Vector fields are advantageous in handling non holonomic motion planning, as they provide the robot with reference orientation across the workspace. However, additionally incorporating curvature constraints presents challenges due to the interconnection between the design of the curvature-bounded vector field and the tracking controller under limited actuation. In this paper, we present a novel framework to co-develop the vector field and the control law, guiding the nonholonomic robot to the target configuration with curvature-bounded trajectory. First, we formulate the problem by introducing the target positive limit set, which allows the robot to either converge to or pass through the target configuration, depending on its dynamics and the specific tasks. Next, we construct a curvature-constrained vector field (CVF) via blending and embedding elementary flows in the workspace. To track such CVF, a saturated control law with dynamic gains is proposed, under which the tracking error's magnitude decreases even when saturation occurs. Under the control law, the kinematically constrained nonholonomic robot is guaranteed to track the reference CVF and converge to the target positive limit set with bounded trajectory curvature. Numerical simulations show that the proposed CVF method outperforms other vector-field-based algorithms. Experiments on Ackermann UGVs and semi-physical fixed-wing UAVs demonstrate that the method can be effectively implemented in real-world scenarios.

This paper proposes a joint class metric and sparse representation regularized deep belief network (J-DBN) method for intelligent fault diagnosis of the rotary equipment. In this novel method, the joint class metric and sparse representation regularized DBN is considered as a pretraining method to extract data features. It combines advantages of both class metric and sparse representation, which can optimize the distance of features in the same class and penalize the distance of features in different classes, and generate sparse features. Specifically, a new metric matrix is constructed to avoid using the same structural parameters for the local structure of each sample. The J-DBN-based fault diagnosis is implemented by the pretraining learning method, which contributes to better classification capabilities. Finally, gearbox and bearing fault diagnosis experiments are conducted to validate the effectiveness and the superiority of the proposed method. The results show that the ability of the J-DBN method to extract features is significantly enhanced, and the clustering of features of the same data is more obvious; furthermore, the proposed method has higher diagnostic accuracy than other fault diagnosis methods.

自1957年第一颗人造卫星发射以来, 日益增加的人类太空活动导致空间环境不断恶化。地球轨道上出现大量微小空间碎片(毫米到微米级), 其超高速撞击会对航天器的结构和功能单元, 如舱室外表面、热障材料、热控涂层、太阳能电池板、管道、电缆等, 造成严重破坏。因此, 对空间碎片造成的撞击损伤进行探测和评估, 提供风险预警和及时修复是保证航天器安全运行和空间任务顺利完成的重要环节。然而, 由于航天器外表面材料的复杂性以及撞击损伤事件的不可预测性, 采集的损伤检测数据呈现多样性特点。传统的基于人们经验的损伤特征提取与识别评估方法难以准确描述复杂损伤特征信息。近年来, 人工智能技术受到相关学者及工程技术人员广泛关注, 在解决诸如空间碎片撞击感知、损伤检测、风险评估等复杂技术问题上取得一系列突破。然而, 应用人工智能技术解决空间碎片问题仍有许多难题需要解决。在此背景下, 利用人工智能方法进行航天器损伤检测和评估显现出以下几个重要趋势:

The high fidelity and fraudulence of deceptive jamming can severely mislead synthetic aperture radar (SAR), which poses a big challenge in SAR imaging. In this letter, an imagery domain target reconstruction approach is proposed to suppress deceptive jamming for single-channel SAR. Specifically, the distinction between the echo signals of true targets and deceptive jamming in the azimuth phase is ascertained first. Then, the imaging process encountering deceptive jamming is formulated as a linear model, and the target reconstruction problem is converted to a linear inverse problem with the dictionary containing the explored phase characteristics. Finally, considering the sparsity of man-made targets, the imageries of the true and false targets can be reconstructed simultaneously through solving this sparse signal recovery problem. Theoretical analysis and experimental results showcase the superiority of the proposed method.

Convolutional Neural Networks (CNNs) are a class of deep neural networks. The image to column (im2col) procedure is an important step for CNN and consumes about 28.8% of the whole inference time. In this paper, we present an efficient im2col algorithm, name im2cole (word “e” means efficient). The condition with different stride and pad in im2cole is well handled and the judgements in the innermost loop are removed. The procedure with pad = 1 is split into three conditions. This will reduce the pause of CPU instruction pipeline. The performances of the presented im2cole algorithm are reported with different inputs. Some discussion and performance issues are also reported. The experimental results show that the overall performance speedup of im2cole ranges from 2.12 to 4.33 compared with the original algorithm. The real application with Darknet shows that im2cole can get 20.75% whole performance improvement.

This paper proposes a novel 1-bit SAR imaging scheme with the assistance of a single-frequency threshold. Such a threshold is able to maintain the amplitude information lost in the 1-bit quantization. Moreover, the influence of high order harmonics is also suppressed due to the spectrum shifting effect brought by the threshold and its high order harmonics. The 1-bit SAR imaging quality is thus improved while the system simplification brought by 1-bit sampling, which is gained by replacing a conventional multiplier with a logic gate, can still be retained. Strategy for SAR parameter selection is discussed to guarantee the performance. Experiment based on the RADARSAT-2 data verifies the validity of the proposed scheme.

This paper addresses a novel SAR imaging scheme based on 1-bit sampling assisted with a single-frequency threshold. The 1-bit sampling approach is able to considerably reduce the quantization cost. However, when the sampling technique simplifies the SAR system by reducing the word length of each sample to only 1 bit, amplitude information of the SAR echo is lost and high-order harmonics are introduced, degrading the SAR imaging quality. The strategy of single-frequency threshold is able to linearly maintain the amplitude information and shifts the spectra of the harmonics away from the imaging component caused by the intermodulation. Hence, the imaging quality using 1-bit sampled data can be guaranteed. By selecting different SAR parameter groups according to a comprehensive consideration on spectrum aliasing, filter mismatching, and radio frequency interfering, a good tradeoff can be achieved between imaging quality and system simplification. Examples of ideal scatterers and a real measured scene are provided for quantitative analysis. Real measured RADARSAT-1 data are also imaged using the proposed scheme to validate its effectiveness.