A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics

2025-05-19

AI Summary

Foundational Model–driven Robots (FMRs) pose emerging safety risks in physical environments, yet no comprehensive temporal framework exists to systematically address these risks across the lifecycle of deployment. Method: This work establishes a three-dimensional temporal risk control framework—spanning pre-deployment, pre-incident, and post-incident phases—by integrating robotics control theory, safety-critical system verification, human factors engineering, and foundational model robustness analysis. Contribution/Results: It introduces, for the first time, a high-resolution physical risk taxonomy and a corresponding control roadmap for FMRs. The study identifies three critical research gaps: (1) proactive pre-incident intervention mechanisms; (2) dynamic modeling of human–robot physical interaction; and (3) ontological safety of foundational models. These contributions constitute the first systematic methodology supporting both theoretical development and engineering implementation of safe, trustworthy embodied AI systems.

Technology Category

• Intelligent Robots: Other Foundations and Applications
• Natural Language Processing: Safety and Robustness
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Recent Foundation Model-enabled robotics (FMRs) display greatly improved general-purpose skills, enabling more adaptable automation than conventional robotics. Their ability to handle diverse tasks thus creates new opportunities to replace human labor. However, unlike general foundation models, FMRs interact with the physical world, where their actions directly affect the safety of humans and surrounding objects, requiring careful deployment and control. Based on this proposition, our survey comprehensively summarizes robot control approaches to mitigate physical risks by covering all the lifespan of FMRs ranging from pre-deployment to post-accident stage. Specifically, we broadly divide the timeline into the following three phases: (1) pre-deployment phase, (2) pre-incident phase, and (3) post-incident phase. Throughout this survey, we find that there is much room to study (i) pre-incident risk mitigation strategies, (ii) research that assumes physical interaction with humans, and (iii) essential issues of foundation models themselves. We hope that this survey will be a milestone in providing a high-resolution analysis of the physical risks of FMRs and their control, contributing to the realization of a good human-robot relationship.

Problem

• Mitigating physical risks in Foundation Model-enabled Robotics (FMRs)
• Ensuring safety during human-robot physical interaction
• Addressing pre- and post-incident risk control strategies

Innovation

• Survey covers FMRs' physical risk control lifespan
• Divides control into pre-deployment, incident, post-incident phases
• Highlights gaps in human-robot interaction risk studies