Multi-variant Planing for Dynamic Problems with Agent-based Signal Modeling

The problem of planning for groups of autonomous beings is gaining attention over the last few years. Real life tasks, like mobile robots coordination or urban traffic management, need robust and flexible solutions. In this paper a new approach to the problem of multi-variant planning in such systems is presented. It assumes use of simple reactive controllers by the beings, however the state observation is enriched by dynamically updated model, which contains planning results. The approach gives promising results in the considered use case, which is the Multi Robot Task Allocation problem.