indoor environments.
To study COOPERA, we propose an approach for continual HRC, alongside benchmark methods. Our approach enables the robot to improve its assistive performance by learning correlations between human intentions, tasks, traits, and temporal dependencies at each time of day.
@inproceedings{ma2025coopera,
title={COOPERA: Continual Open-Ended Human-Robot Assistance},
author={Ma, Chenyang and Lu, Kai and Desai, Ruta and Puig, Xavier and Markham, Andrew and Trigoni, Niki},
booktitle = {Proceedings of the Conference on Neural Information Processing Systems (NeurIPS)},
year={2025}
}