Research Interest

My research focus is on increasing self-awareness of vehicles about their obstructed environments via enhancing collaborative sensing and communication between the different sensor nodes placed on the vehicles. I am currently working on designing algorithms that select optimal sensor subsets in a communication constrained network such that the best coverage-age of information trade-off is achieved. Nodes may be both consumers and producers of sensed information. Consumers express interest in information about particular locations, e.g., obstructed regions and/or road intersections, whilst producers provide updates on what they are currently able to see. Accordingly, I introduce and explore optimizing trade-offs between the coverage and the space-time average of the “age” of the information available to consumers.

My interests also include estimation theory, computer vision and reinforcement learning. I had the opportunity to intern at Qualcomm for two consecutive summers (2019-2020), where I worked on modeling and generating the local map of a self-driving car. Accurate localization of vehicles in 3D is critical and crucial for the safety of the self-driving car. My role was to design, test and implement algorithms to accurately locate the vehicle in its ego-plane. The project included concepts from different fields, such as robotics, estimation theory, deep-learning and computer vision.