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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ganai, Milan, Sinha, Rohan, Agia, Christopher, Morton, Daniel, Di Lillo, Luigi, Pavone, Marco
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914055173701632
author Ganai, Milan
Sinha, Rohan
Agia, Christopher
Morton, Daniel
Di Lillo, Luigi
Pavone, Marco
author_facet Ganai, Milan
Sinha, Rohan
Agia, Christopher
Morton, Daniel
Di Lillo, Luigi
Pavone, Marco
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10547
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning
Ganai, Milan
Sinha, Rohan
Agia, Christopher
Morton, Daniel
Di Lillo, Luigi
Pavone, Marco
Robotics
Artificial Intelligence
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.
title Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2505.10547