JAALR Volume2 Issue1


Journal of Advances in Artificial Life Robotics

Volume 2, Issue 1, June 2021

Research Article
1.Emotion recognition classification by EEG based on spectrum analysis
Tianyi Zhang1, Fengzhi Dai1,2, Di Yin1, Jichao Zhao1
1Tianjin University of Science and Technology, China
2Tianjin Tianke Intelligent and Manufacture Technology CO., LTD, China
pp. 1–5
ABSTRACT
Research shows that human emotion is closely related to the activity correlation of cerebral cortex, so the research of emotion classification by EEG (Electroencephalogram) provides a reliable basis. The feature extraction and classification application for EEG has been greatly improved in recent years, so we use EEG to study emotion classification. However, there are differences between EEG signals of different subjects, which have a certain impact on emotion classification. How to ensure the high accuracy and robustness of recognition is a problem. For this problem, when studying different subjects in different states, spectrum analysis can be used for their feature extraction. When the extracted features are classified, discriminant analysis algorithm is used and achieved better classification results. There are many methods involved in feature extraction, and different feature extraction methods will be compared later, so as to improve the robustness and efficiency of emotional classification by EEG signals.

ARTICLE INFO
Article History
Received 25 October 2019
Accepted 28 February 2021

Keywords
EEG
Feature extraction
Channel selection
Spectrum analysis
Sentiment classification

JAALR2101

Download article(PDF)

Research Article
2.Graph-Based Path Generation for Robot Navigation in a Forest Environment
Ayumu Tominaga1, Eiji Hayashi1, Ryusuke Fujisawa1, Abbe Mowshowitz2
1Graduate School of Computer Science and Systems Engineering, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka, Japan
2Department of Computer Science, The City College of New York, 160 Convent Avenue, New York, NY 10031, USA
pp. 6–11
ABSTRACT
This study evaluates a trajectory generation method for the efficient navigation of autonomous mobile robots in forests. We propose a graph-based cycle generation method. A graph was generated using environmental landmarks as nodes, and the graph was modified to be Eulerian. The Hamiltonian cycle contained nodes that could be regarded as the midpoint between a pair of landmarks; an efficient path could then be found. We applied this method to an artificial forest to verify the feasibility.

ARTICLE INFO
Article History
Received 25 November 2019
Accepted 02 March 2021

Keywords
Path generation
Area coverage
Field robot
Navigation
Graph
Forestry

JAALR2102

Download article(PDF)

Research Article
3.An Automatic Water Supply System Based on KingView and PLC
Peng Lu1, Fengzhi Dai1,2, Tianyi Zhang1
1Tianjin University of Science and Technology, China;
2Tianjin Tianke Intelligent and Manufacture Technology CO., LTD, China
pp. 12–16
ABSTRACT
The existing water supply system has poor water supply quality and low level of automatic control. Therefore, this paper designed an automatic water supply system based on Siemens PLC and the software of KingView . The pressure sensor in the water supply pipeline is used to detect the pressure of the pipeline, and the liquid level sensor monitors the liquid level in the tank. The sensor transmits the data to the PLC, and the PLC issues the control instruction after the computation processing. The KingView can realize real-time monitoring and fault alarm. The system can not only avoid the problem of large fluctuation of water pressure, reduce the failure rate of water supply equipment, but also realize the automatic control of water supply system.

ARTICLE INFO
Article History
Received 25 October 2020
Accepted 06 May 2021

Keywords
KingView
Constant pressure water supply
PLC
Upper computer system
Remote control

JAALR2103

Download article(PDF)

Research Article
4.Extension of Striped Image by Inverse Line Convergence Index Filter to Video
Toru Hiraoka1, Ryosuke Takaki2
1Department of Information Systems, University of Nagasaki, 1-1-1, Manabino Nagayo-chou, Nishisonogi-gun, Nagasaki-ken, 815—2195, Japan
2Division of Computer Science, Graduate School of Regional Design and Creation, University of Nagasaki, 1-1-1, Manabino, Nagayo-chou, Nishisonogi-gun, Nagasaki-ken, 815-2195, Japan
pp. 17–21
ABSTRACT
A non-photorealistic rendering method has been proposed for generating a striped image which is overlaid striped patterns in a photograph. The conventional method generates the striped image by an iterative process using an inverse line convergence index filter from the photograph. In this paper, we propose a method to extend the method of generating the striped image so that it can be applied to a video. In the proposed method, it is possible to suppress flicker due to the striped patterns. To verify the effectiveness of the proposed method, an experiment was conducted to visually and quantitatively evaluate the degree of flicker using Yuzenzome video. As a result of the experiment, it was found that the proposed method can suppress flicker.

ARTICLE INFO
Article History
Received 06 November 2020
Accepted 10 May 2021

Keywords
Non-photorealistic rendering
Video
Striped pattern
Inverse line convergence index filter

JAALR2104

Download article(PDF)

Research Article
5.Deep Learning Methods for Robotic Arm Workspace Scene Reconstruction
Pei Yingjian, Eiji Hayashi, Sakmongkon Chumkamon
MIST, Hayashi Lab, Kyushu Institute of Technology, 680-4 Kawazu. Iizuka-shi, Fukuoka 820-8502, Japan
pp. 22–26
ABSTRACT
This research is part of the Yaskawa Motoman Robot Autonomous Control Project, which aims to map the real workspace in a virtual environment using a depth camera mounted on the robot, and to plan the robot's autonomous obstacle avoidance path based on the 3D octomap. The main tool used in this study is RTAB-Map, which is based on the built-in handheld mapping scheme to improve it to meet our actual needs. After the actual test, our solution shows finer mapping accuracy, can update the map data in real time, and the perception of obstacles within the field of view is more comprehensive, but there is still a lot of room for optimizing the mapping speed.

ARTICLE INFO
Article History
Received 25 November 2020
Accepted 11 May 2021

Keywords
3D SLAM
Semantic segmentation
Point cloud
ROS

JAALR2105

Download article(PDF)

Research Article
6.Experimental Consideration on Requirements Specification of Haptic Device that Presents Sensation Corresponding to Palm on Back of Hand for Teleoperation of Robot Hand
Kyosuke Ushimaru, Noritaka Sato, Yoshifumi Morita
Department of Electrical and Mechanical Engineering, Graduate School of Engineering, Nagoya Institute of Technology, Gokiso-cho, Showa-ku, Nagoya, Aichi 466-8555, Japan
pp. 27–31
ABSTRACT
Teleoperated rescue robots have recently been on demand. However, it is known that the teleoperation of a robot hand mounted on a rescue robot is difficult. Therefore, we proposed a new haptic device that presents a haptic sensation for the teleoperation of a robot hand. The device stimulates the back of the hand instead of the palm of the operator. The determination of the required specifications by an experiment with subjects is presented in this paper. To design the device, the interval of the stimulation points (i), the diameter of the stimulation point (d), and the force of the stimulation (f) should be optimized. From the experimental results, we found that the accuracy rate was highest, when (i, d, f) = (30mm, 6mm, 0.9kgf). Moreover, we considered the decided specification in an additional experiment.

ARTICLE INFO
Article History
Received 25 November 2020
Accepted 11 May 2021

Keywords
Rescue robot
Haptic device
Teleoperation
Robot hand
Palm

JAALR2106

Download article(PDF)

Research Article
7.Real-Time AGVs moving control of Autonomous decentralized FMS by mind change with deep learning
Hidehiko Yamamoto1, Ryunosuke Yamane2
1Department of Mechanical Engineering, Gifu University, Yanagido 1-1, Gifu, Gifu 501-1194, Japan
2JR Tokai Information Systems Company, Ohzone, Higashi-ku, Nagoya, Japan
pp. 32–36
ABSTRACT
This study describes the control method of Automated Guided Vehicles (AGV) movements by using a mind model in order to avoid AGVs interferences. The mind uses the two types of mind, the arrogant mind and the modest mind model. The interferences between AGVs are avoided by repeating the two types of mind changes, the arrogant mind and the modest mind. The mind model includes the deep learning system. By the mind including the deep learning, we can improve the decrease of the route interference time.

ARTICLE INFO
Article History
Received 23 October 2020
Accepted 13 May 2021

Keywords
Autonomous decentralized FMS
AGV
Mind
Deep learning

JAALR2107

Download article(PDF)

Research Article
8.Extension of the Function to Ensure Real-time Traceability between UML Sequence Diagram and Java Source Code on RETUSS
Kaoru Arima1, Tetsuro Katayama1, Yoshihiro Kita2, Hisaaki Yamaba1, Kentaro Aburada1, Naonobu Okazaki1
1Department of Computer Science and Systems Engineering, Faculty of Engineering, University of Miyazaki, 1-1 Gakuen-kibanadai nishi, Miyazaki, 889-2192, Japan
2Department of Information Security, Faculty of Information Systems, Siebold Campus, University of Nagasaki, 1-1-1 Manabino, Nagayo-cho, Nishi-Sonogi-gun, Nagasaki, 851-2195, Japan
pp. 37–41
ABSTRACT
Ensuring traceability of software deliverables is one of the methods to ensure software quality. RETUSS (Real-time Ensure Traceability between UML and Source-code System) is a tool that saves labor and time, and eliminates mistakes by human handling in ensuring traceability between UML and source code. However, RETUSS is not useful due to its limited scope of application. This paper improves the usefulness of RETUSS by extending the function to ensure real-time traceability between UML sequence diagrams and Java source code on RETUSS.

ARTICLE INFO
Article History
Received 25 November 2020
Accepted 28 May 2021

Keywords
Software quality
Traceability
UML
Sequence diagram
Java

JAALR2108

Download article(PDF)

Research Article
9.Wallet Operation Inspection System Using Deep Learning for Image Processing
Junichiro Yamawaki1, Yasunari Yoshitomi2, Masayoshi Tabuse2, Taro Asada2
1Client System Development Dep., SKY Co., Ltd.,3-4-30 Miyahara,Yodogawa-ku, Osaka 532-0003, Japan
2Graduate School of Life and Environmental Sciences, Kyoto Prefectural University, 1-5 Nakaragi-cho, Shimogamo, Sakyo-ku, Kyoto 606-8522, Japan
pp. 42–47
ABSTRACT
As the average age of Japan’s population increases, it is becoming increasingly important to identify persons suffering from mild cognitive impairment (MCI), which is one of the pre-stages of dementia, to ensure they have proper care while working to suppress the progression of the disease. As a method for investigating MCI, wallet operation evaluations have been receiving considerable attention recently. Herein, we propose a system for inspecting wallet operation based on deep learning for image processing. In our system, the bills and coins extracted from a wallet are automatically scanned and recognized, which makes it possible to evaluate a person’s ability to correctly select and extract the correct bills and coins from the wallet within a reasonable period

ARTICLE INFO
Article History
Received 19 October 2020
Accepted 25 June 2021

Keywords
Mild cognitive impairment
Dementia
Wallet operation inspection
Deep learning
Image processing

JAALR2109

Download article(PDF)

Research Article
10.Design of a Data-Driven Controller based on Estimated I/O Data using Open-Loop Data
Yasuteru Nishiya, Takuya Kinoshita, Toru Yamamoto
Graduate School of Advanced Science and Engineering, Hiroshima University, 1-4-1, Kagamiyama, Higashihiroshima city, Hiroshima, Japan
pp. 48–52
ABSTRACT
In recent years, data-driven control that does not require system modeling has been proposed and extended to a non-linear system by using the database. At this time, various data are required to obtain good control performance but the cost is required. In this paper, a new scheme that enables various data generation and control system design from a set of open-loop data is proposed. Besides, the filter is designed to keep the value of the reference signal constant. A simulation example numerically verifies the effectiveness of the proposed scheme.

ARTICLE INFO
Article History
Received 15 November 2020
Accepted 31 May 2021

Keywords
Data-driven control
PID controller
Response prediction
Offline
Reference signal
Filter

JAALR2110

Download article(PDF)