An SPN planning methodology with neural networks

This paper presents a planning methodology based on stochastic Petri nets and neural nets. The SPN plan method generates a global plan based on the states of the elements of the universe of discourse. The plan includes all the possible conflict-free planning paths to achieve the goals. Moreover, it presents all the interesting features of the SPN model, such as synchronization, parallelism, concurrency and timing of events. An associated neural network is used for searching the SPN network for the appropriate selection of plans. The coordination of two robot hands is used as an illustrative example for the proposed method