8 papers · 1 filter
Foundation models on the bridge: Semantic hazard detection and safety maneuvers for maritime autonomy with vision-language models
Kim Alexander Christensen, Andreas Gudahl Tufte, Alexey Gusev +5
The draft IMO MASS Code requires autonomous and remotely supervised maritime vessels to detect departures from their operational design domain, enter a predefined fallback that not…
Preventing Robotic Jailbreaking via Multimodal Domain Adaptation
Francesco Marchiori, Rohan Sinha, Christopher Agia +4
Large Language Models (LLMs) and Vision-Language Models (VLMs) are increasingly deployed in robotic environments but remain vulnerable to jailbreaking attacks that bypass safety me…
Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning
Milan Ganai, Rohan Sinha, Christopher Agia +3
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, dyn…
CUPID: Curating Data your Robot Loves with Influence Functions
Christopher Agia, Rohan Sinha, Jingyun Yang +5
In robot imitation learning, policy performance is tightly coupled with the quality and composition of the demonstration data. Yet, developing a precise understanding of how indivi…
RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models
Jacky Kwok, Christopher Agia, Rohan Sinha +5
Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in visuomotor control, yet ensuring their robustness in unstructured real-world environments remains a…
Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress
Christopher Agia, Rohan Sinha, Jingyun Yang +4
Robot behavior policies trained via imitation learning are prone to failure under conditions that deviate from their training data. Thus, algorithms that monitor learned policies a…