Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models

TL;DR

HELPER is an embodied agent that uses memory-augmented large language models to interpret natural language instructions and adapt to individual user routines, achieving state-of-the-art results in robot task benchmarks.

Contribution

This paper introduces HELPER, a novel memory-augmented LLM framework that personalizes robot instruction parsing through retrieval of dialogue-based memories, improving performance on complex benchmarks.

Findings

Achieved 1.7x improvement on TfD benchmark

Set new state-of-the-art in TEACh benchmark tasks

Effectively personalizes robot instructions using external memory

Abstract

Pre-trained and frozen large language models (LLMs) can effectively map simple scene rearrangement instructions to programs over a robot's visuomotor functions through appropriate few-shot example prompting. To parse open-domain natural language and adapt to a user's idiosyncratic procedures, not known during prompt engineering time, fixed prompts fall short. In this paper, we introduce HELPER, an embodied agent equipped with an external memory of language-program pairs that parses free-form human-robot dialogue into action programs through retrieval-augmented LLM prompting: relevant memories are retrieved based on the current dialogue, instruction, correction, or VLM description, and used as in-context prompt examples for LLM querying. The memory is expanded during deployment to include pairs of user's language and action plans, to assist future inferences and personalize them to the user's language and routines. HELPER sets a new state-of-the-art in the TEACh benchmark in both Execution from Dialog History (EDH) and Trajectory from Dialogue (TfD), with a 1.7x improvement over the previous state-of-the-art for TfD. Our models, code, and video results can be found in our project's website: https://helper-agent-llm.github.io.