Grounding Language Models with Semantic Digital Twins for Robotic Planning
This addresses the challenge of adaptive robotic planning for household automation, though it is incremental as it builds on existing LLM and digital twin technologies.
The paper tackles the problem of enabling robots to execute tasks from natural language instructions in dynamic environments by integrating Semantic Digital Twins with Large Language Models, resulting in robust performance on household tasks from the ALFRED benchmark.
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.