Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning
Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning
Foundation models can provide robust high-level reasoning on appropriate safety interventions in hazardous scenarios beyond a robot's training data, i.e. out-of-distribution (OOD) failures. However, due to the high inference latency of Large Vision and Language Models, current methods rely on manually defined intervention policies to enact fallbacks, thereby lacking the ability to plan generalizable, semantically safe motions. To overcome these challenges we present FORTRESS, a framework that generates and reasons about semantically safe fallback strategies in real time to prevent OOD failures. At a low frequency in nominal operations, FORTRESS uses multi-modal reasoners to identify goals and anticipate failure modes. 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.
Milan Ganai、Rohan Sinha、Christopher Agia、Daniel Morton、Marco Pavone
自动化技术、自动化技术设备计算技术、计算机技术
Milan Ganai,Rohan Sinha,Christopher Agia,Daniel Morton,Marco Pavone.Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning[EB/OL].(2025-05-15)[2025-06-30].https://arxiv.org/abs/2505.10547.点此复制
评论