Deep Reinforcement Learning for Robot Batching Optimization and Flow Control
Deep Reinforcement Learning for Robot Batching Optimization and Flow Control
- New search for: Hildebrand, Max
- New search for: Andersen, Rasmus Skovgaard
- New search for: Bøgh, Simon
- New search for: Hildebrand, Max
- New search for: Andersen, Rasmus Skovgaard
- New search for: Bøgh, Simon
Robot batching is an optimization problem found in many industrial applications. Current state-of-the-art approaches utilize a combination of heuristic based parameters and statistical analysis. This approach necessitates many tunable parameters, which again provides challenges when delivering systems to new customers. We challenge current state-of-the-art in statistical approaches by presenting a novel application of a policy gradient method for a Deep Reinforcement Learning (DRL/RL) agent. We have developed a Unity simulation framework of an existing robot- batching cell, on which a RL agent is able to successfully train and obtain a policy for performing robot batching, using a tabula rasa approach. The trained agent is capable of packaging 47.86% of 1218 total batches within the prescribed tolerances, with a positive give-away of 8.76%. The application of DRL in performing robot batching is to the authors knowledge the first of its kind.
Document information
Deep Reinforcement Learning for Robot Batching Optimization and Flow Control
2020-11-01
Hildebrand , M , Andersen , R S & Bøgh , S 2020 , ' Deep Reinforcement Learning for Robot Batching Optimization and Flow Control ' , Procedia Manufacturing , vol. 51 , pp. 1462-1468 . https://doi.org/10.1016/j.promfg.2020.10.203
Article (Journal)
Electronic Resource
English
| DDC: | 629 |
Similar titles
Investigating exploration for deep reinforcement learning of concentric tube robot control
| BASE | 2020
| European Patent Office | 2022