AI Enhances Air Mobility Planning for Faster Response Times
The U.S. Air Force is leveraging artificial intelligence to drastically improve air mobility planning, enabling quicker responses to national security needs worldwide. The initiative focuses on streamlining communication and decision-making processes within the Air Mobility Command’s 618th Air Operations Center (AOC).
Every day, the 618th AOC handles a massive volume of communications between pilots, crew, and controllers. These controllers manage a vast fleet of aircraft, constantly evaluating variables to optimize routes, estimate refueling and supply loading times, and assign personnel. Traditionally, this intricate coordination relied heavily on phone calls and emails. Now, the shift to chat-based communication is opening doors for AI-driven enhancements.
“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,” says Colonel Joseph Monaco, the director of strategy at the 618th AOC, the Department of Defense’s largest air operations center.
The Conversational AI Technology for Transition (CAITT) project, sponsored by the 618th AOC and developed by Lincoln Laboratory, aims to address these challenges. CAITT is part of the Next Generation Information Technology for Mobility Readiness Enhancement (NITMRE) initiative, a major Air Force modernization effort.
CAITT employs natural language processing (NLP) to analyze and understand human language within the chat logs. According to Courtland VanDam, a researcher in Lincoln Laboratory’s AI Technology and Systems Group, “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 CAITT tools is topic summarization. It extracts trending topics from chat messages and presents them in a user-friendly format, highlighting critical conversations and emerging issues. For instance, a trending topic might flag “Crew members missing Congo visas, potential for delay,” providing a summary of related chats and linking back to specific exchanges.
Another tool in production is semantic search. This tool enhances the existing search engine of the chat service, allowing users to ask questions in natural language and receive intelligent results. For example, instead of typing specific keywords, a user could ask, “Why is a specific aircraft delayed?” and receive relevant information.
Other tools in development include features that automatically add users to relevant chat conversations based on their expertise, predict ground time for unloading specific cargo, and summarize key processes from regulatory documents to guide operators in mission planning.
The CAITT project originated from the DAF–MIT AI Accelerator, a collaborative effort between MIT, Lincoln Laboratory, and the Department of the Air Force (DAF). This initiative seeks to develop and transition AI algorithms and systems to benefit both the DAF and society.
As the CAITT tools mature, Lincoln Laboratory researchers are transitioning them to the 402nd Software Engineering Group, a software provider for the Department of Defense. This group will integrate the tools into the operational software environment used by the 618th AOC, ensuring practical implementation and real-world impact.
