2019/02/06 by Shreyas Ramakrishna, Ramakrishna, Shreyas, Charles Hartsell +8
Computer Science · Engineering · Mathematics · #Adversarial Robustness in Machine Learning #Architecture #Artificial Intelligence (cs.AI) #Computer network #Computer science #Controller (irrigation) #Cyber-physical system #Distributed computing #FOS: Computer and information sciences #Formal Methods in Verification #Fuel Cells and Related Materials #Key (lock) #Mathematics #Middleware (distributed applications) #Robotics (cs.RO) #Simplex #Testbed #cs.AI #cs.RO
paper · pdf · doi:10.48550/arxiv.1902.02432
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2019/02/06 · arxiv created 2020/03/10 · arxiv updated 2020/03/11 · openalex created_date 2022/07/29 · openalex updated_date 2026/08/05
Cyber Physical Systems (CPS) have increasingly started using Learning Enabled\nComponents (LECs) for performing perception-based control tasks. The simple\ndesign approach, and their capability to continuously learn has led to their\nwidespread use in different autonomous applications. Despite their simplicity\nand impressive capabilities, these models are difficult to assure, which makes\ntheir use challenging. The problem of assuring CPS with untrusted controllers\nhas been achieved using the Simplex Architecture. This architecture integrates\nthe system to be assured with a safe controller and provides a decision logic\nto switch between the decisions of these controllers. However, the key\nchallenges in using the Simplex Architecture are: (1) designing an effective\ndecision logic, and (2) sudden transitions between controller decisions lead to\ninconsistent system performance. To address these research challenges, we make\nthree key contributions: (1) \dynamic-weighted simplex strategy -- we\nintroduce ``weighted simplex strategy" as the weighted ensemble extension of\nthe classical Simplex Architecture. We then provide a reinforcement learning\nbased mechanism to find dynamic ensemble weights, (2) \middleware\nframework -- we design a framework that allows the use of the dynamic-weighted\nsimplex strategy, and provides a resource manager to monitor the computational\nresources, and (3) \hardware testbed -- we design a remote-controlled\ncar testbed called DeepNNCar to test and demonstrate the aforementioned key\nconcepts. Using the hardware, we show that the dynamic-weighted simplex\nstrategy has 60 % fewer out-of-track occurrences (soft constraint violations),\nwhile demonstrating higher optimized speed (performance) of 0.4 m/s during\nindoor driving than the original LEC driven system.\n