What's Happening?
NASA's Ames Research Center in California is advancing its Flight Deck Collaborative Decision Making (CDM) Research Project to modernize cockpit communications. The project, now in Phase 5, aims to transition from analog, voice-based radio commands to a digital
data environment. This involves digitizing Very High Frequency (VHF) aircraft taxi commands and converting them into digital instructions using a Google Speech-to-Text Large Language Model (LLM). These instructions will be streamed directly to pilots' electronic flight bags (EFB) and air traffic control networks. The project employs a Ground-Based Unit (GBU) with a Raspberry Pi processing core and custom audio electronics to minimize latency and improve real-time operations. Connectsix LLC has been selected for a sole-source contract to provide hardware optimization and engineering support, with testing scheduled for November 2026 and March 2027.
Why It's Important?
This initiative is significant as it represents a shift towards more efficient and reliable communication in aviation, potentially reducing errors and improving safety. By digitizing and automating taxi instructions, NASA aims to streamline aircraft surface movements, which could lead to faster and more efficient airport operations. The use of edge AI and LLMs in this context highlights the growing role of advanced technologies in enhancing operational efficiency in the aerospace industry. This project could set a precedent for future innovations in flight operations, impacting how airlines and airports manage communications and logistics.
What's Next?
NASA plans to conduct 'Shadow Mode' and live-assessment tests to validate the system's performance, focusing on latency and word-error-rate metrics. These tests will involve live or simulated tower audio and a mock control tower environment. The results will determine the feasibility of implementing this technology on a broader scale. Additionally, NASA is open to receiving input from other organizations interested in contributing to the project, with a deadline for submissions set for July 2026. The outcomes of these tests and collaborations could influence future developments in aviation communication systems.
