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

TL;DR

SayComply is presented, which enables grounding robotic task planning with operational compliance using retrievalbased language models and 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.

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.

Figures (5)

• Figure 1: Autonomous robots operating in industrial settings need to comply with operational procedures and past instructions from experts at the deployment sites while following user instructions. SayComply grounds robot tasks with this information via a tree-based retrieval augmented generation (RAG), effectively leveraging data not commonly accessible to general-purpose LLMs.
• Figure 2: SayComply system architecture. Prior to robot deployment, we build a hierarchical context database from various written manuals and instructions. Next, given a user query, relevant context source is retrieved using a tree-based RAG and LLM method. Finally, the compliant task planner generates robot tasks based on the retrieved context. Tasks are executed by the robot through behavior manager and the robot observations are stored in the database.
• Figure 3: Simulation results. The left panel shows the user query and robot answers while executing the plans. The middle and right panels show the robot task execution inspecting the fire extinguishers.
• Figure 4: The compliance & completion rate, and context retrieval accuracy from different types of user queries.
• Figure 5: Experiment results on hardware. The left panel illustrates an expert user first providing site orientation to the robot. The right panel shows the subsequent robot task execution given the user queries.