Institutional Repository of Institute of Automation, CAS
Not a member yet
23433 research outputs found
Sort by
Cascaded effect in a high-peak-power terahertz-wave parametric generator
No full textWe demonstrate megawatt-level terahertz (THz)-wave generation via a Stokes-seed-injected THz-wave parametric generator and study the cascaded effect. The optical-toTHz conversion efficiency was 1.72x10(-3), and the peak power was conservatively estimated to be 1.09 MW using the pulse width of the pump. More than 80% of the THz-wave energy came from primary parametric generation, with the rest coming from high-order parametric amplification. Clear cascaded Stokes spots of second to fourth order were observed, and the factors affecting the high-order parametric process are discussed. The cascaded parametric effect is beneficial for achieving a higher optical-to-THz conversion efficiency, thereby improving the performance of high-peak-power THz-wave parametric sources. (C) 2021 Optical Society of Americ
Monocular 3D Object Detection Based on Uncertainty Prediction of Keypoints
No full textThree-dimensional (3D) object detection is an important task in the field of machine vision, in which the detection of 3D objects using monocular vision is even more challenging. We observe that most of the existing monocular methods focus on the design of the feature extraction framework or embedded geometric constraints, but ignore the possible errors in the intermediate process of the detection pipeline. These errors may be further amplified in the subsequent processes. After exploring the existing detection framework of keypoints, we find that the accuracy of keypoints prediction will seriously affect the solution of 3D object position. Therefore, we propose a novel keypoints uncertainty prediction network (KUP-Net) for monocular 3D object detection. In this work, we design an uncertainty prediction module to characterize the uncertainty that exists in keypoint prediction. Then, the uncertainty is used for joint optimization with object position. In addition, we adopt position-encoding to assist the uncertainty prediction, and use a timing coefficient to optimize the learning process. The experiments on our detector are conducted on the KITTI benchmark. For the two levels of easy and moderate, we achieve accuracy of 17.26 and 11.78 in AP(3D), and achieve accuracy of 23.59 and 16.63 in AP(BEV), which are higher than the latest method KM3D
Quantitative analysis of iron slurry based on laser induced breakdown spectroscopy combined with mutual information feature selection partial least squares method
No full text目前检测矿浆品位相对准确的方法是传统化学分析,但周期长、有滞后性,无法实现在线检测。实验利用激光诱导击穿光谱（Laser induced breakdown spectroscopy, LIBS）在线、原位、快速等优点,分析了铁矿选矿过程尾矿浆中铁元素的品位值。由于LIBS采集到的光谱数据中存在大量对成分分析无用的冗余信息,进而增加了建模复杂程度,导致建立的模型精确度不够、泛化能力不强。因此,在偏最小二乘（PLS）模型基础上,提出了基于互信息特征筛选的偏最小二乘模型。实验结果表明,与传统的PLS模型相比,基于互信息特征筛选的偏最小二乘模型在分析精度上得到了明显改善,测试样品的决定系数R2从0.52提高到0.90,测试样本的平均绝对误差（MAEP）从2.87%下降到1.38%,总样本的平均绝对误差（MAE）从1.0%下降到0.60%。</p
An efficient approach of centroid alignment for spaceflight vehicles considering parameter uncertainties
No full textThis paper deals with centroid alignment for the spaceflight vehicles that work on orbit under microgravity environment, due to the unavailability of centroid measurement on ground, which is based on the principle of mass–radius products in different configurations of static equilibrium. A physical prototype of articulated mechanism for centroid alignment, consisting of three sets of linear modules with moving mass mounted, was developed and experimentally validated. The variational method was adopted to derive the error model for accuracy and sensitivity analysis of the developed articulated mechanism with the consideration of parameter uncertainties, from which it is found that the centroid position of the whole system is much more sensitive to the angular parameter variations than the linear ones. With the developed error model, an iterative approach of centroid alignment to ensure the centroid offset to meet the requirement is proposed, regardless of whether the parameter variations can be ignored, and numerous simulations verify the efficiency of the proposed approach.</p
Multi-agent deep reinforcement learning for end-edge orchestrated resource allocation in industrial wireless networks
No full textEdge artificial intelligence will empower the ever simple industrial wireless networks (IWNs) supporting complex and dynamic tasks by collaboratively exploiting the computation and communication resources of both machine-type devices (MTDs) and edge servers. In this paper, we propose a multi-agent deep reinforcement learning based resource allocation (MADRL-RA) algorithm for end-edge orchestrated IWNs to support computation-intensive and delay-sensitive applications. First, we present the system model of IWNs, wherein each MTD is regarded as a self-learning agent. Then, we apply the Markov decision process to formulate a minimum system overhead problem with joint optimization of delay and energy consumption. Next, we employ MADRL to defeat the explosive state space and learn an effective resource allocation policy with respect to computing decision, computation capacity, and transmission power. To break the time correlation of training data while accelerating the learning process of MADRL-RA, we design a weighted experience replay to store and sample experiences categorically. Furthermore, we propose a step-by-step epsilon-greedy method to balance exploitation and exploration. Finally, we verify the effectiveness of MADRL-RA by comparing it with some benchmark algorithms in many experiments, showing that MADRL-RA converges quickly and learns an effective resource allocation policy achieving the minimum system overhead
Industrial process control method based on local policy interaction exploration-based deep deterministic policy gradient
No full text为了实现对非线性、滞后性和强耦合的工业过程稳定精确控制，提出了一种基于局部策略交互探索的深度确定性策略梯度（LPIE-DDPG）的控制方法，用于深度强化学习的连续控制。首先，使用深度确定性策略梯度（DDPG）算法作为控制策略，极大减小控制过程中的超调和振荡现象；同时，使用原控制器的控制策略作为局部策略进行搜索，以交互探索规则进行学习，提高了学习效率和学习稳定性；最后，在Gym框架下搭建青霉素发酵过程仿真平台并进行实验。仿真结果表明，相较于比例-积分-微分（PID）和DQN,LPIE-DDPG在学习效率上提升了27.3%；在控制效果上有更小的超调和震荡；在产量上青霉素浓度提高了3.8%。所提方法能有效提升训练效率，同时提高工业过程控制的稳定性。</p
Numerical simulation of the stability of water fiber-optic in water jet-guided laser machining
No full textWater jet-guided laser machining is a new compound machining technology, which has been widely used in many fields due to its better processing effect. In this technology, the coupling of laser beam and micro-water jet directly determines the machining effect, and the prerequisite for successful coupling is the steady flow of the water jet, so ensuring the stability of the micro-water jet is the key to the stable machining of water jet-guided laser. Therefore, it is of great significance to studying the stability of the water fiber-optic in water jet-guided laser processing. In this paper, aiming at the problem that the stability of the water fiber-optic is difficult to control, a finite element model of the water fiber-optic is established. The convection model is vortex gas-phase flow “enveloped” water fiber-optic which is used to explain the interaction mechanism, and the flow field distribution of gas-phase flow and water fiber-optic convection was obtained. The results show that water fiber-optic is refined under the constraint of gas-phase flow, and the maximum processing distance can increase by three times. At the same time, the gas-phase flow can accelerate the removal of processing debris, and the processing accuracy and efficiency are improved.</p
Atomic Force Microscopy for Tumor Research at Cell and Molecule Levels
No full textTumors have posed a serious threat to human life and health. Researchers can determine whether or not cells are cancerous, whether the cancer cells are invasive or metastatic, and what the effects of drugs are on cancer cells by the physical properties such as hardness, adhesion, and Young's modulus. The atomic force microscope (AFM) has emerged as a key important tool for biomechanics research on tumor cells due to its ability to image and collect force spectroscopy information of biological samples with nano-level spatial resolution and under near-physiological conditions. This article reviews the existing results of the study of cancer cells with AFM. The main foci are the operating principle of AFM and research advances in mechanical property measurement, ultra-microtopography, and molecular recognition of tumor cells, which allows us to outline what we do know it in a systematic way and to summarize and to discuss future directions.</p
High-precision Calibration of Camera and IMU on Manipulator for Bio-inspired Robotic System
No full textInspired by box jellyfish that has distributed and complementary perceptive system, we seek to equip manipulator with a camera and an Inertial Measurement Unit (IMU) to perceive ego motion and surrounding unstructured environment. Before robot perception, a reliable and high-precision calibration between camera, IMU and manipulator is a critical prerequisite. This paper introduces a novel calibration system. First, we seek to correlate the spatial relationship between the sensing units and manipulator in a joint framework. Second, the manipulator moving trajectory is elaborately designed in a spiral pattern that enables full excitations on yaw-pitch-roll rotations and x-y-z translations in a repeatable and consistent manner. The calibration has been evaluated on our collected visual inertial-manipulator dataset. The systematic comparisons and analysis indicate the consistency, precision and effectiveness of our proposed calibration method