# Generating Robot Constitutions & Benchmarks for Semantic Safety

arXiv: https://arxiv.org/abs/2503.08663 · HTML: https://mlsanity.com/paper/2503.08663/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 164 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Builds on (most cited first, 30 of 43)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [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)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [VIMA: General Robot Manipulation with Multimodal Prompts](https://mlsanity.com/paper/2210.03094/) (2022)
- [Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners](https://mlsanity.com/paper/2307.01928/) (2023)
- [Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models](https://mlsanity.com/paper/2310.10639/) (2023)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [Foundation Models in Robotics: Applications, Challenges, and the Future](https://mlsanity.com/paper/2312.07843/) (2023)
- [PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs](https://mlsanity.com/paper/2402.07872/) (2024)
- [Scaling Robot Learning with Semantically Imagined Experience](https://mlsanity.com/paper/2302.11550/) (2023)
- [RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches](https://mlsanity.com/paper/2311.01977/) (2023)
- [Collective Constitutional AI: Aligning a Language Model with Public Input](https://mlsanity.com/paper/2406.07814/) (2024)
- [RoboVQA: Multimodal Long-Horizon Reasoning for Robotics](https://mlsanity.com/paper/2311.00899/) (2023)
- [DALL-E-Bot: Introducing Web-Scale Diffusion Models to Robotics](https://mlsanity.com/paper/2210.02438/) (2022)
- [Batch Active Preference-Based Learning of Reward Functions](https://mlsanity.com/paper/1810.04303/) (2018)
- [Few-Shot Preference Learning for Human-in-the-Loop RL](https://mlsanity.com/paper/2212.03363/) (2022)

## Built on by (most cited first, 30 of 33)

- [Evaluating Gemini Robotics Policies in a Veo World Simulator](https://mlsanity.com/paper/2512.10675/) (2025)
- [Can AI Perceive Physical Danger and Intervene?](https://mlsanity.com/paper/2509.21651/) (2025)
- [Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms](https://mlsanity.com/paper/2604.23775/) (2026)
- [Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses](https://mlsanity.com/paper/2605.02900/) (2026)
- [Embodied AI: Emerging Risks and Opportunities for Policy Action](https://mlsanity.com/paper/2509.00117/) (2025)
- [Constrained Decoding for Safe Robot Navigation Foundation Models](https://mlsanity.com/paper/2509.01728/) (2025)
- [HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task](https://mlsanity.com/paper/2603.14367/) (2026)
- [Using large language models for embodied planning introduces systematic safety risks](https://mlsanity.com/paper/2604.18463/) (2026)
- [Contextual Safety Reasoning and Grounding for Open-World Robots](https://mlsanity.com/paper/2602.19983/) (2026)
- [EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents](https://mlsanity.com/paper/2605.30924/) (2026)
- [ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models](https://mlsanity.com/paper/2606.27079/) (2026)
- [SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents](https://mlsanity.com/paper/2510.12985/) (2025)
- [RoboJailBench: Benchmarking Adversarial Attacks and Defenses in Embodied Robotic Agents](https://mlsanity.com/paper/2605.19328/) (2026)
- [Unfettered Forceful Skill Acquisition with Physical Reasoning and Coordinate Frame Labeling](https://mlsanity.com/paper/2505.09731/) (2025)
- [Human Centric General Physical Intelligence for Agile Manufacturing Automation](https://mlsanity.com/paper/2508.11960/) (2025)
- [From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails](https://mlsanity.com/paper/2510.13727/) (2025)
- [HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios](https://mlsanity.com/paper/2603.11975/) (2026)
- [SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models](https://mlsanity.com/paper/2604.19638/) (2026)
- [EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards](https://mlsanity.com/paper/2607.00218/) (2026)
- [On the Dual-Use Dilemma in Physical Reasoning and Force](https://mlsanity.com/paper/2505.18792/) (2025)
- [Towards provable probabilistic safety for scalable embodied AI systems](https://mlsanity.com/paper/2506.05171/) (2025)
- [Specification-Aware Distribution Shaping for Robotics Foundation Models](https://mlsanity.com/paper/2603.17969/) (2026)
- [REBAR: Reference Ethical Benchmark for Autonomy Readiness](https://mlsanity.com/paper/2605.18423/) (2026)
- [Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration](https://mlsanity.com/paper/2605.31196/) (2026)
- [RobotValues: Evaluating Household Robots When Human Values Conflict](https://mlsanity.com/paper/2606.03312/) (2026)
- [VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring](https://mlsanity.com/paper/2606.03954/) (2026)
- [MagicSim: A Unified Infrastructure for Executable Embodied Interaction](https://mlsanity.com/paper/2606.17511/) (2026)
- [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)
- [RobotEQ-Video: A Video-Centric Benchmark for Social Proactive Intelligence with World-State Taxonomy](https://mlsanity.com/paper/2609.21371/) (2026)
- [Security and Privacy in Large-Model-Driven Embodied Agents: Attacks, Defenses, and Future Directions](https://mlsanity.com/paper/2609.27847/) (2026)

## Abstract (arXiv)

Until recently, robotics safety research was predominantly about collision avoidance and hazard reduction in the immediate vicinity of a robot. Since the advent of large vision and language models (VLMs), robots are now also capable of higher-level semantic scene understanding and natural language interactions with humans. Despite their known vulnerabilities (e.g. hallucinations or jail-breaking), VLMs are being handed control of robots capable of physical contact with the real world. This can lead to dangerous behaviors, making semantic safety for robots a matter of immediate concern. Our contributions in this paper are two fold: first, to address these emerging risks, we release the ASIMOV Benchmark, a large-scale and comprehensive collection of datasets for evaluating and improving semantic safety of foundation models serving as robot brains. Our data generation recipe is highly scalable: by leveraging text and image generation techniques, we generate undesirable situations from real-world visual scenes and human injury reports from hospitals. Secondly, we develop a framework to automatically generate robot constitutions from real-world data to steer a robot's behavior using Constitutional AI mechanisms. We propose a novel auto-amending process that is able to introduce nuances in written rules of behavior; this can lead to increased alignment with human preferences on behavior desirability and safety. We explore trade-offs between generality and specificity across a diverse set of constitutions of different lengths, and demonstrate that a robot is able to effectively reject unconstitutional actions. We measure a top alignment rate of 84.3% on the ASIMOV Benchmark using generated constitutions, outperforming no-constitution baselines and human-written constitutions. Data is available at asimov-benchmark.github.io