How Can LLMs and Knowledge Graphs Contribute to Robot Safety? A Few-Shot Learning Approach
This work addresses safety verification for LLM-driven robotics, but it is incremental as it builds on existing methods like fine-tuning and knowledge graphs.
The paper tackles the safety risks of using LLM-generated code in robotics by introducing a safety layer that verifies ChatGPT-generated code before execution in a simulated drone environment, achieving improved safety and compliance with drone regulations.
Large Language Models (LLMs) are transforming the robotics domain by enabling robots to comprehend and execute natural language instructions. The cornerstone benefits of LLM include processing textual data from technical manuals, instructions, academic papers, and user queries based on the knowledge provided. However, deploying LLM-generated code in robotic systems without safety verification poses significant risks. This paper outlines a safety layer that verifies the code generated by ChatGPT before executing it to control a drone in a simulated environment. The safety layer consists of a fine-tuned GPT-4o model using Few-Shot learning, supported by knowledge graph prompting (KGP). Our approach improves the safety and compliance of robotic actions, ensuring that they adhere to the regulations of drone operations.