Node-centric Data Centers (NDCs) are highly flexible, cost-efficient, and failure-resilient, and have gained growing popularity in recent years. However, RDMA technology used in NDC still faces challenges, including high retransmission overhead, Head-of-Line Blocking (HoLB) and deadlock problems. Existing solutions for traditional data centers cannot simultaneously address these issues due to the unique topology and server transmission characteristics of NDC. In this paper, we propose a per-port flow control named PortFC for NDC. PortFC addresses the above problems through the designs of a Pause/Resume control signal, a per-port queue allocation method, an egress-detecting per-port flow control mechanism, and a server-aware queue scheduling method. Our evaluation shows that PortFC is free from retransmission, capable of eliminating HoLB and avoiding deadlocks. PortFC achieves 1.7-8.0 times higher throughput and reduces latency by 11.7%-87.7% compared to the state-of-the-art lossy RDMA based on IRN and the lossless RDMA method based on PFC. In particular, PortFC still demonstrates good performance in a Rail-only NDC with heterogeneous bandwidth domains.

Flying through body-size narrow gaps in the environment is one of the most challenging moments for an underactuated multirotor. We explore a purely data-driven method to master this flight skill in simulation, where a neural network directly maps pixels and proprioception to continuous low-level control commands. This learned policy enables wholebody control through gaps with different geometries demanding sharp attitude changes (e.g., near-vertical roll angle). The policy is achieved by successive model-free reinforcement learning (RL) and online observation space distillation. The RL policy receives (virtual) point clouds of the gaps' edges for scalable simulation and is then distilled into a high-dimensional pixel space. However, this flight skill is fundamentally expensive to learn by exploring in RL due to restricted feasible solution space. We propose to reset the agent as states on the trajectories generated by a model-based trajectory optimizer to alleviate this problem. The presented training pipeline is compared with baseline methods, and ablation studies are conducted to identify the key ingredients of the method. The immediate next step is to demonstrate the sim-to-real transformation, which can be challenging due to the high precision demands by this extreme flight skill.

Deep learning (DL) methods have shown great potential for remote sensing image change detection recently, but still suffer from several limitations. Within the identical semantic concept, significant but irrelevant changes in surface texture, color and spatial shifting of building objects resulted from variations in imaging physical factors, causes feature inconsistency of building objects in bitemporal sences. Conventional DL methods lack the capability to effectively distinguish real changes from irrelevant changes, leading to some false detections. This letter propose a novel framework, the multi-scale residual alignment transformer (AlignFormer), to mitigate the above issues. Specifically, inspired by deformable attention mechanism, we firstly design an adaptive feature alignment module (AFAM) to suppress the inconsistency of feature pairs, where the regions of building can be adaptively focused on and the spatial-temporal dependencies of relevant building objects in feature pairs effectively captured, via scheme of flexibly sampling Keys/Values for each given Query. Besides, we utilize an extremely tiny Swin Transformer as the backbone of differencing-based framework for obtaining hierarchical features. Moreover, inspired by residual learning strategy, three AFAMs are integrated into the framework to form the multi-scale residual architecture for the coarse-to-fine alignment of the paired features. Experimental results confirm the superiority of our proposed method over several state-of-the-art algorithms. Our code will be released at https://github.com/lilei-aircas/AlignFormer_CD.

Drone racing has become a popular international competition and has attained wide attention in recent years. However, the requirements of high-level operation keep the novice pilots away from participating in it. This paper presents a trajectory-based flight assistive system that enables various operators to fly the drone in a racing scene at a high speed. The whole system is structured hierarchically, consisting of both offline and online components. In the offline part, a global time-optimal trajectory is generated as the expert reference, and a dense flight corridor is constructed to provide sufficiently large safe region. In the online part, a remote control-mapped primitive is designed to fast encapsulate pilots’ inputs, and the time mapping based trajectory progress is customized to further capture intention. Then, a trajectory planner is proposed to generate intention-aligned, smooth, feasible, and safe trajectories periodically. Additionally, a yaw planning that provides the pilot with the best suitable view angle is employed to further alleviate the operation difficulty. Simulations and real world experiments are implemented to verify the performance of our system. The maximum flight speed can reach 6.0 m/s for a novice drone pilot in a real racing scene. Our code is released as an open-source package1.

Earth-observing satellites provide global observations of many geophysical variables. As these variables are derived from measured radiances, the underlying radiance data are the most reliable sources of information for change detection. Here, we identify statistically significant trends in the color and spatial texture of the Earth as viewed from multiple directions from the Multi-angle Imaging SpectroRadiometer (MISR), which has been sampling the angular distribution of scattered sunlight since 2000. Globally, our results show that the Earth has been appearing relatively bluer (up to 1.6% per decade from both nadir and oblique views) and smoother (up to 1.5% per decade only from oblique views) over the past 15 years. The magnitude of the global blueing trends is comparable to that of uncertainties in radiometric calibration stability. Regional shifts in color and texture, which are significantly larger than global means, are observed, particularly over polar regions, along the boundaries of the subtropical highs, the tropical western Pacific, Southwestern Asia, and Australia. We demonstrate that the large regional trends cannot be explained either by uncertainties in radiometric calibration or variability in total or spectral solar irradiance; hence, they reflect changes internal to the Earth's climate system. The 15-year-mean true color composites and texture images of the Earth at both nadir and oblique views are also presented for the first time.

Infrared channels on the Moderate Resolution Imaging Spectroradiometer (MODIS) are used to infer cloud-top pressure (CTP), temperature, and effective cloud amount or emissivity. For low clouds, those with tops at pressures greater than 700 hPa, the infrared window 11-$\mu\hbox{m}$channel brightness temperature is used to determine the CTP and the corresponding cloud-top temperature by comparison with the temperature profile obtained from the NCEP Global Data Assimilation System meteorological analysis. In the presence of strong inversions which are common for marine stratus and stratocumulus, this leads to the identification of an erroneously high cloud-top height (CTH). This discrepancy is illustrated by comparing MODIS CTHs with those inferred from the geometric method used by the Multiangle Imaging SpectroRadiometer on the same satellite platform, and field observations. The error in CTH is typically about 2 km and depends on the shape of the actual temperature profile. It is shown that column water vapor above cloud retrieved from the MODIS solar infrared channels in the vicinity of the 0.94-$\mu\hbox{m}$water vapor absorption band can be used to flag the error and that the location of the true CTH could possibly be obtained using lapse rate formulations for cloud-topped boundary layers.