Provably Guaranteed Polytopic Uncertainty Quantification for SLAM
具有可证明保证的多面体不确定性量化用于SLAM
机构 * School of Data Science, The Chinese University of Hong Kong, Shenzhen(数据科学学院,香港中文大学(深圳)) ; School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen(人工智能学院,香港中文大学(深圳)) ; Department of Electrical and Electronic Engineering, Imperial College London(电子与电气工程系,帝国理工学院伦敦分校) ; School of Aerospace, Mechanical and Mechatronic Engineering, The University of Sydney(航空航天、机械与机电工程学院,悉尼大学)
AI总结 本文提出基于多面体表示的不确定性量化算法,通过前向映射、后向位姿跟踪和位姿复合三个模块,为3D-3D路标SLAM提供可证明的确定性保证,并结合共形预测提高实用性。
Comments 16 pages, 10 figures; accepted by Robotics: Science and Systems 2026