An augmented Petri net for modeling and control of assembly tasks with uncertainties

Uncertainties are inevitable in robotic assembly in unstructured environment since it is difficult to construct fixtures to guide motions of robots. This study proposes an augmented Petri net to model and control assembly tasks in unstructured environment. Conditions and costs of state changes can be simply computed from the output functions of the Petri net model. An algorithm is also proposed to adapt the model on-line. The model constructed by the algorithm is more compact and efficient than an off-line model since its states and events are dynamically modified on-line. The proposed method is evaluated by experiments with L-type peg-in-hole assembly using a two-arm robot system.