Digital twins employs simulation in conjunction with virtual environments and a variety of data coming from different plant equipment and physical systems to continuously update the digital models of the world in a feedback loop scheme to facilitate the decision-making processes. The heterogeneity of existing hardware and software requires the development of software architectures able to deal with the information exchange due to the integration and interaction of several system components and autonomous decision-making systems. In this work we propose the design and construction of a software architecture that integrates a manufacturing process simulator with the well-known robot operating system (ROS-Robot Operating System) to easily interchange information with an autonomous decision-making system. The proposal is tested with the simulator Tecnomatix and the free distribution ROS Melodic. We present an instance of software architecture for a typical complex case study of manufacturing plants and demonstrate its easy integration with an autonomous decision-making system based on the reinforcement- learning paradigm.

中文翻译：

---

集成 ROS 和 Tecnomatix 以开发基于数字孪生的智能工厂决策系统

数字孪生将模拟与虚拟环境以及来自不同工厂设备和物理系统的各种数据结合使用，以反馈循环方案不断更新世界的数字模型，以促进决策过程。由于多个系统组件和自主决策系统的集成和交互，现有硬件和软件的异构性需要开发能够处理信息交换的软件架构。在这项工作中，我们提出了一种软件架构的设计和构建，该架构将制造过程模拟器与著名的机器人操作系统（ROS-Robot Operating System）集成在一起，以轻松地与自主决策系统交换信息。该提案已使用模拟器 Tecnomatix 和免费分发的 ROS Melodic 进行测试。我们为制造工厂的典型复杂案例研究提供了一个软件架构实例，并展示了它与基于强化学习范式的自主决策系统的轻松集成。