The current trend in automated optical inspection (AOI) systems employs deep learning models to detect defects on a metal surface. The setback of deep learning models is that they are time-consuming because the images obtained after every lighting adjustment must be used to train the deep learning models again and confirm whether the detection results have improved. To save the time spent using datasets to train deep networks, we proposed a comprehensive assessment score that combines defect visibility, visibility distribution, and overexposure based on the operation principles of convolution neural networks. It can be used to assess whether the training image dataset can improve the defect detection rate of the deep learning model such as You Only Look Once (YOLO), Single Shot MultiBox Detector (SSD), and Faster Region-based Convolutional Neural Network (Faster R-CNN) without training defect image datasets. We collected all of the weight combinations with the right prediction results and used linear regression to obtain the optimal weight coefficients. We found that visibility and overexposure had a greater impact on the comprehensive assessment score. We compared the proposed approach with existing image quality assessment methods, including mean absolute error (MAE), peak signal-to-noise ratio (PSNR), universal image quality index (UIQI), natural image quality evaluator (NIQE), perception-based quality evaluator (PIQE), and blind/referenceless image spatial quality evaluator (BRISQUE). The experiment results indicated that our proposed comprehensive assessment score is more correlated to the F2-score of the detection models than the IQA methods by the verification methods of Spearman Rank Correlation Coefficient (SRCC), Pearson Correlation, and Kendall Correlation. Thus, referring to this index during the collection of image data and choosing datasets with the highest score to train the model will produce better detection accuracy.

In this study, we proposed a behavior analysis for increasing the efficiency of human–robot collaboration in an assembly task. This study was inspired by previous research, in which a set of operator intentions in assembly was translated into an intention graph to formulate a probabilistic decision model for planning robot actions in the presence of operator intention ambiguity and perception uncertainty. Here, we achieved improvement by considering the analysis of human behavior in the form of fatigue and adaptation ability. We also switched the collaboration scheme from cooperative to collaborative, in which both the robot and operator work in parallel, not sequentially. We then tested the proposed method with chair assembly and the results indicated that shortening the assembly duration increased the effectiveness of the assembly process. The results also indicated that the proposed method for assembling 50 chairs was 4.68 s faster than the previous method.

This paper introduces a system which can monitor the environment of the garbage center in a city. Comparing with developed countries, they have technologies to process garbage, while those technologies are still difficult to be implemented in developing countries. In Indonesia, garbage are mostly placed in a wide-open area called landfill, where methane gas could be produced by a decomposition process. The gas has a characteristic that it can be burned easily. However, it is potentially to be used as an alternative energy for gas stoves. Considering this characteristic, the gas should be managed appropriately for both of distributing and monitoring gas leakage. Since the production of methane gas is plentiful enough, the gas can be distributed among the households surrounding the garbage center. Monitoring of methane gas has to be done continuously and real time during producing and distributing, without generating pollutions to the environment. Here, the monitoring system has been developed using a micro controller equipped with a methane gas sensor, i.e., TGS 2611. The data of monitoring will be distributed using an Internet-based system, where a Wi-Fi module is attached to the micro controller to send and communicate with the web-based server. Furthermore, information of monitoring the gas can be accessed by using android application. The advantage of the proposed system is that the user can monitor, record, and get the information of gas level. The system can also be used as an early-warning system when the gas exceeds the limit and when a danger situation occurs. The proposed system was tested using the black box method to evaluate the functionality. Finally, the system is used to optimize the Waste Management program through the utilization of methane gas. Hence, the utilization of methane gas monitoring system is tested to the user, whether they can use it easily.

This paper introduces a method to connect a camera, i.e., Pixy CMUcam5 as the vision detector of a robot soccer. The challenge point is to study how to connect this camera to CM-530 for Bioloid robot, since it is a low-prize compared with the embedded vision module of Havimo, which is a hardware platform of a Bioloid robot. In the genuine Bioloid robot, CM-530 works as the main processor. However, in this paper, CM-530 is used as the processor of actuators only, while the main processor is replaced by using Arduino micro controller. This method will be used for the learning material of robotics; thus, there are some topics should be observed, i.e., connection, data interpretation, and its implementation for robot soccer. In this paper, Pixy CMUcam 5 was confirmed that it can be used appropriately for robot soccer, especially for detecting ball, goalpost, opponent, and team mates based on color. Furthermore, this camera can also be used to interpret the distance of objects to determine the motion actions.

The mating of the board-to-board (BtB) connector is rugged because of its design complexity, small pitch (0.4 mm), and susceptibility to damage. Currently, the assembly task of BtB connectors is performed manually because of these factors. A high chance of damage to the connectors can also occur during the mating process. Thus, it is essential to automate the assembly process to ensure its safety and reliability during the mating process. Commonly, the mating procedure adopts a model-based approach, including error recovery methods, owing to less design complexity and fewer pins with a high pitch. However, we propose a data-driven approach prediction for the mating process of the fine pitch 0.4 mm board-to-board connector utilizing a manipulator arm and force sensor. The data-driven approach uses force data for time series encoding methods such as recurrence plot (RP), Gramian matrix, k-nearest neighbor dynamic time warping (kNN-DTW), Markov transition field (MTF), and long short-term memory (LSTM) to compare each of the model prediction performances. The proposed method combines the RP model with the convolutional neural network (RP-CNN) to predict the force data. In the experiment, the proposed RP-CNN model used two final layers, SoftMax and L2-SVM, to compare with the other prediction models mentioned above. The output of the data-driven prediction is the coordinate alignment of the female board-to-board connector with the male board-to-board connector based on the value of force. Based on the experiment, the encoding approach, especially RP-CNN (L2-SVM), outperformed all prediction models as mentioned above with an accuracy of 86%.

This paper describes the proposed system, which is able to monitor, record and give indicator about air quality information especially the CO values in the environment. The system is designed to work real time using web-based and android applications. A portable gas detector was developed using micro controller. In order to detect the CO value, TGS2600 is used; here an additional function is added by using a thermal sensor to detect the temperature in the environment. Furthermore, a WiFi module is attached to the micro controller to send the data and communicate with the web-based server. The advantage of the proposed system is that, the users can monitor, record and get a warning about the CO value portably. Moreover, the user can also setup the threshold level of each parameter. The proposed system was to be tested using by Black-box method to test the functionality. The results showed that the system runs well with 0% error and can show the CO and temperature values in real time.