arXiv 2407.081622024-11-19cs.CVcs.RO

通过验证定位估计改进基于视觉地点识别的机器人导航

Improving Visual Place Recognition Based Robot Navigation By Verifying Localization Estimates

Queensland University of Technology（昆士兰科技大学）；QUT Centre for Robotics（昆士兰科技大学机器人中心）；School of Electrical Engineering and Robotics（电气工程与机器人学院）；Australian National University（澳大利亚国立大学）；College of Engineering, Computing and Cybernetics（工程、计算与网络学院）

Owen Claxton, Connor Malone, Helen Carson, Jason Ford, Gabe Bolton, Iman Shames, Michael Milford

备注：: Author Accepted Preprint for Robotics and Automation Letters
发表信息：: IEEE Robotics and Automation Letters 2024
DOI：: 10.1109/LRA.2024.3483045

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种基于多层感知机的视觉地点识别完整性监控器，通过实时验证定位估计显著降低了机器人导航中的目标误差和定位误差，并提高了任务成功率与定位精度。

摘要：

视觉地点识别（VPR）系统通常性能并不完美，这会影响位置估计的“完整性”以及后续的机器人导航决策。此前，支持向量机（SVM）分类器已被用于监控VPR完整性。本研究引入了一种新颖的多层感知机（MLP）完整性监控器，其表现出更好的性能和泛化能力，消除了逐环境训练的需求，并减少了手动调参要求。我们在大量真实世界实验中测试了所提出的系统，提出了两种实时的基于完整性的VPR验证方法：一种用于机器人导航至目标区域的单次查询拒绝方法（实验1）；以及一种历史查询方法，该方法从其近期轨迹中选取一个最佳的、经过验证的匹配，并使用里程计外推当前的位置估计（实验2）。实验1的显著结果包括：总体平均沿航迹目标误差从约9.8米降低到约3.1米，总体任务成功完成率从约41%提高到约55%。实验2显示，总体平均沿航迹定位误差从约2.0米降低到约0.5米，总体定位精度从约97%提高到约99%。总体而言，我们的结果证明了VPR完整性监控器在真实世界机器人中的实用价值，能够改善VPR定位以及随后的导航性能。

英文摘要：

Visual Place Recognition (VPR) systems often have imperfect performance, affecting the `integrity' of position estimates and subsequent robot navigation decisions. Previously, SVM classifiers have been used to monitor VPR integrity. This research introduces a novel Multi-Layer Perceptron (MLP) integrity monitor which demonstrates improved performance and generalizability, removing per-environment training and reducing manual tuning requirements. We test our proposed system in extensive real-world experiments, presenting two real-time integrity-based VPR verification methods: a single-query rejection method for robot navigation to a goal zone (Experiment 1); and a history-of-queries method that takes a best, verified, match from its recent trajectory and uses an odometer to extrapolate a current position estimate (Experiment 2). Noteworthy results for Experiment 1 include a decrease in aggregate mean along-track goal error from ~9.8m to ~3.1m, and an increase in the aggregate rate of successful mission completion from ~41% to ~55%. Experiment 2 showed a decrease in aggregate mean along-track localization error from ~2.0m to ~0.5m, and an increase in the aggregate localization precision from ~97% to ~99%. Overall, our results demonstrate the practical usefulness of a VPR integrity monitor in real-world robotics to improve VPR localization and consequent navigation performance.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。