https://store-images.s-microsoft.com/image/apps.37659.52cd5a59-6e5f-4e38-ab21-30ba59abe506.bed2b83b-b96e-4127-a412-2d84bcd02563.2988bf30-2c8f-419e-83ab-3253c1b14c46
Material handling with Deep Reinforcement Learning on Bonsai
by ENGINEERING - INGEGNERIA INFORMATICA - SPA
Just a moment, logging you in...
Simulate material handling shared between two shuttles with Deep Reinforcement Learning on Bonsai
We provide a simulation model to apply Deep Reinforcement Learning for material handling in manufacturing industries. The design and training of the DRL model was done using the Microsoft Project Bonsai platform.
Challenge
Material handling is the process of movimentating materials from one place to another within a manufacturing plant. The costs for this activity are not negligible (e.g. labor, equipment, time and distance) and therefore material handling heuristics are continuously changed to meet production constraints and customer demand by adjusting resources accordingly.
Material handling is the process of movimentating materials from one place to another within a manufacturing plant. The costs for this activity are not negligible (e.g. labor, equipment, time and distance) and therefore material handling heuristics are continuously changed to meet production constraints and customer demand by adjusting resources accordingly.
Thus, the flexibility of a materials management system is crucial in order to enable optimal and quick decision making to best handle uncertain situations.
Use case
We have realized a use case on two shuttles that transport materials (one material at a time) while sharing the same track.
The materials are placed in the pallet rack and each is assigned a destination chosen from 4 destinations.
Once the pallet has arrived at its destination, it remains at the destination for a fixed time, after which the destination will be free again.
The objective is to transport the materials to their destinations in the shortest possible time, avoiding collisions between the two shuttles and considering that each destination can hold a maximum of 1 pallet at the same time.
In order to produce this use case we adopted the AnyLogic simulator and the Inkling code. Documentation and further discussions of the use case can be found on the accompanying simulation model description document.
At a glance
https://store-images.s-microsoft.com/image/apps.4258.52cd5a59-6e5f-4e38-ab21-30ba59abe506.7f21b4c4-ef52-41cf-a1c7-ac29c7652b86.2b9fd1d4-79e2-4d9e-95de-5b8ab610a2d7
https://store-images.s-microsoft.com/image/apps.25755.52cd5a59-6e5f-4e38-ab21-30ba59abe506.17f48707-a03f-4749-b961-c6603ab48a54.ba7532c2-c95d-4026-bea2-7ada862a7fbe