NRI: Small: Robotic Scouts: Augmenting Human Perception for Underground Rescue

在矿难等地下救援行动中，机器人是潜在的救生工具。人类救援人员受阻于屋顶坍塌、爆炸危险、空气质量、烟尘能见度、精神压力和身体耐力。人类救援人员无法在短时间内覆盖足够的距离，往往会给事故受害者带来致命的后果。机器人能够在人类救援人员之前自主侦察并汇总环境信息，可以极大地增强态势感知，使团队能够毫不拖延地向前推进。这项提议设想了身临其境的机器人创建的3D模型，融合了许多传感器来源，并通过烟雾、灰尘、泥浆、洪水和火灾创建。这些扩展的模型为救援人员提供了不受环境条件破坏的视觉清晰度。通过激光雷达、雷达、多光谱成像和主动照明RGB传感等全新模式的融合和智能视图规划，消除了照明伪影、传感器噪声和误差。虽然世界经常被高能见度的矿难所吸引，但机器人是有形的工具，具有明显的结果，有机会成为任何救援努力的中心。救援机器人发现了第一名被困矿工，拯救了人类的生命，这种破坏作用将激励无数人欣赏科学技术在我们生活中不断演变的作用。该团队之前的地下机器人工作已经引起了相当大的压力，并开始接受机器人技术，即使是在最不利于变化的行业。调查人员将继续通过在媒体上露面、为学童进行实验室和矿山之旅以及在科学博物馆进行现场演示来推动机器人。该项目将支持各级教育，包括支持CMU在机器人方面的博士后和研究生研究，雇用REU本科生实习生，以及为CMU的移动机器人设计课程开发课程。这项研究的贡献将影响从地下生产到公民检查和国防等行业的自动化。

Robots are potential tools for life saving in underground rescue operations like mine disasters. Human rescuers are thwarted by roof falls, explosion dangers, quality of air, visibility through smoke and dust, mental stress and physical endurance. The inability of human rescuers to cover sufficient distance in a short time often has fatal consequences for accident victims. Robots which autonomously scout ahead of human rescuers and summarize environmental information can greatly enhance situational awareness, enabling teams to push forward without delay. This proposal envisions immersive, robotically-created 3D models, fused from many sensor sources and created through smoke, dust, mud, flood and fire. These expansive models provide rescuers with visual clarity that are uncorrupted by environmental condition. Illumination artifacts, sensor noise and errors are removed by fusion and intelligent view planning of radical new modalities including LIDAR, RADAR, multispectral imaging and actively-illuminated RGB sensing. While the world has often been captivated by high-visibility mine accidents, robots are tangible tools with visible results that have the opportunity to become the centerpiece of any rescue effort. The disrupting effect of the first trapped miner found and human life saved by a rescue robot would inspire countless people to appreciate the evolving role of science and technology in our lives. Prior underground robotics work by this team have generated considerable press and initiated acceptance of robotic technology in even the most change-adverse industries. The investigators will continue to push for robots through media appearances, lab and mine tours for school children and live demonstrations at science museums. This project will support education at all levels, which includes supporting postdoctoral and graduate research in robotics at CMU, employing undergraduate REU interns, and developing curriculum for the Mobile Robot Design course at CMU. Contributions from this research will impact automation in industries ranging from underground production to civic inspection, and defense.