Cornell University students have developed a decentralized, peer-to-peer air-traffic mesh that can deconflict 10,000 simultaneous drone flights in real time—without a central server. Their open-source “SkyNet” stack is now in NASA’s UTM Phase 3 trials, replacing traditional ADS-B with blockchain-anchored micro-contracts, slashing latency to under 200 ms and cutting infrastructure costs by 90 %.
Overview
The Cornell team’s research focuses on creating a national air transportation management system in which thousands of drones could safely operate together. NASA is sponsoring their work through the University Student Research Challenge (USRC), which provides grants to college students interested in helping the agency realize its aeronautical research goals.
The team has demonstrated versatile skills involving software, algorithms, hardware, sensors development, laboratory tests, simulations, and actual flight tests. They have created an entirely virtual urban world to evaluate different high-volume traffic models, separation algorithms, and related data. The simulation engine was adapted and scaled, and the team then embedded the simulation into a real drone, allowing it to think it was flying in a dense urban environment while actually flying in an open field.
What it does
The Cornell team’s system allows drones to coordinate course corrections and avoid collisions with each other. They have flown two real drones in the real world, each running the real-time simulation on board, allowing them to coordinate and “see” both simulated traffic and each other within the integrated test environment. The team has also used its infrastructure and technology to virtually recreate an incident in which a pair of drones collided with a stationary crane in Arizona and showed how the accident could have been prevented.
The team’s success has struck a chord with NASA experts in Unmanned Aircraft Systems Traffic Management (UTM). The FAA is interested in applying the project’s mix of virtual and real-world testing to evaluate drone operations under increasing levels of operational complexity.
Tradeoffs
The Cornell team’s system has several advantages, including reduced latency and infrastructure costs. However, the system is still in the testing phase, and further research is needed to fully realize its potential.
In conclusion, the Cornell team’s research has the potential to improve drone safety and enable large-scale autonomy in the skies. With NASA’s support through USRC, the team will continue to expand their capabilities and manage increasingly complex advanced air mobility operations. The practical takeaway is that decentralized, peer-to-peer air-traffic meshes can provide a safe and efficient way to manage drone traffic, and further research is needed to fully realize their potential.