فهرست مطالب

Computer and Robotics - Volume:15 Issue: 1, Winter and Spring 2022

Journal of Computer and Robotics
Volume:15 Issue: 1, Winter and Spring 2022

  • تاریخ انتشار: 1401/05/20
  • تعداد عناوین: 6
|
  • Mana Azim Araghi, Seyed Mohammad Nami MirMohammad Sadeghi, Seyed Ali MirMohammad Sadeghi * Pages 1-7

    Advanced control systems are required to maintain bicycle stability due to its unstable open-loop behaviour. This work is aimed at designing an optimal state feedback control system for bicycle stabilization. The performance index of the optimal control system is minimized using the newly developed adaptive particularly tunable fuzzy particle swarm optimization algorithm. The states of the system are estimated using a state observer. The obtained results are compared with those of the linear–quadratic regulator (LQR). The main advantage of the developed control system is that, unlike the LQR controller that is limited to linear systems, it can be extended to nonlinear control systems.

    Keywords: Bicycle stabilization, State observer, Optimal Control, APT-FPSO algorithm
  • Amir Shahab Shahabi, MohammadReza Kangavari *, Amir Masoud Rahmani Pages 9-17

    In this research, we discuss the methods that have been proposed so far to solve automatic summarization, in which both single-text and multi-text are summarized with emphasis on experimental methods and text extraction techniques. In multi-text summarization, retrieving redundant information that is readable and coherent and contains maximum information from the original text and minimum redundancy has made research in this field very important. An extraction approach based on several methods for identifying sentence similarities and a meta-heuristic optimization algorithm that has been modified and optimized for faster convergence is presented. In this algorithm, changes are made based on density detection through the probability distribution function to avoid being placed in local optimization and try to search more extensively for the response space. The experimental results obtained from the implementation of the algorithm show that the efficiency on criteria such as ROUGE and the accuracy of the proposed method is effectively increased.

    Keywords: Automatic Summarization, Optimization, ICA Algorithm, Single-text, Multi-text
  • Maryam Shamsadini, Ali Ghaffari * Pages 19-32
    The Internet of everything that is often known as The Internet of Things (IoT), is the next generation internet network that is created by intelligent objects with software and sensors, where machines can communicate with various machines and humans. The IoT industry does not have one clear set of security standards for developers and manufactures to build in consistent security. The data collected and stored with these devices such as name, age, health data, location and more can aid cyber-attack activity. The first step to face these threats is to classify it and determine the risk of attacks and threats according to different classes of layers. The present study discusses about various IoT attacks happening, classify them, its countermeasures and finding the most prominent attacks in IoT in different layers.
    Keywords: IoT, IoT Attacks, IoT Security, Vulnerability of IoT, IoT threats
  • Nasim Jelodari *, Ali Asgharpourhaji Kazem Pages 33-45
    The Internet of Things (IoT) now connects over nine billion devices. This number is predicted to approach 20 billion in the near future, and the number of things is rapidly expanding, implying that a large amount of data will be created. To handle the connected things, an infrastructure must be built. Cloud computing (CC) has become necessary in the analysis and data storage for IoT. A cloud broker, which is an intermediate in the infrastructure that controls connected things in cloud computing, is discussed in this study. An optimization problem is examined for maximizing the broker's profit and system availability while minimizing request response time and energy consumption. For this purpose, an objective function is proposed and solved using the Black Widow Optimization (BWO) algorithm. Subsequently, the obtained results are compared with the particle swarm optimization (PSO) algorithms. The results indicate that the BWO algorithm could outperform the PSO algorithm, and it can provide much better results considering different scenarios.
    Keywords: Internet of Things, Cloud Broker, Black Widow Optimization Algorithm, Optimization, Simulation
  • Sanaz Afshari, Javad Akbari Torkestani *, Mehdi Fartash Pages 47-64
    With the development of technology and the growing number of vehicles, vehicular ad-hoc networks were introduced in order to reduce road accidents and increase the level of safety and comfort of passengers. In these networks, vehicles can communicate with each other, roadside equipment, and other network components. Communications in VANET have been established for the rapid and accurate delivery of integrated information from vehicles and infrastructure to other vehicles and infrastructures through wireless networks, which play an important role in network performance, service quality, safety, and traffic congestion rate. In this article, we have categorized the types of communications in this type of network. We have also categorized and reviewed the works done in this field as a table form based on four parameters: safety, convenience, driver and passenger entertainment, and developing the structure of these communications. Finally, we presented certain aspects and challenges of research in this area that need to be resolved.
    Keywords: Vehicular Ad-Hoc Network (VANET), Intelligent Transportation System (ITS), Communications
  • Mehdi Khakbaz *, Majid Anjidani Pages 65-79
    This paper aims to improve the trajectory by an extended reinforcement learning based method in which a new tracking algorithm is used for mobile robot applications with low-rate control command. There are some trajectories that underactuated robots, like quadrotors, are unable to track; hence a suitable trajectory should be designed with respect to the robot's dynamics. In this paper, the initial trajectory is generated by Rapidly-exploring Random Tree Star algorithm which is not suitable for quadrotor application. Then, the initial trajectory is improved by an extension of Path Integral Policy Improvement with Covariance Matrix Adaption (PI2-CMA) algorithm. The extension includes improving tracking algorithm and controller performance considering low-rate control command. Our proposed algorithm succeeded to reduce the cost of tracking by designing safer and shorter trajectories which are more suitable for real robots. Furthermore, the results show that the proposed tracking algorithm and controller improve the performance of tracking. The hardware requirements for implementing our proposed method are a webcam and a personal computer; therefore with a low-cost implementation of the proposed method, a suitable trajectory is designed. In this paper, the initial trajectory is improved by an extension of PI2-CMA algorithm in which the trajectory tracking is performed such that reciprocating motions are avoided. Also, desired velocity and acceleration are used by controller for better tracking.
    Keywords: Quadrotor robot, Path planning, Trajectory tracking, Reinforcement learning