I am a post doctoral associate at the School of Computing at University of Nebraska - Lincoln. I earned a PhD degree in Electrical and Computer Engineering from Georgia Institute of Technology in May 2022. My research interest include safe and controllable perception in autonomous systems, assured autonomy, resource efficient Deep neural Network s(DNN), sensor data fusion and fault-detection in machine vision. I am also interested in DNN accelerator for embedded systems, image sensor architecture, situational awareness in AI and runtime monitoring of DNN based control systems such as autonomous vehicles and drones.
Autonomous Cyber Physical Systems (CPS) such as Autonomous Vehicles (AV), robots and drones are being developed by the research community for large scale deployments in real world applications such as agriculture, defense, urban planning etc. To operate safely in such diverse and dynamic scenarios, these systems must be aware of their own limitations and react accordingly. Closed-Loop Perception combines ideas from computer vision, embedded systems, and control theory to create a perception system that can introspect and adapt to the real-time requirements of an Autonomous CPS System operating in the wild. My research on the Closed-Loop Perception indicates that the Perception system can be controlled by an intelligent feedback signal to improve the accuracy of perception tasks in regions of interest by focusing computational resources on regions most important to safety.