“Machine Learning Subsystem for Autonomous Collision Avoidance on a small UAS with Embedded GPU” has been accepted to IEEE International Workshop on Communication and Networking for Swarms Robotics (Robocom) 2022. In this work, we introduce and demonstrate MR-iFLY, a framework that combines the strengths of traditional approaches and machine learning for autonomous collision avoidance for sUAS with minimal sensors. This is part of Navy SBIR Phase II work that is being done at ANDRO’s MR Lab. We are currently working on including adaptive dynamic mission control, natural user interface for human-machine teaming among other capabilities to the framework.
Read the paper here