A Photorealistic Dataset and Vision-Based Algorithm for Anomaly Detection During Proximity Operations in Lunar Orbit
面向月球轨道近距操作的逼真数据集和基于视觉的异常检测算法
机构 * Space and Terrestrial Autonomous Robotic Systems (STARS) Laboratory at the University of Toronto Institute for Aerospace Studies (UTIAS)(多伦多大学航空航天研究所(UTIAS)空间与地面自主机器人系统实验室) ; Toronto Robotics and AI Laboratory (TRAIL) at the University of Toronto Institute for Aerospace Studies (UTIAS)(多伦多大学航空航天研究所(UTIAS)多伦多机器人与人工智能实验室) ; MDA Space Inc.(MDA航天公司)
AI总结 本文提出MRAD算法,通过月球轨道合成数据集ALLO实现空间域异常检测,展现算法在像素和图像层面的高检测性能,推动空间操作中鲁棒的异常检测方法发展。
Comments In IEEE Robotics and Automation Letters (RA-L) and presented at the IEEE International Conference on Robotics and Automation (ICRA'26), 1-5 Jun. 2026, Vienna, Austria
Journal ref IEEE Robotics and Automation Letters (RA-L), Vol. 11, No. 3, pp. 2418 - 2415, Mar. 2026