# Towards Safe Robot Foundation Models

arXiv: https://arxiv.org/abs/2503.07404 · HTML: https://mlsanity.com/paper/2503.07404/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Mar 2025.

## Built on by (most cited first, 1 of 1)

- [ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models](https://mlsanity.com/paper/2606.27079/) (2026)

## Abstract (arXiv)

Robot foundation models hold the potential for deployment across diverse environments, from industrial applications to household tasks. While current research focuses primarily on the policies' generalization capabilities across a variety of tasks, it fails to address safety, a critical requirement for deployment on real-world systems. In this paper, we introduce a safety layer designed to constrain the action space of any generalist policy appropriately. Our approach uses ATACOM, a safe reinforcement learning algorithm that creates a safe action space and, therefore, ensures safe state transitions. By extending ATACOM to generalist policies, our method facilitates their deployment in safety-critical scenarios without requiring any specific safety fine-tuning. We demonstrate the effectiveness of this safety layer in an air hockey environment, where it prevents a puck-hitting agent from colliding with its surroundings, a failure observed in generalist policies.