Multi-agent systems for the real world

To support real world applications, a multi-agent system must deal with all relevant issues from the environment, the problem, the users and the technological infrastructure. The real world introduces restrictions and noise at all levels. The communication network may provide intermittent connectivity, variable latency and limited bandwidth. Devices have limited computation. The world is uncertain and dynamic. Tasks, resources and the team objective can change. The software may give incorrect advice. Users can make errors and initiate unplanned actions.