arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2001.10789cs.CVcs.LGcs.RO
收藏

在雷达下:学习预测雷达中里程估计和度量定位的鲁棒关键点

Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar

University of Oxford(牛津大学);Applied AI Lab(应用人工智能实验室)

Dan Barnes, Ingmar Posner

摘要:

本文提出了一种自监督的框架,学习检测强大的里程估计和度量定位雷达的关键点。通过在我们的架构中嵌入可微的基于点的运动估计器,我们可以单独从定位误差中学习关键点位置,分数和描述符。这种方法避免了对什么是鲁棒的关键点施加任何假设,并且关键是允许它们针对我们的应用进行优化。此外,该架构是传感器不可知的,并且可以应用于大多数模态。我们在牛津雷达RobotCar数据集的280公里真实世界驾驶中进行了实验,并改进了基于点的雷达里程计的最新技术,将误差减少了45%,同时运行速度提高了一个数量级,同时解决了度量环路闭合问题。结合这些输出,我们提供了一个框架,能够在城市环境中使用雷达进行完整的映射和定位。

英文摘要:

This paper presents a self-supervised framework for learning to detect robust keypoints for odometry estimation and metric localisation in radar. By embedding a differentiable point-based motion estimator inside our architecture, we learn keypoint locations, scores and descriptors from localisation error alone. This approach avoids imposing any assumption on what makes a robust keypoint and crucially allows them to be optimised for our application. Furthermore the architecture is sensor agnostic and can be applied to most modalities. We run experiments on 280km of real world driving from the Oxford Radar RobotCar Dataset and improve on the state-of-the-art in point-based radar odometry, reducing errors by up to 45% whilst running an order of magnitude faster, simultaneously solving metric loop closures. Combining these outputs, we provide a framework capable of full mapping and localisation with radar in urban environments.

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。

↑