Grounding Language Models with Semantic Digital Twins for Robotic Planning

TL;DR

This paper presents a framework combining Semantic Digital Twins with Large Language Models to improve robotic task planning and execution in dynamic environments, enabling adaptability, error recovery, and semantic understanding.

Contribution

It introduces a novel integration of SDTs with LLMs for semantic grounding and adaptive planning in robotics, addressing real-time environmental changes and failures.

Findings

Robust task completion across household scenarios

Effective error recovery and plan revision

Semantic grounding improves interpretability and adaptability

Abstract

We introduce a novel framework that integrates Semantic Digital Twins (SDTs) with Large Language Models (LLMs) to enable adaptive and goal-driven robotic task execution in dynamic environments. The system decomposes natural language instructions into structured action triplets, which are grounded in contextual environmental data provided by the SDT. This semantic grounding allows the robot to interpret object affordances and interaction rules, enabling action planning and real-time adaptability. In case of execution failures, the LLM utilizes error feedback and SDT insights to generate recovery strategies and iteratively revise the action plan. We evaluate our approach using tasks from the ALFRED benchmark, demonstrating robust performance across various household scenarios. The proposed framework effectively combines high-level reasoning with semantic environment understanding, achieving reliable task completion in the face of uncertainty and failure.