Hybrid Localization using Model- and Learning-Based Methods: Fusion of Monte Carlo and E2E Localizations via Importance Sampling
Hybrid Localization using Model- and Learning-Based Methods: Fusion of Monte Carlo and E2E Localizations via Importance Sampling
复制标题
DOI：
10.1109/icra40945.2020.9196568
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Naoki Akai;Takatsugu Hirayama;H. Murase
中科院分区：
文献类型：
--
作者：
Naoki Akai;Takatsugu Hirayama;H. Murase
本文提出了一种融合蒙特卡罗定位（MCL）和卷积神经网络（CNN）的端到端（E2E）定位的混合定位方法。MCL是基于粒子滤波器，并需要建议分布采样的粒子。通常使用运动模型来预测提议分布。然而，由于运动模型不能处理意外的误差，预测的分布有时是不准确的。使用其他理想的建议分布，如测量模型，可以提高对这种意外错误的鲁棒性。这种技术被称为重要性抽样（IS）。然而，很难从这样的理想分布中采样颗粒，因为它们没有以封闭形式表示。最近的工作已经证明，具有dropout层的CNN表示以输入为条件的输出上的后验分布，并且CNN预测等效于从后验中采样输出。因此，所提出的方法利用CNN对粒子进行采样，并通过IS将它们与MCL融合。因此，可以同时利用MCL和E2E本地化的优点，同时防止它们的缺点。实验结果表明，该方法能够像基于模型的方法那样平滑地估计出机器人位姿，像基于学习的方法那样能够快速地从故障中重新定位出机器人位姿。
This paper proposes a hybrid localization method that fuses Monte Carlo localization (MCL) and convolutional neural network (CNN)-based end-to-end (E2E) localization. MCL is based on particle filter and requires proposal distributions to sample the particles. The proposal distribution is generally predicted using a motion model. However, because the motion model cannot handle unanticipated errors, the predicted distribution is sometimes inaccurate. The use of other ideal proposal distributions, such as the measurement model, can improve robustness against such unanticipated errors. This technique is called importance sampling (IS). However, it is difficult to sample the particles from such ideal distributions because they are not represented in the closed form. Recent works have proved that CNNs with dropout layers represent the posterior distributions over their outputs conditioned on the inputs and the CNN predictions are equivalent to sampling the outputs from the posterior. Therefore, the proposed method utilizes a CNN to sample the particles and fuses them with MCL via IS. Consequently, the advantages of both MCL and E2E localization can be simultaneously leveraged while preventing their disadvantages. Experiments demonstrate that the proposed method can smoothly estimate the robot pose, similar to the model-based method, and quickly re-localize it from the failures, similar to the learning-based method.