# Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy

arXiv: https://arxiv.org/abs/2411.18289 · HTML: https://mlsanity.com/paper/2411.18289/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 69 references that are in the map.
- First posted on arXiv 27 Nov 2024.

## Builds on (most cited first, 30 of 47)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [Vision-Language Foundation Models as Effective Robot Imitators](https://mlsanity.com/paper/2311.01378/) (2023)
- [Language to Rewards for Robotic Skill Synthesis](https://mlsanity.com/paper/2306.08647/) (2023)
- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [Text2Motion: From Natural Language Instructions to Feasible Plans](https://mlsanity.com/paper/2303.12153/) (2023)
- [In-Context Unlearning: Language Models as Few Shot Unlearners](https://mlsanity.com/paper/2310.07579/) (2023)
- [TidyBot: Personalized Robot Assistance with Large Language Models](https://mlsanity.com/paper/2305.05658/) (2023)
- [Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making](https://mlsanity.com/paper/2410.07166/) (2024)
- [Towards Safer Large Language Models through Machine Unlearning](https://mlsanity.com/paper/2402.10058/) (2024)

## Built on by (most cited first, 9 of 9)

- [SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents](https://mlsanity.com/paper/2509.25885/) (2025)
- [DETACH: Cross-domain Learning for Long-Horizon Tasks via Mixture of Disentangled Experts](https://mlsanity.com/paper/2508.07842/) (2025)
- [Using large language models for embodied planning introduces systematic safety risks](https://mlsanity.com/paper/2604.18463/) (2026)
- [SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues](https://mlsanity.com/paper/2603.19092/) (2026)
- [ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI](https://mlsanity.com/paper/2602.14135/) (2026)
- [M4Diffuser: Multi-View Diffusion Policy with Manipulability-Aware Control for Robust Mobile Manipulation](https://mlsanity.com/paper/2509.14980/) (2025)
- [OmniDexVLG: Learning Dexterous Grasp Generation from Vision Language Model-Guided Grasp Semantics, Taxonomy and Functional Affordance](https://mlsanity.com/paper/2512.03874/) (2025)
- [When Words Are Safe But Actions Kill: Probing Physical Jailbreak Beyond Textual Jailbreak in Hidden-State Risk Space](https://mlsanity.com/paper/2607.15218/) (2026)
- [Safe Task Planning with Long-Term Graph Memory for Embodied Agents](https://mlsanity.com/paper/2609.08444/) (2026)

## Abstract (arXiv)

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.