Search results

The purpose of this paper is to present the development of an architecture for real‐time routing of automated guided vehicles (AGV) in a random flexible manufacturing system (FMS).

AGV routing problem is modeled using an evolutionary algorithm‐based intelligent path planning model, which handles vehicle assignments to material handling requests and makes routing decisions with the objective of maximizing the system throughput. The architecture is implemented on a 3‐layer software environment in order to evaluate the effectiveness of the proposed model.

The proposed architecture, along with the evolutionary algorithm‐based routing model, is implemented in a simulated FMS environment using hypothetical production data. In order to benchmark the performance of the path planning algorithm, the same FMS model is run by traditional dispatching rules. The analysis shows that the proposed routing model outperforms the traditional dispatching rules for real‐time routing of AGVs in many cases.

Future work includes expanding the scope of the current work by developing and implementing other routing models and benchmarking them against the proposed model on different performance measures.

The implementation of evolutionary algorithms in real‐time routing of AGVs is unique. In addition, due to its modularity, the proposed 3‐layer architecture can allow effective and efficient integration of different real‐time routing algorithms; therefore it can be used as a benchmarking platform.