Luigi Di Lillo

Alessandro Zanardi, Andrea Censi, Margherita Atzei et al.

Autonomous Vehicles (AVs) promise a range of societal advantages, including broader access to mobility, reduced road accidents, and enhanced transportation efficiency. However, evaluating the risks linked to AVs is complex due to limited historical data and the swift progression of technology. This paper presents a data-driven framework for assessing the risk of different AVs' behaviors in various operational design domains (ODDs), based on counterfactual simulations of "misbehaving" road users. We propose the notion of counterfactual safety margin, which represents the minimum deviation from nominal behavior that could cause a collision. This methodology not only pinpoints the most critical scenarios but also quantifies the (relative) risk's frequency and severity concerning AVs. Importantly, we show that our approach is applicable even when the AV's behavioral policy remains undisclosed, through worst- and best-case analyses, benefiting external entities like regulators and risk evaluators. Our experimental outcomes demonstrate the correlation between the safety margin, the quality of the driving policy, and the ODD, shedding light on the relative risks of different AV providers. Overall, this work contributes to the safety assessment of AVs and addresses legislative and insurance concerns surrounding this burgeoning technology.

Milan Ganai, Rohan Sinha, Christopher Agia et al.

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.