LLM-Personalize: Aligning LLM Planners with Human Preferences via Reinforced Self-Training for Housekeeping Robots
*Under submission to IROS 2024*
Abstract
Large language models (LLMs) have shown significant potential for robotics applications, particularly task planning, by harnessing their language comprehension and text generation capabilities. However, in applications such as household robotics, a critical gap remains in the personalization of these models to individual user preferences. We introduce LLM-Personalize, a novel framework with an optimization pipeline designed to personalize LLM planners for household robotics. Our LLM-Personalize framework features an LLM planner that performs iterative planning in multi-room, partially-observable household scenarios, making use of a scene graph constructed with local observations. The generated plan consists of a sequence of high-level actions which are subsequently executed by a controller. Central to our approach is the optimization pipeline, which combines imitation learning and iterative self-training to personalize the LLM planner. In particular, the imitation learning phase performs initial LLM alignment from demonstrations, and bootstraps the model to facilitate effective iterative self-training, which further explores and aligns the model to user preferences. We evaluate LLM-Personalize on Housekeep, a challenging simulated real-world 3D benchmark for household rearrangements, and show that LLM-Personalize achieves more than a 30 percent increase in success rate over existing LLM planners, showcasing significantly improved alignment with human preferences.
Citing Our Work
Our paper is available on Arxiv. If you find our code useful, please consider citing us!
@misc{han2024llmpersonalize,
title={LLM-Personalize: Aligning LLM Planners with Human Preferences via Reinforced Self-Training for Housekeeping Robots},
author={Dongge Han and Trevor McInroe and Adam Jelley and Stefano V. Albrecht and Peter Bell and Amos Storkey},
year={2024},
eprint={2404.14285},
archivePrefix={arXiv},
primaryClass={cs.RO}
}
Acknowledgements
The housekeep benchmark and the housekeep simulator code used in this work is developed by Kant et. al. for their paper: Housekeep: Tidying Virtual Households using Commonsense Reasoning. The simulator is based on the Habitat simulator introduced in the paper Habitat 2.0: Training Home Assistants to Rearrange their Habitat.