A Machine Learning Approach for Collaborative Robot Smart Manufacturing Inspection for Quality Control Systems
| Autor: | Lucas de Azevedo Fernandes, Thadeu Brito, Paulo Leitão, Luis Piardi, José Lima, Jonas Queiroz |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Flexibility (engineering)
0209 industrial biotechnology Computer science media_common.quotation_subject Quality control Context (language use) 02 engineering and technology Industrial and Manufacturing Engineering Task (project management) 020303 mechanical engineering & transports 020901 industrial engineering & automation 0203 mechanical engineering Artificial Intelligence Human–computer interaction Path (graph theory) Trajectory Robot Quality (business) media_common |
| Zdroj: | Procedia Manufacturing. 51:11-18 |
| ISSN: | 2351-9789 |
| DOI: | 10.1016/j.promfg.2020.10.003 |
| Popis: | The 4th industrial revolution promotes the automatic inspection of all products towards a zero-defect and high-quality manufacturing. In this context, collaborative robotics, where humans and machines share the same space, comprises a suitable approach that allows combining the accuracy of a robot and the ability and flexibility of a human. This paper describes an innovative approach that uses a collaborative robot to support the smart inspection and corrective actions for quality control systems in the manufacturing process, complemented by an intelligent system that learns and adapts its behavior according to the inspected parts. This intelligent system that implements the reinforcement learning algorithm makes the approach more robust once it can learn and be adapted to the trajectory. In the preliminary experiments, it was used a UR3 robot equipped with a Force-Torque sensor that was trained to perform a path regarding a product quality inspection task. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|