AI Enhances Air Mobility Planning: Streamlining Operations at Air Mobility Command
The U.S. Air Force’s Air Mobility Command (AMC) is leveraging artificial intelligence to enhance its air mobility planning, streamlining operations at the 618th Air Operations Center (AOC). The 618th AOC, the Department of Defense’s largest air operations center, manages a vast fleet of aircraft, coordinating routes, fueling, supply loading, and mission assignments to ensure rapid response to global national security needs.
Colonel Joseph Monaco, the director of strategy at the 618th AOC, emphasized the shift from traditional methods to chat-based communication, stating, “It takes a lot of work to get a missile defense system across the world, for example, and this coordination used to be done through phone and email. Now, we are using chat, which creates opportunities for artificial intelligence to enhance our workflows.”
To harness the power of AI, the 618th AOC is sponsoring Lincoln Laboratory to develop AI tools through the Conversational AI Technology for Transition (CAITT) project. This initiative is part of a broader effort to integrate AI technology into the Air Force’s Next Generation Information Technology for Mobility Readiness Enhancement (NITMRE).
CAITT utilizes natural language processing (NLP) to enable AI models to understand and process human language. Courtland VanDam, a researcher at Lincoln Laboratory’s AI Technology and Systems Group, explained, “We are utilizing NLP to map major trends in chat conversations, retrieve and cite specific information, and identify and contextualize critical decision points.”
One of the most advanced tools within CAITT is topic summarization, which extracts trending topics from chat messages and presents them in a user-friendly format. For instance, a trending topic might highlight a potential delay due to crew members missing Congo visas, summarizing relevant chats and linking back to specific exchanges.
Semantic search is another tool in production, enhancing the chat service’s search engine by allowing users to ask questions in natural language. This tool uses neural networks to understand user intent and provide intelligent results, even if the query doesn’t match every word in the chat messages.
Other tools under development include features to automatically add users to relevant chat conversations, predict ground time for unloading cargo, and summarize key processes from regulatory documents to guide operators in mission planning.
The CAITT project emerged from the DAF–MIT AI Accelerator, a collaborative effort between MIT, Lincoln Laboratory, and the Department of the Air Force (DAF). Lieutenant Colonel Tim Heaton noted, “Through our involvement in the AI Accelerator via the NITMRE project, we realized we could do something innovative with all of the unstructured chat information in the 618th AOC.”
As Lincoln Laboratory researchers refine the CAITT tools, they are transitioning them to the 402nd Software Engineering Group for implementation into the operational software environment used by the 618th AOC.
