期刊
IEEE ROBOTICS AND AUTOMATION LETTERS
卷 6, 期 4, 页码 6985-6992出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2021.3096745
关键词
Localization; autonomous vehicle navigation; vision-based navigation
类别
资金
- Australian Government [AUSMURIB000001]
- ONR MURI [N00014-19-1-2571]
- Queensland University of Technology (QUT) through the Centre for Robotics
Probabilistic state-estimation approaches provide a principled foundation for localization systems, and the new probabilistic topometric localization system effectively addresses the shortcomings of existing systems, achieving superior performance in the presence of appearance change and route deviations.
Probabilistic state-estimation approaches offer a principled foundation for designing localization systems, because they naturally integrate sequences of imperfect motion and exteroceptive sensor data. Recently, probabilistic localization systems utilizing appearance-invariant visual place recognition (VPR) methods as the primary exteroceptive sensor have demonstrated state-of-the-art performance in the presence of substantial appearance change. However, existing systems 1) do not fully utilize odometry data within the motion models, and 2) are unable to handle route deviations, due to the assumption that query traverses exactly repeat the mapping traverse. To address these shortcomings, we present a new probabilistic topometric localization system which incorporates full 3-dof odometry into the motion model and furthermore, adds an off-map state within the state-estimation framework, allowing query traverses which feature significant route detours from the reference map to be successfully localized. We perform extensive evaluation on multiple query traverses from the Oxford RobotCar dataset exhibiting both significant appearance change and deviations from routes previously traversed. In particular, we evaluate performance on two practically relevant localization tasks: loop closure detection and global localization. Our approach achieves major performance improvements over both existing and improved state-of-the-art systems.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据