Dr. Jithin Jagannath, Director of the Marconi-Rosenblatt AI/ML Lab at ANDRO Computational Solutions, LLC is proud to announce his teams paper, MR-iNet Gym: Framework for Edge Deployment of Deep Reinforcement Learning on Embedded Software Defined Radio, won the Best Paper Award at the ACM WiseML conference.
The team showed how they leveraged their MR-iNet Gym to demonstrate one such instance of distributed power control using an adaptive LPI/D waveform. The entire LPI/D PHY layer and the Intelligent protocol stack that employs the RL engine runs on Deepwave Digital‘s AIR-T SDR.
At the Marconi-Rosenblatt AI/ML Lab, we have further advanced the solutions to provide joint frequency and power allocation in the presence of jammers demonstrating uninterrupted video transmission over-the-air while making real-time decisions. This is just the first step and a lot more exciting work lies ahead at the intersection of machine learning and wireless.
This initial part of our work was presented at ACM Workshop on Wireless Security and Machine Learning (WiseML 2022).
