Securing multi-agent systems through physical cognition and control synthesis:
- Project website: http://sites.bu.edu/securingmas/
- NSF Award: https://nsf.gov/awardsearch/showAward?AWD_ID=1932162
This project will develop the foundations of a cross-layer paradigm for building adaptive, dependable and secure systems under weakly-hard real-time constraints.
Four exciting talks from industry and academia on the topic of safety assurance of autonomous systems using formal reasoning: https://iccad.com/event_details?id=283-7-A!
Our paper "ReachNN: Reachability Analysis of Neural-Network Controlled Systems" has been accepted to appear at EMSOFT'19. Congratulations to Jiameng and our collaborators at Northwestern and Dayton!
Paper on Safety-Guided Deep Reinforcement Learning via Online Gaussian Process Estimation accepted at ICLR'19 Workshop on SafeML. Congratulations, Jiameng!
Papers on resilience of multi-robot systems to physical masquerade attacks accepted at AAMAS'19 and SafeThings'19. Congratulations, Kacper!