Industrial domain knowledge modeling aims to integrate multi-source industrial information to build a knowledge model that facilitates industrial system construction. Some studies have sought solutions by fuzzy Petri nets (FPNs), which graphically represent domain knowledge to realize interpretable knowledge modeling. However, these methods cannot meet the intelligent development demands of current industrial systems due to laborious manual modeling, inflexible knowledge representation, and non-adaptive parameter determination. In this paper, we propose an interpretable data-driven FPN (IDFPN) method to realize industrial domain knowledge modeling. Unlike traditional FPN modeling paradigm, IDFPN develops a data mining-based explicit knowledge acquisition (DEKA) to automatically explore the FPN structure. Then, a novel q-rung orthopair fuzzy Petri net (q-ROFPN) model and an adaptive model learning algorithm are proposed to dynamically adjust the knowledge representation ranges and adaptively determine q-ROFPN parameters. We apply IDFPN to address a real-world knowledge modeling problem in energy efficiency management of the data center cooling system. Experimental results demonstrate that the proposed IDFPN can fulfill the industrial domain knowledge modeling task automatically and generate an interpretable q-ROFPN model with good parameter learning capabilities and reasonable inferences regarding system behavior statuses.

Person detection is a crucial task for mobile robots navigating in human-populated environments. LiDAR sensors are promising for this task, thanks to their accurate depth measurements and large field of view. Two types of LiDAR sensors exist: the 2D LiDAR sensors, which scan a single plane, and the 3D LiDAR sensors, which scan multiple planes, thus forming a volume. How do they compare for the task of person detection? To answer this, we conduct a series of exper-iments, using the public, large-scale JackRabbot dataset and the state-of-the-art 2D and 3D LiDAR-based person detectors (DR-SPAAM and CenterPoint respectively). Our experiments include multiple aspects, ranging from the basic performance and speed comparison, to more detailed analysis on localization accuracy and robustness against distance and scene clutter. The insights from these experiments highlight the strengths and weaknesses of 2D and 3D LiDAR sensors as sources for person detection, and are especially valuable for designing mobile robots that will operate in close proximity to surrounding humans (e.g. service or social robot).

Autonomous navigation in highly populated areas remains a challenging task for robots because of the difficulty in guaranteeing safe interactions with pedestrians in unstructured situations. In this work, we present a crowd navigation control framework that delivers continuous obstacle avoidance and post-contact control evaluated on an autonomous personal mobility vehicle. We propose evaluation metrics for accounting efficiency, controller response and crowd interactions in natural crowds. We report the results of over 110 trials in different crowd types: sparse, flows, and mixed traffic, with low- (< 0.15 ppsm), mid- (< 0.65 ppsm), and high- (< 1 ppsm) pedestrian densities. We present comparative results between two low-level obstacle avoidance methods and a baseline of shared control. Results show a 10% drop in relative time to goal on the highest density tests, and no other efficiency metric decrease. Moreover, autonomous navigation showed to be comparable to shared-control navigation with a lower relative jerk and significantly higher fluency in commands indicating high compatibility with the crowd. We conclude that the reactive controller fulfils a necessary task of fast and continuous adaptation to crowd navigation, and it should be coupled with high-level planners for environmental and situational awareness.

Deep learning is the essential building block of state-of-the-art person detectors in 2D range data. However, only a few annotated datasets are available for training and testing these deep networks, potentially limiting their performance when deployed in new environments or with different LiDAR models. We propose a method, which uses bounding boxes from an image-based detector (e.g. Faster R-CNN) on a calibrated camera to automatically generate training labels (called pseudo-labels) for 2D LiDAR-based person detectors. Through experiments on the JackRabbot dataset with two detector models, DROW3 and DR-SPAAM, we show that self-supervised detectors, trained or fine-tuned with pseudolabels, outperform detectors trained only on a different dataset. Combined with robust training techniques, the self-supervised detectors reach a performance close to the ones trained using manual annotations of the target dataset. Our method is an effective way to improve person detectors during deployment without any additional labeling effort, and we release our source code to support relevant robotic applications.

Detecting persons using a 2D LiDAR is a challenging task due to the low information content of 2D range data. To alleviate the problem caused by the sparsity of the LiDAR points, current state-of-the-art methods fuse multiple previous scans and perform detection using the combined scans. The downside of such a backward looking fusion is that all the scans need to be aligned explicitly, and the necessary alignment operation makes the whole pipeline more expensive - often too expensive for real-world applications. In this paper, we propose a person detection network which uses an alternative strategy to combine scans obtained at different times. Our method, Distance Robust SPatial Attention and Auto-regressive Model (DR-SPAAM), follows a forward looking paradigm. It keeps the intermediate features from the backbone network as a template and recurrently updates the template when a new scan becomes available. The updated feature template is in turn used for detecting persons currently in the scene. On the DROW dataset, our method outperforms the existing state-of-the-art, while being approximately four times faster, running at 87.2 FPS on a laptop with a dedicated GPU and at 22.6 FPS on an NVIDIA Jetson AGX embedded GPU. We release our code in PyTorch and a ROS node including pre-trained models.

Full-polarimetric SAR image is very useful for the landslide monitoring especially in the well vegetation-covered mountainous region. GaoFen-3 (GF-3) is the first civil C-band fully polarimetric SAR satellite in China. In order to test the ability of GF-3 full-polarimetric SAR data on landslide monitoring, 2 cases of mountainous landslide in southwestern part of China in 2017 and 4 polarimetric decomposition methods (Pauli, Krogager, Freeman, and H-α/A) were selected. It was found that GF-3 full-polarimetric SAR data had a good performance on that. The scattering mode had changed from volume to surface mode by the four methods which indicated the vegetation covered has been destroyed by landslide. In the incoherent decomposition methods, the scattering mode in the vegetation region around the landslides had a more consistent result than that in the incoherent decomposition methods. It can also be a good tool to do the autonomous landslide recognition in a larger region combined with some change detection methods.

The precisely and timely extraction of burned areas after forest fire plays an important role in reducing disaster losses, maintaining ecological balance and protecting forest resources. In this article, we propose a method of automatically extracting forest fire burned areas by using Gaofen-1 remote sensing images. Firstly, the geometric correction and atmospheric correction are carried out in Gaofen-1 WFV (Wide Field Viewer) images, and then the normalized vegetation index is calculated using the nearinfrared band and red band. In the vegetation index results, the Otsu's method is used to set the threshold value to automatically obtain the burned areas. Taking the forest fire that occurred in the Daxing'anling Khanma Nature Reserve on June 2, 2018 as an example, the method can extract the burned areas fully automatically and the precision is better than 94%.

The efficiency of caches plays a vital role in microprocessors. In this paper, we introduce a novel and flexible cache substrate, which integrates nonvolatile memory devices into the standard SRAM cells. By allowing this nonvolatile SRAM (NV-SRAM) cell to store inconsistent data between SRAM portion and NV portion, we show that the proposed NV2-SRAM cache not only provides enriched functionalities, but also allows simultaneous multiple optimizations. For example, the NV2-SRAM cache can reduce cache misses caused by context-switching and improve the performance by 15%. It can also save up to 67% energy over the SRAM-based cache, outperforming the drowsy cache in terms of both power efficiency and reliability. Moreover, the proposed cache architecture can be used to improve the performance of prefetching by 10%. Comparing with a conventional cache (equipped with a victim buffer) that occupies the same die area, the NV2-SRAM cache gains an 11% performance benefit. To achieve simultaneous optimizations, we propose architecture and OS support to optimize the cache power, performance and reliability concurrently on multicore-based systems.