A robotic soccer passing task using petri net plans

The Petri Net Plans framework (PNPs [2]) allows the representation of high level programs for robotic behavior, providing all the action features needed to describe complex plans in dynamic, partially observable and unpredictable environments. The multi-robot extension of PNPs allows the synchronization of actions among different robots, the performance of deliberate cooperation and the cooperative handling of local failures in a multi-robot system. A multi-robot PNP is automatically divided by each single robot of the system for the individual execution. The robots perform their actions relying on their individual knowledge base, and during the plan execution they are able to communicate through a reliable channel, to attain synchronization and sharing of information. This demonstration shows the use of multi-robot PNPs for the implementation of a robotic-soccer task. Two Sony AIBO quadruped robots are placed on a soccer field with the task of passing a ball (Figure 1). Before the execution of each pass the robots dynamically assign the roles for the execution of the task (Passer, Receiver) according to the information that is exchanged during a synchronization action. The passing robot reaches and grabs the ball, waiting for its partner to be ready for receiving the pass. At the reception of an acknowledgement the ball is kicked. At the end of the pass the robots perform a new synchronization and the proce-