SayComply: Grounding Field Robotic Tasks in Operational Compliance through Retrieval-Based Language Models

TL;DR

SayComply introduces a retrieval-augmented language model framework that enables robots to generate task plans compliant with operational manuals by efficiently retrieving relevant domain-specific knowledge, improving adherence in real-world scenarios.

Contribution

This work presents a hierarchical database and a tree-based RAG method for grounding robot task planning in operational compliance, addressing transferability and context limitations of existing models.

Findings

Outperforms standard RAG in real-world experiments

Enables scalable and edge-deployable compliance in robotic task planning

Demonstrates effective context retrieval across diverse operational scenarios

Abstract

This paper addresses the problem of task planning for robots that must comply with operational manuals in real-world settings. Task planning under these constraints is essential for enabling autonomous robot operation in domains that require adherence to domain-specific knowledge. Current methods for generating robot goals and plans rely on common sense knowledge encoded in large language models. However, these models lack grounding of robot plans to domain-specific knowledge and are not easily transferable between multiple sites or customers with different compliance needs. In this work, we present SayComply, which enables grounding robotic task planning with operational compliance using retrieval-based language models. We design a hierarchical database of operational, environment, and robot embodiment manuals and procedures to enable efficient retrieval of the relevant context under the limited context length of the LLMs. We then design a task planner using a tree-based retrieval augmented generation (RAG) technique to generate robot tasks that follow user instructions while simultaneously complying with the domain knowledge in the database. We demonstrate the benefits of our approach through simulations and hardware experiments in real-world scenarios that require precise context retrieval across various types of context, outperforming the standard RAG method. Our approach bridges the gap in deploying robots that consistently adhere to operational protocols, offering a scalable and edge-deployable solution for ensuring compliance across varied and complex real-world environments. Project website: saycomply.github.io.