Path planning of multirobot systems using Petri net models. Results and open problems.

Abstract

This paper presents a trajectory planning approach in multirobot systems based on Petri net models. This type of models is very useful for high-level specifications since, in this case, the classical planning methods (potential functions, RRT algorithms, RRT*) cannot be used being difficult to determine a priori the sequence of configurations for each robot. This work presents the formal definition of the Robot Motion Petri net that is obtained from a partition of the environment in cells. Using the structure of the Petri net, in case of specifications defined as Boolean or Linear Temporal Logic (LTL) formulas, different optimization problems are presented that can be used to obtain trajectories for robots. The main advantage of models based on Petri nets is their scalability with respect to the number of robots. This makes it possible to efficiently solve planning problems with a large number of robots. In the second part of the paper, some extensions and new results for distributed planning in unknown environments and with partial communications between robots are presented.