最近一年带来了电动汽车（EV）和相关基础设施/通信的大幅进步。入侵检测系统（ID）被广泛部署在此类关键基础架构中的异常检测。本文提出了一个可解释的异常检测系统（RX-ADS），用于在电动汽车中的CAN协议中进行入侵检测。贡献包括：1）基于窗口的特征提取方法； 2）基于深度自动编码器的异常检测方法； 3）基于对抗机器学习的解释生成方法。在两个基准CAN数据集上测试了提出的方法：OTID和汽车黑客。将RX-ADS的异常检测性能与这些数据集的最新方法进行了比较：HID和GID。 RX-ADS方法提出的性能与HIDS方法（OTIDS数据集）相当，并且具有超出HID和GID方法（CAR HACKING DATASET）的表现。此外，所提出的方法能够为因各种侵入而引起的异常行为产生解释。这些解释后来通过域专家使用的信息来检测异常来验证。 RX-ADS的其他优点包括：1）该方法可以在未标记的数据上进行培训； 2）解释有助于专家理解异常和根课程分析，并有助于AI模型调试和诊断，最终改善了对AI系统的用户信任。

We present NusaCrowd, a collaborative initiative to collect and unite existing resources for Indonesian languages, including opening access to previously non-public resources. Through this initiative, we have has brought together 137 datasets and 117 standardized data loaders. The quality of the datasets has been assessed manually and automatically, and their effectiveness has been demonstrated in multiple experiments. NusaCrowd's data collection enables the creation of the first zero-shot benchmarks for natural language understanding and generation in Indonesian and its local languages. Furthermore, NusaCrowd brings the creation of the first multilingual automatic speech recognition benchmark in Indonesian and its local languages. Our work is intended to help advance natural language processing research in under-represented languages.

Recent image degradation estimation methods have enabled single-image super-resolution (SR) approaches to better upsample real-world images. Among these methods, explicit kernel estimation approaches have demonstrated unprecedented performance at handling unknown degradations. Nonetheless, a number of limitations constrain their efficacy when used by downstream SR models. Specifically, this family of methods yields i) excessive inference time due to long per-image adaptation times and ii) inferior image fidelity due to kernel mismatch. In this work, we introduce a learning-to-learn approach that meta-learns from the information contained in a distribution of images, thereby enabling significantly faster adaptation to new images with substantially improved performance in both kernel estimation and image fidelity. Specifically, we meta-train a kernel-generating GAN, named MetaKernelGAN, on a range of tasks, such that when a new image is presented, the generator starts from an informed kernel estimate and the discriminator starts with a strong capability to distinguish between patch distributions. Compared with state-of-the-art methods, our experiments show that MetaKernelGAN better estimates the magnitude and covariance of the kernel, leading to state-of-the-art blind SR results within a similar computational regime when combined with a non-blind SR model. Through supervised learning of an unsupervised learner, our method maintains the generalizability of the unsupervised learner, improves the optimization stability of kernel estimation, and hence image adaptation, and leads to a faster inference with a speedup between 14.24 to 102.1x over existing methods.

Visual localization is the task of estimating camera pose in a known scene, which is an essential problem in robotics and computer vision. However, long-term visual localization is still a challenge due to the environmental appearance changes caused by lighting and seasons. While techniques exist to address appearance changes using neural networks, these methods typically require ground-truth pose information to generate accurate image correspondences or act as a supervisory signal during training. In this paper, we present a novel self-supervised feature learning framework for metric visual localization. We use a sequence-based image matching algorithm across different sequences of images (i.e., experiences) to generate image correspondences without ground-truth labels. We can then sample image pairs to train a deep neural network that learns sparse features with associated descriptors and scores without ground-truth pose supervision. The learned features can be used together with a classical pose estimator for visual stereo localization. We validate the learned features by integrating with an existing Visual Teach & Repeat pipeline to perform closed-loop localization experiments under different lighting conditions for a total of 22.4 km.

Visual Teach and Repeat 3 (VT&R3), a generalization of stereo VT&R, achieves long-term autonomous path-following using topometric mapping and localization from a single rich sensor stream. In this paper, we improve the capabilities of a LiDAR implementation of VT&R3 to reliably detect and avoid obstacles in changing environments. Our architecture simplifies the obstacle-perception problem to that of place-dependent change detection. We then extend the behaviour of generic sample-based motion planners to better suit the teach-and-repeat problem structure by introducing a new edge-cost metric paired with a curvilinear planning space. The resulting planner generates naturally smooth paths that avoid local obstacles while minimizing lateral path deviation to best exploit prior terrain knowledge. While we use the method with VT&R, it can be generalized to suit arbitrary path-following applications. Experimental results from online run-time analysis, unit testing, and qualitative experiments on a differential drive robot show the promise of the technique for reliable long-term autonomous operation in complex unstructured environments.

自主表面容器（ASV）代表了自动化湖泊水质监测的有前途的技术。在这项工作中，我们使用卫星图像作为粗图，并计划机器人的采样路线。但是，卫星图像与实际湖泊之间的不一致以及环境干扰（例如风，水生植被和不断变化的水位）可能使机器人难以参观先前地图建议的地方。本文提出了一种强大的路线规划算法，鉴于这些环境干扰，该算法可最大程度地减少预期的总行驶距离，从而引起地图中的不确定性。我们验证了算法在一千多个加拿大湖泊中的模拟中的功效，并在加拿大安大略省北部的一个湖泊中证明了我们在3.7 km长的现实世界机器人实验中应用算法的应用。

定位移动机器人的一种常见方法是测量已知位置点的距离，称为锚点。从距离测量值中定位设备通常是由于测量模型的非线性而作为非凸优化问题。当使用局部迭代求解器（如高斯 - 牛顿）时，非凸优化问题可能会产生次优的解决方案。在本文中，我们为连续范围的本地化设计了最佳证书。我们的公式可以整合运动，从而确保溶液的平滑度，并且对于仅从几个距离测量值进行定位至关重要。拟议的证书几乎没有额外的成本，因为它的复杂性与稀疏本地求解器本身的复杂性相同：位置数量的线性。我们在仿真和现实世界数据集中显示，有效的本地求解器通常会找到全球最佳解决方案（通过我们的证书确认），而当没有证书确认时，简单的随机重新初始化最终会导致可认证的最佳选择。

频率调制连续波（FMCW）LIDAR是一种最近新兴的技术，可通过多普勒效应效率进行每次返回的瞬时相对径向速度测量。在这封信中，我们使用这些多普勒速度测量值从FMCW激光雷达（FMCW Lidar）介绍了第一个连续的一次性绕线算法算法，以帮助几何变性环境中的探测率。我们应用现有的连续时间框架，该框架使用高斯工艺回归有效地估算车辆轨迹，以补偿由于任何机械驱动的激光雷达（FMCW和非FMCW）的扫描性质而引起的运动失真。我们在几个现实世界数据集上评估了我们提出的算法，包括我们收集的公开可用数据集和数据集。我们的算法优于也使用多普勒速度测量值的唯一现有方法，我们研究了包括此额外信息在内的困难条件，可大大提高性能。我们还证明了在标称条件下使用多普勒速度测量值的情况下，仅在有和不使用多普勒速度测量的情况下，仅激光射击的前进量的最新性能。该项目的代码可以在以下网址找到：https：//github.com/utiasasrl/steam_icp。

我们提出了一种生成，预测和使用时空占用网格图（SOGM）的方法，该方法嵌入了真实动态场景的未来语义信息。我们提出了一个自动标记的过程，该过程从嘈杂的真实导航数据中创建SOGM。我们使用3D-2D馈电体系结构，经过训练，可以预测SOGM的未来时间步骤，并给定3D激光镜框架作为输入。我们的管道完全是自我监督的，从而为真正的机器人提供了终身学习。该网络由一个3D后端组成，该后端提取丰富的特征并实现了激光镜框架的语义分割，以及一个2D前端，可预测SOGM表示中嵌入的未来信息，从而有可能捕获房地产的复杂性和不确定性世界多代理，多未来的互动。我们还设计了一个导航系统，该导航系统在计划中使用这些预测的SOGM在计划中，之后它们已转变为时空风险图（SRMS）。我们验证导航系统在模拟中的能力，在真实的机器人上对其进行验证，在各种情况下对真实数据进行研究SOGM预测，并提供一种新型的室内3D LIDAR数据集，该数据集在我们的实验中收集，其中包括我们的自动注释。

现代状态估计通常被表达为优化问题，并使用有效的本地搜索方法解决。这些方法最能保证与本地最小值的融合，但是在某些情况下，全球最优性也可以得到认证。尽管此类全球最佳证书已经为3D姿势格言优化确定了，但是对于基于3D地标的SLAM问题，尚未确定细节，其中估计的状态包括机器人姿势和地图地标。在本文中，我们通过使用图理论方法来解决这一差距，将基于里程碑的SLAM的子问题投入到一种形式，该形式产生了足够的全球最优状态。存在计算这些子问题的最佳证书的有效方法，但首先需要构建大型数据矩阵。我们表明，该矩阵可以以复杂性构建，该复杂性在地标数量中保持线性，并且不超过一个局部求解器的最新计算复杂性。最后，我们证明了证书对基于模拟和现实世界标记的大满贯问题的功效。