Grounding Language Models with Semantic Digital Twins for Robotic Planning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Naeem, Mehreen, Melnik, Andrew, Beetz, Michael
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908414661099520
author Naeem, Mehreen
Melnik, Andrew
Beetz, Michael
author_facet Naeem, Mehreen
Melnik, Andrew
Beetz, Michael
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16493
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Grounding Language Models with Semantic Digital Twins for Robotic Planning
Naeem, Mehreen
Melnik, Andrew
Beetz, Michael
Robotics
Artificial Intelligence
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.
title Grounding Language Models with Semantic Digital Twins for Robotic Planning
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2506.16493