The Department of Defense (DoD) is seeking proposals for improved data collection and knowledge graphing in the Tactical Assault Kit (TAK) ecosystem. The objective of this topic is to demonstrate the capability to define, capture, organize, label, and reason over the data generated by end-user devices and servers in the TAK ecosystem for use in machine learning model development, re-training, fine-tuning, and federated learning. The technology should leverage general-purpose machine learning tools, Android sensor hubs, and semantic network/knowledge graphing tools to extend the TAK-ML framework. The Phase I award is not required, and the offeror should provide documentation demonstrating accomplishment of a "Phase I-type" effort in the Direct to Phase II proposal. Phase II objectives include the development of technologies to collect and harness data from the TAK ecosystem for machine learning tasks, integrating with AFRL toolkits. Successful Phase II technologies may be candidates for Phase III development and potential transition to the TAK ecosystem or other AFRL programs. The project duration and funding specifics are not provided in the document. For more information, refer to the DoD SBIR 23.3 BAA solicitation notice on grants.gov.