Evaluation of hydraulic excavator Human–Machine Interface concepts using NASA TLX

This study evaluated newly proposed Human–Machine Interface (HMI) design concepts for improving the ergonomics of hydraulic excavators. The design concepts were based on an augmented interaction technique which involved the use of heads-up display (HUD) and coordinated control as HMI elements. Two alternative HMI designs were elaborated in order to separately evaluate the ergonomic impacts of the head-up display and the coordinated control by comparing them to the standard HMI design. The effectiveness of these three HMI designs in terms of the reduction of the operators' mental and physical workload were assessed by conducting experiments utilizing human subjects, ages 23–35 years. The National Aeronautics and Space Administration's Task Load Index (NASA TLX) method was used for collecting subjective workload scores based on a weighted average of ratings of six factors: Mental Demand, Physical Demand, Temporal Demand, Own Performance, Effort, and Frustration Level. The results showed that the type of HMI design affects different aspects of the operator's workload. Indeed, it showed how the proposed augmented interaction is an effective solution for reducing the ergonomic gaps in terms of mental workload, and to a lesser extent the physical workload, subjected by the standard HMI design.     

A multi-echelon production–inventory system with supply disruption

The article investigates an integrated multi-layer supply chain model consisting of supplier, manufacturer and retailer while supply disruption, machine breakdown, safety stock, maintenance breakdown occur simultaneously. At beginning of the production, manufacturer keeps some raw materials in stock received from second supplier at high price, as safety stock due to supply disruption of first supplier. Corrective maintenance is done immediately to restore its normal stage when machine breakdown occurs. Stock out situations at manufacturer and retailer are considered due to disruption of production for machine breakdown. The integrated expected costs of the chain in centralized (collaborating) and decentralized (Stakelberg approach) system are compared. A numerical example and its sensitivity analysis are provided to test feasibility of the model.     

Autonomous tactile perception: A combined improved sensing and Bayesian nonparametric approach

In recent years, autonomous robots have increasingly been deployed in unknown environments and required to manipulate or categorize unknown objects. In order to cope with these unfamiliar situations, improvements must be made both in sensing technologies and in the capability to autonomously train perception models. In this paper, we explore this problem in the context of tactile surface identification and categorization. Using a highly-discriminant tactile probe based upon large bandwidth, triple axis accelerometer that is sensitive to surface texture and material properties, we demonstrate that unsupervised learning for surface identification with this tactile probe is feasible. To this end, we derived a Bayesian nonparametric approach based on Pitman–Yor processes to model power-law distributions, an extension of our previous work using Dirichlet processes Dallaire et al. (2011). When tested against a large collection of surfaces and without providing the actual number of surfaces, the tactile probe combined with our proposed approach demonstrated near-perfect recognition in many cases and achieved perfect recognition given the right conditions. We consider that our combined improvements demonstrate the feasibility of effective autonomous tactile perception systems.     

基于Hough圆卷积变换的孔组检测

为降低孔组测量的成本,提高测量的精确度,提出一种基于Hough国卷积的孔组检测方法.对孔组图像进行中值滤波、拉普拉斯锐化增强和边缘检测;根据孔组半径大小的变化范围,对Hough圆锥进行改进;在此基础上,利用改进的Hough圆锥与边缘检测后的图像进行三维卷积,得到Hough参数空间,计算出孔组的坐标和半径值;采用快速傅立叶变换法代替三维卷积,减少算法的计算时间.实验结果表明,该方法的检测精度高、实时性强,可以用于孔组的自动化检测.     

结构光视觉引导的焊接机器人系统自标定技术

为实现结构光视觉引导的焊接机器人系统的标定,解决现有标定方法复杂,标定靶标制作要求高等缺点,提出一种基于主动视觉的自标定方法。该标定方法对场景中3个特征点取像,通过精确控制焊接机器人进行5次平移运动,标定摄像机内参数和手眼矩阵旋转部分;通过进行2次带旋转运动,结合激光条在特征点平面的参数方程,标定手眼矩阵平移部分和结构光平面在摄像机坐标系下的平面方程;并针对不同焊枪长度进行修正。在以Denso机器人为主体构建的结构光视觉引导的焊接机器人系统上的测试结果稳定,定位精度可达到±0.93 mm。该标定方法简单,特征选取容易,对焊接机器人系统在实际工业现场的使用有重要意义。     

基于线性判别边信息结合PHL的三维人脸识别

针对三维人脸识别中受光照、姿态、表情等变化而影响识别性能的问题,提出了一种原型超平面学习算法。利用SVM将弱标记数据集中的每个样本表示为一个原型超平面中层特征,使用学习组合系数从未标记的通用数据集中选择支持向量稀疏集;借助于Fisher准则最大化未标记数据集的判别能力,使用迭代优化算法求解目标函数;利用SILD进行特征提取,余弦相似性度量完成最终的人脸识别。在USCD/Honda、FRGC v2、LFW及自己搜集的人脸数据集上的实验结果表明,该算法优于其他几种三维人脸识别算法。     

基于IMAQ Vision和PLC的水果大小自动分级系统设计

水果大小是水果分级的一个重要依据,随着计算机技术和图像处理技术的飞速发展,计算机视觉技术被广泛用于水果品质的检测。所设计的水果大小自动分级系统由机器视觉检测系统和基于PLC的水果传送分拣机构组成。使用LabbVIEW软件编写水果大小自动分级系统的监控界面,并实现对CCD摄像机的控制及获取图片;使用IMAQ Vision工具包对所获取的水果图片进行处理,并进行大小分析,根据大小的等级由LabVIEW通过串口通信发送命令给PLC,由PLC控制水果的传送并进入对应的分级口,从而完成水果的自动分级。实际运行证明该系统能实时进行动态采集图片,有效地进行水果大小分析及自动分级。     

基于机器视觉的转辙机缺口检测方法研究

针对现有转辙机缺口检测方法所存在的问题,本文介绍了一种基于机器视觉技术的转辙机缺口检测基本方法及其原理和步骤。文章详细论述了LSD算法的工作原理,同时本文作者对该算法做出了改进。最后将改进的LSD算法应用在转辙机缺口检测当中,结果表明该检测算法具有良好的稳定性和快速性,并且能够很好的解决转辙机缺口检测的问题。     

Multimodal Pre-training Method for Vision-language Understanding and Generation

Most existing vision-language pre-training methods focus on understanding tasks and use BERT-like loss functions (masked language modeling and image-text matching) during pre-training. Despite their good performance in the understanding of downstream tasks, such as visual question answering, image-text retrieval, and visual entailment, these methods cannot generate information. To tackle this problem, this study proposes Unified multimodal pre-training for Vision-Language understanding and generation (UniVL). The proposed UniVL is capable of handling both understanding tasks and generation tasks. It expands existing pre-training paradigms and uses random masks and causal masks simultaneously, where causal masks are triangular masks that mask future tokens, and such pre-trained models can have autoregressive generation abilities. Moreover, several vision-language understanding tasks are turned into text generation tasks according to specifications, and the prompt-based method is employed for fine-tuning of different downstream tasks. The experiments show that there is a trade-off between understanding tasks and generation tasks when the same model is used, and a feasible way to improve both tasks is to use more data. The proposed UniVL framework attains comparable performance to recent vision-language pre-training methods in both understanding tasks and generation tasks. Moreover, the prompt-based generation method is more effective and even outperforms discriminative methods in few-shot scenarios.     

基于多尺度特征融合的皮肤烧伤创面分级算法

为实现遭受重大火灾等灾害后,对伤员皮肤烧伤自动化分级,加快诊断效率,提出提出一种用于皮肤烧伤分类的轻量化模型BI-YOLOv5算法。替换Swish激活函数,提高模型收敛能力及检测效率;使用K-means++算法对anchors聚类分析,增强对不同尺度目标的适应能力;修改特征提取网络,提取多个尺度的特征信息,建立多尺度特征融合网络,提高模型对深层特征信息的利用率,提高小面积烧伤的识别精度。实验结果表明,BI-YOLOv5算法在检测并区分不同烧伤类别及环境干扰下烧伤检测有较高的精度和效率,mAP达到97.6,对比YOLOv5提升8.4个百分点。