# RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields

arXiv: https://arxiv.org/abs/2412.02818 · HTML: https://mlsanity.com/paper/2412.02818/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 38 of its 52 references that are in the map.
- First posted on arXiv 3 Dec 2024.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 38)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations](https://mlsanity.com/paper/2310.17596/) (2023)
- [TEASER: Fast and Certifiable Point Cloud Registration](https://mlsanity.com/paper/2001.07715/) (2020)
- [REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction](https://mlsanity.com/paper/2306.15724/) (2023)
- [Data Scaling Laws in Imitation Learning for Robotic Manipulation](https://mlsanity.com/paper/2410.18647/) (2024)
- [THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation](https://mlsanity.com/paper/2402.08191/) (2024)
- [AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation](https://mlsanity.com/paper/2410.00371/) (2024)
- [Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations](https://mlsanity.com/paper/2003.06085/) (2020)
- [Curiosity-driven Red-teaming for Large Language Models](https://mlsanity.com/paper/2402.19464/) (2024)
- [Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation](https://mlsanity.com/paper/2307.03659/) (2023)
- [Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences](https://mlsanity.com/paper/2002.09089/) (2020)
- [A Survey of Algorithms for Black-Box Safety Validation of Cyber-Physical Systems](https://mlsanity.com/paper/2005.02979/) (2020)
- [Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress](https://mlsanity.com/paper/2410.04640/) (2024)
- [Out-of-Distribution Detection for Automotive Perception](https://mlsanity.com/paper/2011.01413/) (2020)
- [On the Importance of Exploration for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2306.05483/) (2023)
- [Failure Prediction with Statistical Guarantees for Vision-Based Robot Control](https://mlsanity.com/paper/2202.05894/) (2022)
- [How Do We Fail? Stress Testing Perception in Autonomous Vehicles](https://mlsanity.com/paper/2203.14155/) (2022)

## Built on by (most cited first, 7 of 7)

- [Score the Steps, Not Just the Goal: VLM-Based Subgoal Evaluation for Robotic Manipulation](https://mlsanity.com/paper/2509.19524/) (2025)
- [KDPE: A Kernel Density Estimation Strategy for Diffusion Policy Trajectory Selection](https://mlsanity.com/paper/2508.10511/) (2025)
- [Geometric Red-Teaming for Robotic Manipulation](https://mlsanity.com/paper/2509.12379/) (2025)
- [RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models](https://mlsanity.com/paper/2605.09410/) (2026)
- [Behavior-Skill: A Fine-Grained Benchmark for Evaluating Vision-Language-Action Policies in Long-Horizon Tasks](https://mlsanity.com/paper/2608.30536/) (2026)
- [Mulligan: Performance-Guided Data Collection for Efficient On-Robot Learning](https://mlsanity.com/paper/2610.05882/) (2026)
- [YUBI-Real2Sim: 3DGS Scene Verification for Reliable Policy Evaluation](https://mlsanity.com/paper/2610.17521/) (2026)

## Abstract (arXiv)

Robot manipulation policies, while central to the promise of physical AI, are highly vulnerable in the presence of external variations in the real world. Diagnosing these vulnerabilities is hindered by two key challenges: (i) the relevant variations to test against are often unknown, and (ii) direct testing in the real world is costly and unsafe. We introduce a framework that tackles both issues by learning a separate deep reinforcement learning (deep RL) policy for vulnerability prediction through virtual runs on a continuous vision-language embedding trained with limited success-failure data. By treating this embedding space, which is rich in semantic and visual variations, as a potential field, the policy learns to move toward vulnerable regions while being repelled from success regions. This vulnerability prediction policy, trained on virtual rollouts, enables scalable and safe vulnerability analysis without expensive physical trials. By querying this policy, our framework builds a probabilistic vulnerability-likelihood map. Experiments across simulation benchmarks and a physical robot arm show that our framework uncovers up to 23% more unique vulnerabilities than state-of-the-art vision-language baselines, revealing subtle vulnerabilities overlooked by heuristic testing. Additionally, we show that fine-tuning the manipulation policy with the vulnerabilities discovered by our framework improves manipulation performance with much less fine-tuning data.