A branch-and-bound procedure for robot assembly planning

The objective of this study was to develop a branch-and-bound procedure for the global optimization of problems in Robot selection (R), Layout of cell accessories (L) and Sequence of assembly tasks (S) for single-arm assembly cells. The three planning decisions are interdependent because the local optimization of one decision variable may no longer be optimal when either one or both of the other two variable changes. To evaluate the performance of the proposed procedure, a computer software RAPS (Robot Assembly Planning System) was developed to run the procedure as well as the complete enumeration method. Results from the experiments reveal that the proposed branch-and-bound procedure yields significant savings on execution time, run-time memory required and a weighted sum of the number of mathematical operations required with respect to complete enumeration approach.     

A peg-in-hole robot assembly system based on Gauss mixture model

Using robots to assemble parts has always been a research hotspot, but the traditional analysis model of assembly mainly focuses on establishing the linear equation between the feedback force and the relative position of the peg and hole, which leads to high requirements for the material properties and geometric parameters of the assembly parts. In this paper, a new assembly strategy is proposed that learns skills from manual teaching to carry out the assembly process. A Gauss mixture model and regression is used to fit the teaching data, and then, the compliance control method is applied to conduct assembly when the geometric profile parameters and material elastic parameters of the assembly are inaccurate. Finally, the experiment was implemented under the tolerance is 0.18 mm, and the success rate reaches 100%. These findings verified the effectiveness of the compliance control method.     

Minimizing neighborhood evidential decision error for feature evaluation and selection based on evidence theory

Feature selection is an important preprocessing step in pattern recognition and machine learning, and feature evaluation arises as key issues in the construction of feature selection algorithms. In this study, we introduce a new concept of neighborhood evidential decision error to evaluate the quality of candidate features and construct a greedy forward algorithm for feature selection. This technique considers both the Bayes error rate of classification and spatial information of samples in the decision boundary regions.Within the decision boundary regions, each sample x_i in the neighborhood of x provides a piece of evidence reflecting the decision of x so as to separate the decision boundary regions into two subsets: recognizable and misclassified regions. The percentage of misclassified samples is viewed as the Bayes error rate of classification in the corresponding feature subspaces. By minimizing the neighborhood evidential decision error (i.e., Bayes error rate), the optimal feature subsets of raw data set can be selected. Some numerical experiments were conducted to validate the proposed technique by using nine UCI classification datasets. The experimental results showed that this technique is effective in most of the cases, and is insensitive to the size of neighborhood comparing with other feature evaluation functions such as the neighborhood dependency.     

Deep learning based robot cognitive architecture for collaborative assembly tasks

As the manufacturing industry becomes more agile, the use of collaborative robots capable of safely working with humans is becoming more prevalent, while adaptable and natural interaction is a goal yet to be achieved. This work presents a cognitive architecture composed of perception and reasoning modules that allows a robot to adapt its actions while collaborating with humans in an assembly task. Human action recognition perception is performed using convolutional neural network models with inertial measurement unit and skeleton tracking data. The action predictions are used for task status reasoning which predicts the time left for each action in a task allowing a robot to plan future actions. The task status reasoning uses a recurrent neural network method which is developed for transferability to new actions and tasks. Updateable input parameters allowing the system to optimise for each user and task with each trial performed are also investigated. Finally, the complete system is demonstrated with the collaborative assembly of a small chair and wooden box, along with a solo robot task of stacking objects performed when it would otherwise be idle. The human actions recognised are using a screw driver, Allen key, hammer and hand screwing, with online accuracies between 83–92%. User trials demonstrate the robot deciding when to start collaborative actions in order to synchronise with the user, as well as deciding when it has time to complete an action on its solo task before a collaborative action is required.     

Issues in using robots for electronics assembly

This paper addresses some of the many problems that exist in using robotics for inserting electronic components into printed circuit boards. A number of laboratory experiments were conducted, using an IBM 7535 robot, to evaluate the effect of several systems factors on successful component insertion rates. The results of these experiments are used to point to directions of further research in the evolution of systems that use robots and other automatic equipment in a flexible manufacturing environment.     

Limiting design criteria framework for manual electronics assembly

The electronics assembly industry is mainly characterized by high‐mix, low‐batch production of components that are becoming more miniaturized. The concomitant formidable physical and mental demands placed on operators goes well beyond the traditional scope of manual assembly. This research provides a framework for the design of manual electronics assembly by identifying the limiting design criteria from a human factors perspective that affect productivity. Collecting and analyzing in vivo biomechanical and throughput data, which provided the basis for quantifying ergonomic risks and productivity ratios, validated the design criteria. An increase of 53 PC boards per shift was obtained, thereby minimizing biomechanical risk factors associated with manual electronics assembly. © 2003 Wiley Periodicals, Inc. Hum Factors Man 13: 165–179, 2003.     

Circuit diagnosis support system for electronics assembly operations

Diagnosis and repair operations are often major bottlenecks in electronics circuit assembly operations. Increasing board density and circuit complexity have made fault diagnosis difficult. But, with shrinking product life cycles and increasing competition, quick diagnosis and feedback is critical for cost control, process improvement, and timely product introduction. This paper describes a case-based diagnosis support system to improve the effectiveness and efficiency of circuit diagnosis in electronics assembly facilities. The system stores individual diagnostic instances rather than general rules and algorithmic procedures, and prioritizes the tests during the sequential testing process. Its knowledge base grows as new faults are detected and diagnosed by the analyzers. The system provides distributed access to multiple users, and incorporates on-line updating features that make it quick to adapt to changing circumstances. Because it is easy to install and update, this method is well-suited for real manufacturing applications. We have implemented a prototype version, and tested the approach in an actual electronics assembly environment. We describe the system's underlying principles, discuss methods to improve diagnostic effectiveness through principled test selection and sequencing, and discuss managerial implications for successful implementation.     

基于工控机的AGV装配机器人控制系统设计

设计了一套基于工控机的双举升AGV装配机器人的控制系统。采用磁带导航完成寻线功能,采用PSD完成AGV与生产线的同步检测。利用无线网卡WiFi接入网方式,通过TCP/IP协议完成AGV与监控中心的数据传输以及运行调度。     

Simulation‐based actuator selection for redundantly actuated robot mechanisms

This article presents a simulation‐based strategy for sizing the actuators of a redundantly actuated robotic mechanism. The class of robotic mechanisms we consider may contain one or more closed loops and possess an arbitrary number of active and passive joints, and the number of actuators may exceed the mechanism's kinematic degrees of freedom. Our approach relies on a series of dynamic simulations of the mechanism, by applying Taguchi's method to systematically perform the simulations. To efficiently perform each of the dynamic simulations, we develop, using tools from modern screw theory, new recursive algorithms for the forward and inverse dynamics of the class of redundantly actuated mechanisms described. © 2002 Wiley Periodicals, Inc.     

一种基于元数据的众包图片效用最优选择算法

随着互联网的高速发展,移动终端设备产生的众包图片可以用在许多重要应用场景当中以获得有效的信息。例如地震后现场区域的修复、重大事故的处理。但是,这些应用场景往往都会有资源限制的问题,如带宽、终端的存储与处理能力等等,这就限制了形成众包图片的数量。因此,如何在资源有限的情况下,从众包图片中实现目标的最佳还原是一个巨大挑战。通过采集与处理图片的地理和几何数据,形成图片的元数组,在限制计算资源的条件下,提出了一种以元数据为输入的众包图片效用最优选择算法,以实现目标的最佳还原。算法的输入是元数据而非像素,所以在资源有限的应用场景中能够高效地分析众包。采用图片的效用来衡量目标区域被覆盖的程度,并提出了图片效用计算方法。最后设计了仿真实验,实验结果验证了算法的有效性与优越性。     

Feature evaluation and selection with cooperative game theory

Recent years, various information theoretic based measurements have been proposed to remove redundant features from high-dimensional data set as many as possible. However, most traditional Information-theoretic based selectors will ignore some features which have strong discriminatory power as a group but are weak as individuals. To cope with this problem, this paper introduces a cooperative game theory based framework to evaluate the power of each feature. The power can be served as a metric of the importance of each feature according to the intricate and intrinsic interrelation among features. Then a general filter feature selection scheme is presented based on the introduced framework to handle the feature selection problem. To verify the effectiveness of our method, experimental comparisons with several other existing feature selection methods on fifteen UCI data sets are carried out using four typical classifiers. The results show that the proposed algorithm achieves better results than other methods in most cases.     

基于证据理论的虚拟力机器人网络控制*

将网络与机器人相连,延伸网络的应用领域,可以实现价格低廉的远程监视与操作,而远程控制成功实现的关键在于信息的正确获得。利用Dempster-Shafer对六个超声波传感器所获取的距离信息进行融合,而后连同速度信息提供给弹簧-阻尼器系统以构建虚拟力;力的信息通过编程映射到游戏杆上,变成操纵方向的约束力。通过采用微软公司的带有力反馈的操纵杆作为力觉提示装置控制移动机器人在结构化环境下顺利运行,验证了虚拟力信息获取方法的有效性。     

A heuristic for software evaluation and selection

The proliferation of software packages has created a difficult, complex problem of evaluation and selection for many users. Traditional approaches to the quantification of package performance have relied on compensatory models, such as the linear weighted attribute model, which sums the weighted ratings of software attributes. These approaches define the dimensions of quality too narrowly and, therefore, omit substantial amounts of information from consideration. This paper presents an alternative methodology, previously used in capital rationing and tournament ranking, that expands the opportunity for objective insight into software quality. In particular, it considers three measures of quality, the frequency with which the attribute ratings of one package exceed those of another, the presence of outliers, where very poor performance may exist on a single attribute and be glossed over by compensatory methods, and the cumulative magnitude of attribute ratings on one package that exceed those on others. The proposed methodology is applied to the evaluation of the following software types: word processing, database management systems, spreadsheet/financial planning, integrated software, graphics, data communications and project management.     

A case-based approach for coordinated action selection in robot soccer

Designing coordinated robot behaviors in uncertain, dynamic, real-time, adversarial environments, such as in robot soccer, is very challenging. In this work we present a case-based reasoning approach for cooperative action selection, which relies on the storage, retrieval, and adaptation of example cases. We focus on cases of coordinated attacking passes between robots in the presence of the defending opponent robots. We present the case representation explicitly distinguishing between controllable and uncontrollable indexing features, corresponding to the positions of the team members and opponent robots, respectively. We use the symmetric properties of the domain to automatically augment the case library. We introduce a retrieval technique that weights the similarity of a situation in terms of the continuous ball positional features, the uncontrollable features, and the cost of moving the robots from the current situation to match the case controllable features. The case adaptation includes a best match between the positions of the robots in the past case and in the new situation. The robots are assigned an adapted position to which they move to maximize the match to the retrieved case. Case retrieval and reuse are achieved within the distributed team of robots through communication and sharing of own internal states and actions. We evaluate our approach, both in simulation and with real robots, in laboratory scenarios with two attacking robots versus two defending robots as well as versus a defender and a goalie. We show that we achieve the desired coordinated passing behavior, and also outperform a reactive action selection approach.     

An integrated fuzzy MCDM based approach for robot selection considering objective and subjective criteria

Robots with vastly different capabilities and specifications are available for a wide range of applications. Selection of a robot for a specific application has become more complicated due to increase in the complexity, advanced features and facilities that are continuously being incorporated into the robots by different manufacturers. The aim of this paper is to present an integrated approach for the optimal selection of robots by considering both objective and subjective criteria. The approach utilizes Fuzzy Delphi Method (FDM), Fuzzy Analytical Hierarchical Process (FAHP), Fuzzy modified TOPSIS or Fuzzy VIKOR and Brown–Gibson model for robot selection. FDM is used to select the list of important objective and subjective criteria based on the decision makers’ opinion. Fuzzy AHP method is then used to find out the weight of each criterion (both objective and subjective). Fuzzy modified TOPSIS or Fuzzy VIKOR method is then used to rank the alternatives based on objective and subjective factors. The rankings obtained are used to calculate the robot selection index based on Brown–Gibson model. The proposed methodology is illustrated with a case study related to selection of robot for teaching purpose. It is found that the highest ranked alternative based on Fuzzy VIKOR is closest to the ideal solution.     

Multicriteria decision model for outsourcing contracts selection based on utility function and ELECTRE method

An outsourcing contract problem has been analyzed. This is a typical problem when dealing with outsourcing vendor selection. For each alternative of an outsourcing contract there is an evaluation of both cost and quality of service. The latter may include probabilistic delivery time and confidence in quality commitment. The decision-maker takes into account multicriteria evaluation through ELECTRE method. Besides, each criterion is evaluated through a utility function. The model integrates both approaches to indicate a contract proposal. This paper presents the formulation for the decision model and a numerical application to illustrate the use of the model.     

A robot calligraphy writing method based on style transferring algorithm and similarity evaluation

Intelligent Service Robotics - This paper proposes a robot calligraphy writing method based on style transfer algorithm, which can transfer the art style of Chinese font and maintain the imitation...     

An ERP model for supplier selection in electronics industry

Asus Tech. is the largest motherboard manufacturer in Taiwan. Hundreds of suppliers cooperate with the company in business. So that supplier selection is the most important function of a purchasing department in the enterprise. An enterprise resource planning (ERP) system in the process of supplier selection may result in the great savings in both costs and man hours. In the concept of push and pull, an ERP system acts as an efficient tool in the resource integration and profit creation for a company. Through ERP, a decision manager can clearly realize the strength and weakness of the purchasing operation. To establish a real-time purchasing environment, a methodology of analytic network process (ANP), technique for order preference by similarity to ideal solution (TOPSIS) and linear programming (LP) are effectively applied in the supplier selection process. ANP and TOPSIS are used to calculate the weight and give suppliers a ranking; LP effectively allocates order quantity to each vendor. As to the result, four PC board suppliers are given orders for 1200, 727, 1000 and 73 pieces.