LLM-informed Object Search in Partially-Known Environments via Model-based Planning and Prompt Selection

Abhishek Paudel, Abhish Khanal, Shahriar Hossain, Gregory J. Stein

Keywords: llm-informed object search, model-based planning, planning under uncertainty, prompt selection

TL;DR: We present a novel LLM-informed model-based planning framework for object search in partially-known environments, and propose deployment-time prompt selection in this domain.

Abstract: We present a novel LLM-informed model-based planning framework for object search in partially-known environments. Our approach uses an LLM to estimate statistics about the likelihood of finding the target object when searching various locations throughout the scene that, combined with travel costs extracted from the environment map, are used to instantiate a model, thus using the LLM to inform, rather than replace, planning and achieve effective search performance. Moreover, the abstraction upon which our approach relies is amenable to deployment-time model selection via the recent offline replay approach, an insight we leverage to enable fast prompt and LLM selection during deployment. Simulation experiments demonstrate that our LLM-informed model-based planning approach outperforms the baseline planning strategy that fully relies on LLM and optimistic strategy with as much as 11.8% and 39.2% improvements respectively, and our bandit-like selection approach enables quick selection of best prompts and LLMs resulting in 6.5% lower average cost and 33.8% lower average cumulative regret over baseline UCB bandit selection. Real-robot experiments in household settings demonstrate similar improvements and so further validate our approach.

Primary Area: applications to robotics, autonomy, planning

Submission Number: 4136