Excavator 3D pose estimation using deep learning and hybrid datasets

Earthwork operations are crucial parts of most construction projects. Heavy construction equipment and workers are often required to work in limited workspaces simultaneously. Struck-by accidents resulting from poor worker and equipment interactions account for a large proportion of accidents and fatalities on construction sites. The emerging technologies based on computer vision and artificial intelligence offer an opportunity to enhance construction safety through advanced monitoring utilizing site cameras. A crucial pre-requisite to the development of safety monitoring applications is the ability to identify accurately and localize the position of the equipment and its critical components in 3D space. This study proposes a workflow for excavator 3D pose estimation based on deep learning using RGB images. In the proposed workflow, an articulated 3D digital twin of an excavator is used to generate the necessary data for training a 3D pose estimation model. In addition, a method for generating hybrid datasets (simulation and laboratory) for adapting the 3D pose estimation model for various scenarios with different camera parameters is proposed. Evaluations prove the capability of the workflow in estimating the 3D pose of excavators. The study concludes by discussing the limitations and future research opportunities.     

Adaptive prescribed time control for quadrotor formation with stochastic links failure

The formation control for multiple quadrotors subject to maintaining the formation configuration and collision avoidance in the situation of stochastic links failure is investigated in this paper. First, the distributed formation controller is designed, the position controller is developed to manage the desired formation of position, and the attitude controller is developed to control the translation and rotation movements of the quadrotor. Then, in order to avoid the collisions between multiple quadrotors and the obstacles, a potential energy function method is introduced into the quadrotor formation control combined with the nest adaptive control. Inspired by the design of event trigger controller, a communication compensation controller is designed to ensure the stability of quadrotor formation under the condition of random communication interruption and recovery. Moreover, a prescribed time function is designed, which means the convergence time of the formation system can be set in advance. The prescribed time stability of the formation control system is proved by Lyapunov theory. Finally, the simulation results verify the effectiveness and superiority of this method.     

Linking air quality and watershed models for environmental assessments: Analysis of the effects of model-specific precipitation estimates on calculated water flux

Directly linking air quality and watershed models could provide an effective method for estimating spatially-explicit inputs of atmospheric contaminants to watershed biogeochemical models. However, to adequately link air and watershed models for wet deposition estimates, each model’s temporal and spatial representation of precipitation needs to be consistent. We explore how precipitation implemented within the Community Multi-Scale Air Quality Model (CMAQ) model algorithms, and multiple spatially-explicit precipitation datasets that could be used to improve the CMAQ model deposition estimates, links with the standard precipitation sources used to calibrate watershed models (i.e., rain gage data) via modeled water fluxes. Simulations are run using a grid-based watershed mercury model (GBMM) in two watersheds. Modeled monthly runoff suggests that multiple resolution Parameter-elevations Regressions on Independent Slopes Model (PRISM) and National Multi-sensor Precipitation Analysis Stage IV (NPA) data generate similar monthly runoff estimates, with comparable or greater accuracy when evaluated against stream gage data than that produced by the base rain gage data. However, across longer time periods, simulated water balances using 36 km Pennsylvania State University/National Center for Atmospheric Research mesoscale model (MM5) data are similar to that of base data. The investigation also examines the implications our results, providing suggestions for linking air quality and watershed fate and transport models.     

Reaching a consensus in networks of high-order integral agents under switching directed topologies

Consensus problem of high-order integral multi-agent systems under switching directed topology is considered in this study. Depending on whether the agent’s full state is available or not, two distributed protocols are proposed to ensure that states of all agents can be convergent to a same stationary value. In the proposed protocols, the gain vector associated with the agent’s (estimated) state and the gain vector associated with the relative (estimated) states between agents are designed in a sophisticated way. By this particular design, the high-order integral multi-agent system can be transformed into a first-order integral multi-agent system. Also, the convergence of the transformed first-order integral agent’s state indicates the convergence of the original high-order integral agent’s state, if and only if all roots of the polynomial, whose coefficients are the entries of the gain vector associated with the relative (estimated) states between agents, are in the open left-half complex plane. Therefore, many analysis techniques in the first-order integral multi-agent system can be directly borrowed to solve the problems in the high-order integral multi-agent system. Due to this property, it is proved that to reach a consensus, the switching directed topology of multi-agent system is only required to be ‘uniformly jointly quasi-strongly connected’, which seems the mildest connectivity condition in the literature. In addition, the consensus problem of discrete-time high-order integral multi-agent systems is studied. The corresponding consensus protocol and performance analysis are presented. Finally, three simulation examples are provided to show the effectiveness of the proposed approach.     

Methods for evaluating volunteers’ contributions in a deforestation detection citizen science project

Today, due to the availability of free remote sensing data, efficient algorithms for image classification and increased connectivity and computing power, together with international policy initiatives, such as the United Nations Programme on Reducing Emissions from Deforestation and Forest Degradation (UN-REDD), more and more countries are investing in their own national forest monitoring schemes. However, tropical forests remain under threat worldwide. Recently, a citizen science project that enables citizens around the globe to be involved in forest monitoring tasks has been proposed, called “ForestWatchers” (www.forestwatchers.net). Its main goal is to allow volunteers (many of them with no scientific training) around the globe, with their own smartphones, tablets and notebooks, review satellite images of forested regions and confirm whether automatic assignments of forested and deforested regions are correct. Inspected images are then sent to a central database where the results are integrated to generate up-to-date deforestation maps. This approach offers a low-cost way to both strengthen the scientific infrastructure and engage members of the public in science. Here, we describe the methods developed within the scope of the ForestWatchers project to assess the volunteers’ performance. These tools have been evaluated with data of two of the project’s preliminary tasks. The first, called “BestTile”, asks volunteers to select which of several images of the same area has the least cloud cover, while in the second, called “Deforestation”, volunteers draw polygons on satellite images delimiting areas they believe have been deforested. The results from more than 500 volunteers show that using simple statistical tests, it is possible to achieve a triple goal: to increase the overall efficiency of the data collecting tasks by reducing the required number of volunteers per task, to identify malicious behavior and outliers, and to motivate volunteers to continue their contributions.     

基于模型的方法在软件测试领域的应用与发展

伴随着软件在当今社会中扮演着日益重要的角色,在各类软件或系统的开发过程中,测试变得越来越重要.随着面向对象技术的广泛应用和软件测试自动化的要求,基于模型的测试(MBT)技术逐渐得到了软件开发和测试人员的认可和接受.尽管有许多国内出版物讨论了基于模型的测试技术,但还没有相关技术文章对MBT技术及工具的当前发展进行回顾与总结.文章对当前MBT技术的通用模型、测试用例生成方法、测试目标选择等MBT方法进行回顾,并对基于模型的自动化测试工具、应用实践进行了概述.最后,探讨了MBT技术的未来发展与研究方向.     

Radiometric Calibration and Validationof TG-1 Hyper-spectral Imager

TG-1,the first Chinese space laboratory module launched on 29 September 2011,has accumulated large numbers of high-resolution image data by the hyper-spectral imager.However,these images still can’t be applied to quantitative analysis because of the huge spectral and radiance difference between ground and onboard conditions.So a radiometric calibration is very necessary to correct these laboratory and on-board radiance calibration parameters for better quantitative application.This paper aims to calibrate TG-1 hyper-spectral imager using reflectance-based calibration method through performing ground calibration experiments on 3 February and 6 March 2011.Firstly,this study used the ground experiment data on 6 March to obtain each channel’s calibration correction coefficients,which were different a lot from laboratory and on-board ones,relative error in all channels are bigger than 10 percent.Then,the calibration experiment data on 3 February 2011 were used to validate the result.Results show that calibration correction coefficients improved the image accuracy,the calibration and validation experiments’ results are in good agreement.In most channels,the relative errors are less than 10 percent,except that bigger error appears in absorption channels.Therefore,this calibration experiment renewed the calibration coefficients,and improved the quantitative level of the TG radiance products.     

基于PLUTO的载荷遥操作地面控制平台设计

针对现有的载荷遥控操作模式不能适应空间科学实验需求的实际,提出使用标准控制测试语言(PLUTO语言)实现载荷控制的新模式。PLUTO是一种过程化脚本语言,能够应用于航天飞行器和有效载荷的地面测试、在轨测试与在轨运控操作,该语言能满足载荷操作的各种需求,为载荷控制人员提供有力的工具。文中以我国有效载荷在轨操控需求为出发点,同时根据PLUTO语言的特点,结合面向对象方法学、编译技术、设计模式等理念,提出一种快速实现其编译程序的技术途径,并通过原型系统验证设计的可行性。     

Design optimization of stiffened storage tank for spacecraft

Stiffened storage tank is an important structural component in spacecraft. Its structural weight is one of the key criterions in the design phase. This paper focuses on the design optimization of the structure by using finite element method, structural sensitivity analysis techniques, and sequential linear/quadratic programming aimed to reduce the structural weight. Design variables include the numbers of stiffeners, stiffeners’ section dimensions, and shell thickness distribution. Detailed finite element modeling processes are presented, which are the ways to construct the stiffener (beam orientation and offset) and shell elements and the ways to determine the analysis model and structural boundary conditions. A brief introduction to sensitivity analysis and optimization solution algorithm is also given. Main attention is paid to the studies of design optimization of the tank structure, including the selection of design cases, evaluation, and comparison of the optimal results. There are six design cases considered in the design procedures. Numerical results show that by using the above computational techniques, the structural weight is effectively reduced. In this work, MSC.Patran/Nastran is employed to construct the Finite Element Model (FEM), and JIFEX, which is developed in our group, is used to conduct the structural design optimization. JIFEX is a structural analysis and optimization software package developed by Gu and colleagues in the Dalian University of Technology Department of Engineering Mechanics. Among its many functions is the ability to analyze and optimize piezoelectric smart structures.     

Formation and characterization of silicon films on flexible polymer substrates

Polysilicon thin film transistors on flexible substrates are of considerable interest for applications in flexible displays. This paper investigates the formation of nanocrystalline silicon on flexible, transparent polymer substrates. An 800-nm layer of amorphous silicon was deposited on a polyimide substrate followed by a 20-nm layer of aluminum. Samples were rapid thermal annealed at 900 °C for 20 s, forming silicon nanocrystallites in a porous amorphous silicon film. The films were analyzed using Rutherford backscattering spectrometry, Raman Spectroscopy and cross-section transmission electron microscopy. A mechanism is proposed for the formation of silicon nanocrystallites and pores in the a-Si layer.