Robotic low stress assembly of large, compliant components

大型柔顺部件的装配包括四个主要步骤：首先，必须拿起部件，然后带到装配地点，放置在最佳位置，最后在装配点连接。大型兼容组件的自动化装配目前还不是最先进的技术，因为这样做还有许多未解决的挑战。其中包括组件的大规模，其变形的关键作用以及需要非常灵活的规划和执行的各种应用。另一方面，机器人技术正越来越多地进入工业制造和生产领域。自主工业移动机械手（AIMM）是移动平台和机械臂的融合，在这里发挥着特殊的作用。然而，到目前为止，移动机器人还没有广泛应用于工业生产，特别是在大规模装配过程中。在各自的生产环境中，如航空航天工业，使用移动平台是可取的。该项目的目标是使用aimm进行大型柔性部件的低应力装配。AIMM内部的必要研究主要包括三个主要领域。首先，有一些主题处理特定组件的6D位置估计。这个领域在很大程度上依赖于人工神经网络的发展和自动训练它们的能力。其次，需要研究复杂的机器人控制方法，包括离线最优路径规划、执行时间、路径长度和能量优化、环境建模、多传感器融合以及工件和场景施加的重大约束下的在线规划方法。最后，与大型部件的交互在装配规划和执行方面提出了不成比例的更复杂的挑战，这仍然是未知的科学领域。在小型物体的移动处理中不存在的具体挑战来自机动和安装大型组件的规模，地球重力场的影响，因为它分别影响被操纵组件和机器人平台本身的内应力和状态，并且尺寸越来越大。这需要对部件的物理特性和变形进行建模，并将这些模型插入到移动和装配计划中，以在整个运输和装配过程中保持低应力。因此，在地球重力场中使用aimm组装大型部件在文献中基本上没有解决。因此，该项目的目标是研究和开发适当的方法，以推进并结合adaptronics (Sinapius)，力学（Böl）和机器人（Steil）的专业知识来实现这一目标。

The assembly of large, compliant components consists of four main steps: First, the components must be picked up, then brought to the place of assembly, placed there in the optimal position, and finally joined at the assembly points. Automated assembly of large, compliant components is by no means state of the art today as there are numerous unsolved challenges in doing so. These include the large scale of the components, the crucial role of their deformations and the high variety of applications that require very flexible planning and execution. On the other hand, robot technology is increasingly finding its way into industrial manufacturing and production. The Autonomous Industrial Mobile Manipulator (AIMM), a fusion of a mobile platform and a robotic arm, plays a particular role here. However, so far mobile robots have not been widely adopted in industrial production, especially not in large-scale assembly processes. In a respective production environment such as the aerospace industry, the use of mobile platforms is desirable. This project targets the use of AIMMs for the low-stress assembly of large flexible components. The necessary research within AIMM mainly covers three major areas. First, there are topics that deal with 6D position estimation of a particular component. This area is heavily dependent on the development of artificial neural networks and the ability to train them automatically. Second, there is a need for research on sophisticated robot control dealing with offline optimal path planning, execution time, path length and energy optimization, environment modeling, multisensor fusion, and online planning approaches under the significant constraints that the workpiece and the scenario impose. Finally, interaction with large components presents a disproportionately more complex challenge in assembly planning and execution that is still uncharted scientific terrain. Specific challenges that are not present in mobile handling of small objects arise from the scale of maneuvering and mounting large components, the influence of the earth's gravity field as it affects the internal stresses and states for both the manipulated component and the robotic platform itself with increasing size, respectively. These require modeling of the component’s physical properties and deformations and insertion of that models in the movement and assembly planning to maintain low stress during the entire transport and assembly process. The assembly of large components in the Earth's gravity field using AIMMs is therefore largely unaddressed in the literature. Therefore, the aim of this project is to research and develop appropriate methods that advance and combine expertise from adaptronics (Sinapius), mechanics (Böl), and robotics (Steil) to this aim.