6th EAI International Conference on Robotic Sensor Networks

herausgegeben von: Predrag S. Stanimirović, Yudong Zhang, Dunhui Xiao, Xinwei Cao

Verlag: Springer International Publishing

Buchreihe : EAI/Springer Innovations in Communication and Computing

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

This book presents the proceedings of the 6th EAI International Conference on Robotics and Networks 2022 (ROSENET 2022). The conference explores the integration of networks and robotic technologies, which has become a topic of increasing interest for both researchers and developers from academic fields and industries worldwide. The authors posit that big networks will be the main approach to the next generation of robotic research, with the explosive number of networks models and increasing computational power of computers significantly extending the number of potential applications for robotic technologies while also bringing new challenges to the networking community. The conference provided a platform for researchers to share up-to-date scientific achievements in this field. The conference took place at Swansea University, Wales, Great Britain.

Inhaltsverzeichnis

Frontmatter

An Intelligent Learning System Based on Robotino Mobile Robot Platform

Abstract

The fourth industrial revolution (Industry 4.0) has attracted more and more attention in education and research activities toward the fields of mechatronics and information technology. In this context, developing an interactive learning system for achieving the effectiveness of education and research activities is increasingly focused by lecturers, scientists, and educational company. Therefore, this paper presents an intelligent learning system that is designed based on Robotino robot, a mobile robot developed by Festo Didactic, for education, training, and research activities. Taking the great advantages of new learning system, users are able to develop their knowledge and practical skills when working with the mobile robot and its applications.

Phan Van Vinh, Phan Xuan Dung, Tran Thi Thuy Hang, Truong Hong Duc

A Neocognitron Based on Multi-objective Optimization for Few-Shot Learning

Abstract

In recent years, with the continuous development of deep learning, more and more network models have been proposed to solve practical problems. However, most models often need a large number of labeled samples to train the network to achieve better recognition results. Because a large number of samples need to be labeled, it is labor-intensive and prone to human error labels. For this reason, a large number of researchers have created the concept of few-shot learning, which entails that the model acquires new information from a limited amount of labeled samples in order to get improved recognition outcomes. In this chapter, we learn from the structure of the visual cortex of the human brain and propose new shape templates to improve the traditional neural network. First, we extract the global characteristics of the image to form a 0-1 mask. As the network hierarchy increases and the field of perception expands, the mask is cut to form shape templates. Then evolutionary computation selects some excellent shape templates, which provide a non-linear constraint for the convolution layer. Moreover, the convolution layer introduces inhibition signals for training, and a new function is proposed to make it more in line with the biomimetic principles of the human visual cortex. The results show that the proposed method can improve the accuracy of few-shot learning.

Hao Pan, Guiyu Guo, Daming Shi

Milk Temperature Control System of Calf Feeding Robot Based on Fuzzy PID

Abstract

With the continuous development of the domestic dairy industry, scientific calving has been paid more and more attention. In the process of raising calves, the temperature of dairy products fed to calves is one of the key factors in determining the healthy development of calves. The fluctuation of dairy product temperature will lead to diarrhea, growth retardation, and a survival rate decline of calves. In order to solve the problem that is difficult to control the temperature of dairy products fed to calves, this paper studies the modeling of the control object, the design of the PID controller, the optimization of the control system, and the optimization of the control system Fuzzy PID controller design and simulation results analysis, designed a set of a feeding control system suitable for calf physiological characteristics, so as to achieve the effect of constant temperature and stable control of dairy products.

Gang He, Xiaohua Cai, Yuntao Hou, Yan Ye

Bluff: A Multi-Robot Dispersion Based on Hybrid Reciprocal Velocity Obstacles to Solve the Blind Man’s Buff Problem

Abstract

This chapter introduces Bluff, a hybrid reciprocal velocity obstacles-based approach to disperse multi-robot systems avoiding collisions with the obstacles, the cohort robots, and the seeker robots and test it to solve the Blind Man’s Buff problem for robots. The environment is clustered and bounded with multiple seekers, a multi-robot system and obstacles that are both dynamic and static.

Compared to some of the traditional approaches, Bluff incorporates a decentralized approach where the robots are not in contact with each other. It makes use of hybrid reciprocal velocity obstacles approach that takes into account the unsavory factions of both velocity obstacles and reciprocal velocity obstacles methods. This makes it even more challenging to solve the problem. However, this is offset by the fact that the robots’ ultimate trajectory is oscillation-free, more natural, and collision-free. The results have been tested using robotic operating system as the middleware and Gazebo as the simulation environment. Pioneer 3-AT has been used as the research robot for the purpose because of its ease of movement and adaptability.

Gokul P

Factors Influencing the Adoption of Robo Advisory Services: A Unified Theory of Acceptance and Use of Technology (UTAUT) Model Approach

Abstract

This paper throws light on how different factors influence the adoption of Robo advisory services by Indian retail investors. There are different factors that influence the adoption of Robo advisory services trust, innovativeness, and insecurity influence perceived usefulness. Smart PLS 3.0 was used to perform the data analysis of the structural model. The uncovering of this study reveals that two prohibitors, viz., trust and innovativeness, and one inhibitor, insecurity, significantly influence the perceived usefulness of individual investors for the adoption of Robo advisory services. The sample size could be considered as one of the limitations while the number of biases that are being studied is another limitation. This study is the first of its type that will study the different aspects and key factors influencing the adoption of Robo advisory services.

Ankita Bhatia, Arti Chandani, Pravin Kumar Bhoyar, Rajiv Divekar

A Multi-region Feature Extraction and Fusion Strategy Based CNN-Attention Network for Facial Expression Recognition

Abstract

In recent years, the field of facial expression recognition (FER) has become increasingly challenging and active. To improve recognition accuracy, facial expression recognition based on a deep learning model has attracted much attention from academia and industry. Convolutional neural network (CNN) combined with attention mechanism shows great advantages in image processing and other tasks. In this study, we propose a facial multi-region feature recognition model, which extracts facial emotion features based on CNN and attention mechanism and fuses the output for facial emotion recognition. The method proposed in this paper not only extracts the overall feature information of the face but also extracts the local feature information of the eyes and mouth region and performs the feature fusion work. Therefore, the proposed method can obtain better recognition accuracy. We used JAFFE, CK+, RAF-DB, and FER-2013 datasets to validate the proposed methods. The experiment results indicate that the proposed method is effective in facial expression recognition.

Yanqiang Yang, Hui Zhou

Real Time Surgical Instrument Object Detection Using YOLOv7

Abstract

With the rapid development of minimally invasive surgery (MIS) in the medical field, surgical robot technology has developed rapidly. Human-machine combined assisted surgical technology has begun to bring good news to the majority of doctors and patients who need surgery. It has gradually become a common medical treatment. Minimally invasive surgery can overcome the shortcomings of traditional surgery. MIS has the advantages of less trauma, less impact on patients, faster recovery, less intraoperative blood loss, and so on. For surgical robots, surgical instruments are important execution components that have been widely concerned and studied in recent years. One of the core technologies of surgical robots is the detection of surgical equipment based on deep learning, which can effectively assist doctors to complete the surgery. Current surgical instrument detection methods need to be improved in real-time performance and accuracy. Therefore, this paper proposes a new real-time detection algorithm, which is based on the deep learning object detection system YOLOv7. The real dataset, which contained information on seven surgical instruments, was selected for training and validation. Experiments show that the method has good precision, recall rate, and mAP, which can be used to improve the ability of robot-assisted doctors to identify instruments during surgery.

Laiwang Zheng, Zhenzhong Liu

A Lightweight Blockchain Framework for Visual Homing and Navigation Robots

Abstract

Visual homing is a lightweight approach to robot visual navigation. Based upon stored visual information of a home location, the navigation back to this location can be accomplished from any other location in which this location is visible by comparing home to the current image. However, a key challenge of visual homing is that the target home location must be within the robot’s field of view (FOV) to start homing. Therefore, this chapter addresses such a challenge by integrating blockchain technology into the visual homing navigation system. Based on the decentralized feature of blockchain, the proposed solution enables visual homing robots to share their visual homing information and synchronously access the stored data (visual homing information) in the decentralized ledger to establish the navigation path. The navigation path represents a per-robot sequence of views stored in the ledger. If the home location is not in the FOV, the proposed solution permits a robot to find another robot that can see the home location and travel toward that desired location. The evaluation results demonstrate the efficiency of the proposed framework in terms of end-to-end latency, throughput, and scalability.

Mohamed Rahouti, Damian M. Lyons, Lesther Santana

Backmatter

Titel: 6th EAI International Conference on Robotic Sensor Networks
herausgegeben von: Predrag S. Stanimirović
Yudong Zhang
Dunhui Xiao
Xinwei Cao
Verlag: Springer International Publishing
Electronic ISBN: 978-3-031-33826-7
Print ISBN: 978-3-031-33825-0
DOI: https://doi.org/10.1007/978-3-031-33826-7