Industrial robotics are redefining inspection and maintenance routines across multiple sectors, enhancing safety, efficiency, and environmental sustainability. In outdoor industrial facilities, it is crucial to inspect and repair complex surfaces affected by corrosion. To address this challenge, mobile manipulators have been developed to navigate these facilities, identify corroded areas, and apply protective coatings. However, given that this technology is still in its infancy and the consequences of improperly coating essential equipment can be significant, human oversight is necessary to review the robot's corrosion identification and repair plan. We present a practical and scalable Augmented Reality (AR)-based system designed to empower non-experts to visualize, modify, and approve robot-generated surface corrosion repair plans in real-time. Built upon an AR-based human-robot interaction framework, Augmented Robot Environment (AugRE), we developed a comprehensive AR application module called Situational Task Accept and Repair (STAR). STAR allows users to examine identified corrosion images, point cloud data, and robot navigation objectives overlaid on the physical environment within these industrial environments. Users are able to additionally make adjustments to the robot repair plan in real-time using interactive holographic volumes, excluding critical nearby equipment that might be at risk of coating overspray. We demonstrate the entire system using a Microsoft HoloLens 2 and a dual-arm mobile manipulator. Our future research will focus on evaluating user experience, system robustness, and real-world validation.

翻译：工业机器人技术正在重新定义多个领域的检查与维护流程，提升安全性、效率与环境可持续性。在室外工业设施中，对受腐蚀影响的复杂表面进行检查与修复至关重要。为应对这一挑战，已开发出移动机械臂系统，使其能够在设施中导航、识别腐蚀区域并施加防护涂层。然而，鉴于该技术仍处于发展初期，且关键设备涂层不当可能造成严重后果，必须通过人工监督来审核机器人的腐蚀识别与修复计划。我们提出一种实用且可扩展的增强现实(AR)系统，旨在让非专业用户能够实时可视化、修改并批准机器人生成的表面腐蚀修复方案。该系统基于增强现实人机交互框架Augmented Robot Environment (AugRE)构建，研发了名为Situational Task Accept and Repair (STAR)的综合AR应用模块。STAR允许用户在工业环境中查看叠加在物理环境上的腐蚀识别图像、点云数据及机器人导航目标。用户还能利用交互式全息体积实时调整机器人修复计划，排除可能受涂层飞溅影响的邻近关键设备。我们使用Microsoft HoloLens 2与双臂移动机械臂完成了系统整体演示。未来研究将聚焦于用户体验评估、系统鲁棒性验证及真实场景应用测试。