Update: September, 2011 – Agent technology center, the research group responsible for this project and demo, has moved from our department to the Department of Computer Science. See the updates on the ATC Projects page.
Air Traffic Control (ATC) scenario provides an open multi-agent test bed that is used for air traffic simulation. ATC is build on the A-globe platform using Aglobex simulation framework. The project aim is to deploy the multi-agent technology for agent based aircraft deconfliction (collision avoidance) among several autonomous aerial vehicles (manned as well as unmanned). In our approach each vehicle is fully autonomous represented by agents. We have built on top of the concept of free flight – an approach to autonomous routing of the aircraft and continuous self-optimization of the flight trajectory. Agents can act cooperatively and non-cooperatively when addressing the See & Avoid capability of the aircraft.
Within the first two phases of the project we have designed:
- multi-agent model of individual flight modeling deconflicted free-flight of fully autonomous arcrafts,
- 2D/3D real-time visualization component and 2D web-client access component,
- component providing a route plan within times specific way-points avoiding no-flight zones,
- cooperative deconfliction negotiation among multiple aerial vehicles using rule-based and utility-based mechanisms,
- non-cooperative deconfliction using no-flight zones encapsulating predicted future positions of non-cooperative aircrafts,
- integration with freely available geographical and tactical data sources.