Research Analyzer
← Back ICRA 2026

Don't Let Your Robot Be Harmful: Responsible Robotic Manipulation Via Safety-As-Policy

Minheng Ni, Lei Zhang, Zihan Chen, Kaixin Bai, Zhaopeng Chen, Jianwei Zhang, Lei Zhang, Wangmeng Zuo

PDF

AI summary

Key figure (auto-extracted from paper)
Safety-as-Policy enables robots to proactively avoid real-world hazards during manipulation by learning safety cognition from virtual interactions, significantly outperforming existing baselines.
Responsible robotics Safety-aware manipulation Large multimodal models Virtual interaction Task and motion planning SafeBox dataset

Problem

Mindlessly executing human instructions can cause severe safety accidents, yet training robots to handle diverse, unseen risks is impractical due to the variability and danger of real-world scenarios.

Approach

The method pairs a large multimodal model with a world model that generates virtual risky scenarios and a mental model that iteratively infers consequences to update safety cognition, enabling safe task planning without physical risk.

Key results

  • Significantly outperforms baselines in safety and success rates across synthetic and real-world tests
  • Introduces SafeBox, a 100-task synthetic dataset that reliably mirrors real-world safety evaluations
  • Enables proactive hazard avoidance in electrical, fire/chemical, and human safety scenarios
  • Learns safety cognition autonomously through iterative virtual interactions and consequence reflection

Why it matters

Provides a scalable, risk-free training paradigm and benchmark for deploying responsible, AI-driven robots in complex human environments.

Abstract

Unthinking execution of human instructions in robotic manipulation can lead to severe safety risks, such as poisonings, fires, and even explosions. In this paper, we present responsible robotic manipulation, which requires robots to consider potential hazards in the real-world environment while completing instructions and performing complex operations safely and efficiently. However, such scenarios in real world are variable and risky for training. To address this challenge, we propose Safety-as-policy, which includes (i) a world model to automatically generate scenarios containing safety risks and conduct virtual interactions, and (ii) a mental model to infer consequences with reflections and gradually develop the cognition of safety, allowing robots to accomplish tasks while avoiding dangers. Additionally, we create the SafeBox synthetic dataset, which includes one hundred responsible robotic manipulation tasks with different safety risk scenarios and instructions, effectively reducing the risks associated with real-world experiments. Experiments demonstrate that Safety-as-policy can avoid risks and efficiently complete tasks in both synthetic dataset and real-world experiments, significantly outperforming baseline methods. Our SafeBox dataset shows consistent evaluation results with real-world scenarios, serving as a safe and effective benchmark for future research. Our code, data, and supplementary materials are available at: https://sites.google.com/view/safety-as-policy.

Index terms

Safety in HRI Task and Motion Planning Multi-Modal Perception for HRI

Related papers