Back to Search Start Over

Highlighting the Safety Concerns of Deploying LLMs/VLMs in Robotics

Authors :
Wu, Xiyang
Chakraborty, Souradip
Xian, Ruiqi
Liang, Jing
Guan, Tianrui
Liu, Fuxiao
Sadler, Brian M.
Manocha, Dinesh
Bedi, Amrit Singh
Publication Year :
2024

Abstract

In this paper, we highlight the critical issues of robustness and safety associated with integrating large language models (LLMs) and vision-language models (VLMs) into robotics applications. Recent works focus on using LLMs and VLMs to improve the performance of robotics tasks, such as manipulation and navigation. Despite these improvements, analyzing the safety of such systems remains underexplored yet extremely critical. LLMs and VLMs are highly susceptible to adversarial inputs, prompting a significant inquiry into the safety of robotic systems. This concern is important because robotics operate in the physical world where erroneous actions can result in severe consequences. This paper explores this issue thoroughly, presenting a mathematical formulation of potential attacks on LLM/VLM-based robotic systems and offering experimental evidence of the safety challenges. Our empirical findings highlight a significant vulnerability: simple modifications to the input can drastically reduce system effectiveness. Specifically, our results demonstrate an average performance deterioration of 19.4% under minor input prompt modifications and a more alarming 29.1% under slight perceptual changes. These findings underscore the urgent need for robust countermeasures to ensure the safe and reliable deployment of advanced LLM/VLM-based robotic systems.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2402.10340
Document Type :
Working Paper