Project Grant 2153440

This Project Grant from the National Science Foundation's Division of Computing and Communication Foundations, under the Computer and Information Science and Engineering program (CFDA 47.070), provides $173,894 to Kennesaw State University Research And Service Foundation, Inc. to develop a neuromorphic processing framework for spatiotemporal fusion of visual sensors. The awardee will design a hybrid neuromorphic framework composed of spiking neural networks and conventional artificial neural networks to process event-frame fused visual data from dynamical vision sensors and standard cameras. This framework will be adapted for unmanned aerial vehicles and robots to develop an end-to-end closed-loop neuromorphic platform for high-speed visual tasks such as detection, tracking, and localization. The awardee will also explore model compression of hybrid neural networks and hardware accelerator architecture design for the proposed framework. This work supports the grant program's goals of advancing computing and communications research and education.