# Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning

arXiv: https://arxiv.org/abs/2505.10547 · HTML: https://mlsanity.com/paper/2505.10547/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 76 references that are in the map.
- First posted on arXiv 15 May 2025.

## Builds on (most cited first, 30 of 53)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (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)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [Control Barrier Functions: Theory and Applications](https://mlsanity.com/paper/1903.11199/) (2019)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Scaling Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.09683/) (2023)
- [Improving Text Embeddings with Large Language Models](https://mlsanity.com/paper/2401.00368/) (2023)
- [Foundation Models in Robotics: Applications, Challenges, and the Future](https://mlsanity.com/paper/2312.07843/) (2023)
- [Hamilton-Jacobi Reachability: A Brief Overview and Recent Advances](https://mlsanity.com/paper/1709.07523/) (2017)
- [Combined Scaling for Zero-shot Transfer Learning](https://mlsanity.com/paper/2111.10050/) (2021)
- [A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges](https://mlsanity.com/paper/2110.14051/) (2021)
- [Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methods](https://mlsanity.com/paper/2202.11762/) (2022)
- [The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systems](https://mlsanity.com/paper/2309.05837/) (2023)
- [Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress](https://mlsanity.com/paper/2410.04640/) (2024)
- [Real-Time Anomaly Detection and Reactive Planning with Large Language Models](https://mlsanity.com/paper/2407.08735/) (2024)
- [Semantic Anomaly Detection with Large Language Models](https://mlsanity.com/paper/2305.11307/) (2023)
- [A Survey for Foundation Models in Autonomous Driving](https://mlsanity.com/paper/2402.01105/) (2024)
- [Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning](https://mlsanity.com/paper/2408.14037/) (2024)

## Built on by (most cited first, 10 of 10)

- [ReconVLA: An Uncertainty-Guided and Failure-Aware Vision-Language-Action Framework for Robotic Control](https://mlsanity.com/paper/2604.16677/) (2026)
- [Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models](https://mlsanity.com/paper/2606.09749/) (2026)
- [Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning](https://mlsanity.com/paper/2602.08167/) (2026)
- [Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systems](https://mlsanity.com/paper/2510.21254/) (2025)
- [CMP: Robust Whole-Body Tracking for Loco-Manipulation via Competence Manifold Projection](https://mlsanity.com/paper/2604.07457/) (2026)
- [Foundation models on the bridge: Semantic hazard detection and safety maneuvers for maritime autonomy with vision-language models](https://mlsanity.com/paper/2512.24470/) (2025)
- [Vision-Based Safe Human-Robot Collaboration with Uncertainty Guarantees](https://mlsanity.com/paper/2604.15221/) (2026)
- [How to Utilize Failure Demo Data?: Effective Data Selection for Imitation Learning Using Distribution Differences in Attention Mechanism](https://mlsanity.com/paper/2605.07560/) (2026)
- [Don't Fool Me Twice: Adapting to Adversity in the Wild with Experience-Driven Reasoning](https://mlsanity.com/paper/2605.31119/) (2026)
- [Predictive Semantic Safety: From Visual Physical Reasoning to Safety-Critical Control](https://mlsanity.com/paper/2609.34356/) (2026)

## Abstract (arXiv)

While foundation models offer promise toward improving robot safety in out-of-distribution (OOD) scenarios, how to effectively harness their generalist knowledge for real-time, dynamically feasible response remains a crucial problem. We present FORTRESS, a joint reasoning and planning framework that generates semantically safe fallback strategies to prevent safety-critical, OOD failures. At a low frequency under nominal operation, FORTRESS uses multi-modal foundation models to anticipate possible failure modes and identify safe fallback sets. When a runtime monitor triggers a fallback response, FORTRESS rapidly synthesizes plans to fallback goals while inferring and avoiding semantically unsafe regions in real time. By bridging open-world, multi-modal reasoning with dynamics-aware planning, we eliminate the need for hard-coded fallbacks and human safety interventions. FORTRESS outperforms on-the-fly prompting of slow reasoning models in safety classification accuracy on synthetic benchmarks and real-world ANYmal robot data, and further improves system safety and planning success in simulation and on quadrotor hardware for urban navigation. Website can be found at https://milanganai.github.io/fortress.