Journal of Robotics, Networking and Artificial Life
Volume 4, Issue 1, June 2017
Jiwu Wang, Yaodong Li, Zhijing Jian, Masanori Sugisaka
Pages: 1 - 4
In order to improve the accuracy in the On-line measurement of rail profile with a line structured light based on machine vision, the accurate extraction of a structured light stripe is a necessary and key step. An accurate extraction method is proposed for the structural light stripe in practical applications....
Yiwei Ru, Hongyue Du, Shuxiao Li, Hongxing Chang
Pages: 5 - 9
Aimed at the problem that the recognition accuracy of the monocular camera is low, we propose a binocular vision recognition algorithm for action recognition based on HART-Net(Human action recognition networks).Firstly, the left and right views obtained by the binocular camera are matched to obtain the...
Wenhao Zheng, Yingmin Jia
Pages: 10 - 13
This paper considers the formation control of nonholonomic mobile robots. The formation problem is converted to the error model based on the leader-follower structure. A sliding mode controller, which is proved to be globally finite-time stable by Lyapunov stability theory, is presented in this study....
Takuya Kinoshita, Toru Yamamoto
Pages: 14 - 17
In the development of the aging society, it is important for patients with hemiplegia to introduce adaptive welfare equipment. However, it is difficult to determine the suitable reference signal for each person. In this study, the design of a data-oriented cascade control system based on Kansei is proposed....
Hajime Itoh, Naohiko Hanajima, Yohei Muraoka, Makoto Ohata, Masato Mizukami, Yoshinori Fujihira
Pages: 18 - 21
Exercise support systems for the elderly have been developed and some were equipped with a motion sensor to evaluate their exercise motion. Normally, it provides three-dimensional time-series data of over 20 joints. In this study, we propose to apply Convolutional Neural Network (CNN) methodology to...
Go Nakamura, Taro Shibanoki, Yuichiro Honda, Akito Masuda, Futoshi Mizobe, Takaaki Chin, Toshio Tsuji
Pages: 22 - 27
This paper proposes a reaching movement model for the generation of desired trajectories within a myoelectric prosthesis training system. First, an experiment was performed to observe reaching movements with a non-impaired subject and a myoelectric prosthesis user. Reaching movements made by the prosthesis...
Kazuki Sugita, Taisuke Tanaka, Yuya Nakata, Minami Takato, Ken Saito, Fumio Uchikoba
Pages: 28 - 31
This paper proposes a hexapod type microrobot controlled by an artificial neural networks IC. The structural component of the microrobot is produced by micro electro mechanical systems (MEMS) process. The rotary actuator inside the robot is composed of the artificial muscle wire of shape memory alloy...
8. An Estimation Method for Environmental Friction Based on Body Dynamic Model of Caenorhabditis elegans
Zu Soh, Michiyo Suzuki, Toshio Tsuji
Pages: 32 - 40
Caenorhabditis elegans is a small worm which is approximately 1 mm in length. The present study proposes an estimation method for frictional force using locomotion information obtained from video analysis of actual worms. The results indicate that the body model driven by the estimated frictional force...
Hidehiko Yamamoto, Hirotaka Moribe, Takayoshi Yamada
Pages: 41 - 44
This study develops the system called UNARM which assists the unit placement decision of the automatic assembling equipment to assemble efficiently. The unit is a part supply or a robot hand constituting assembling equipment. It is the system which decides these unit placements where of the assembling...
10. Obstacle Avoidance Method for Electric Wheelchairs Based on a Multi-Layered Non-Contact Impedance Model
Haruna Kokubo, Taro Shibanoki, Takaaki Chin, Toshio Tsuji
Pages: 45 - 48
This paper proposes an obstacle avoidance method based on a multi-layered non-contact impedance model for control of the biosignal-based electric wheelchair. The proposed system can calculate a virtual repulsive force before the collision by multi-layered impedance fields covered around it. This system...
11. An Improved Parameter Value Optimization Technique for the Reflectionless Transmission-Line Model of the Cochlea
Takemori Orima, Yoshihiko Horio
Pages: 49 - 52
The passive reflectionless transmission-line model can reproduce physiological cochlear properties. We have applied an optimization technique to obtain good parameter values that give a desired cochlear property. However, we found that, in some case, it is difficult to find the sub-optimal parameter...
12. Clinical Evaluation of UR-System-PARKO for Recovery of Motor Function of Severe Plegic Hand after Stroke
Hirofumi Tanabe, Yoshifumi Morita
Pages: 53 - 57
The first author has developed TANABE therapy for severe hemiplegic stroke patients. In this paper we developed a training system (UR-System-PARKO) on the basis of TANABE therapy. The clinical test of the therapeutic effect of the UR-System-PARKO was performed in severe plegic hand. The results show...
Ethan Green, Takashi Kohno
Pages: 58 - 61
This research looks at an ultra-low power subthreshold-operated silicon neuron circuit designed with qualitative neuronal modeling. One technical challenge to future implementation of such circuits is parameter tuning — a problem stemming from temperature sensitivity of subthreshold-operated MOSFETs...
14. A Combination of Machine Learning and Cerebellar-like Neural Networks for the Motor Control and Motor Learning of the Fable Modular Robot
Ismael Baira Ojeda, Silvia Tolu, Moisés Pacheco, David Johan Christensen, Henrik Hautop Lund
Pages: 62 - 66
We scaled up a bio-inspired control architecture for the motor control and motor learning of a real modular robot. In our approach, the Locally Weighted Projection Regression algorithm (LWPR) and a cerebellar microcircuit coexist, in the form of a Unit Learning Machine. The LWPR algorithm optimizes the...
Wisanu Jitviriya, Jiraphan Inthiam, Eiji Hayashi
Pages: 67 - 70
This paper presents the cloud action model for a five DOF Seamless robotic arm using the inverse kinematics solution based on artificial neural network (ANN). Levenberg-Marquardt method is used in training algorithm. The desired position and orientation of the end effector is defined as the input pattern...
Jumpei Ono, Takashi Ogata
Pages: 71 - 76
We propose the concept of a game system that includes an automatic story-generation function based on a table-top role playing game (TRPG). In this idea, stories are generated or transformed based on communication between a “game master (GM),” who controls the story generation, and “players (PLs),” who...
Huailin Zhao, Shunzhou Wang, Shifang Xu, Yani Zhang, Masanori Sugisaka
Pages: 77 - 80
When the ground or air patrol robot monitors a certain area, one of the important intelligent functions is to monitoring and alerting unusual event of the monitored area. This paper proposes a method via the number of people in the monitored area to detect the environment is safety or not. We use mature...
Tsutomu Ito, Katsuhiko Takahashi, Katsumi Morikawa, Takao Ito, Rajiv Mehta, Seigo Matsuno, Makoto Sakamoto
Pages: 81 - 86
A survey of the relevant literature reveals that a plethora of network analytic facets, such as degree, eigenvalue, density, block, cluster, have been developed and employed to further our understanding of network structures. To extend our understanding of network systems, additional dimensions need...
19. A Voice Signal-Based Manipulation Method for the Bio-Remote Environment Control System Based on Candidate Word Discriminations
Taro Shibanoki, Go Nakamura, Takaaki Chin, Toshio Tsuji
Pages: 87 - 90
This paper proposes a voice signal-based manipulation method for the Bio-Remote environment control system. The proposed system learns relationships between multiple candidate words’ phonemes extracted by a largevocabulary speaker-independent model and control commands based on a self-learning look-up...
Dinda Pramanta, Takashi Morie, Hakaru Tamukoh
Pages: 91 - 96
This study proposes an implementation of pulse-coupled phase oscillators over multiple field-programmable-gate-array (FPGA) communication links. Two FPGAs are connected by a gigabit transceiver and a First-In First-Out interface. To verify the effect of communication delay between FPGAs on oscillator...
Takuya Nanami, Filippo Grassia, Takashi Kohno
Pages: 97 - 101
DSSN model is a qualitative neuronal model designed for efficient implementation in a digital arithmetic circuit. In our previous studies, we extended this model to support a wide variety of neuronal classes. Parameters of the DSSN model were hand-fitted to reproduce neuronal activity precisely. In this...
Yun-xiang Liu, Wei Zhang, Lan-feng Zhou
Pages: 102 - 105
Based on the characteristics of wireless sensor network communication in mine, LEACH protocol clustering is optimized, and the factors of energy and distance are considered fully. The selection of cluster head nodes is optimized, and a routing algorithm based on K-means ++ clustering is proposed. The...
Chung-Wen Hung, Yan-Ting Yu, Bo-Kai Huang, Wei-Lung Mao
Pages: 106 - 109
Ultra-high-speed motors play a very important role in machine tools. A speed-sensor-less ultra-high-speed motor driver is proposed in this paper. Without any speed sensor that is extremely expensive, the proposed driver employing a sensor-less estimation scheme can perform a closed-loop control very...