检索结果-内蒙古大学图书馆

Arena-Bench: A Benchmarking Suite for Obstacle Avoidance Approaches in Highly Dynamic Environments

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kästner, Linh Bhuiyan, Teham Le, Tuan Anh Treis, Elias Cox, Johannes Meinardus, Boris Kmiecik, Jacek Carstens, Reyk Pichel, Duc Fatloun, Bassel Khorsandi, Niloufar Lambrecht, Jens Industry Grade Networks and Clouds Faculty of Electrical Engineering and Computer Science Berlin Institute of Technology Berlin Germany

The ability to autonomously navigate safely, especially within dynamic environments, is paramount for mobile robotics. In recent years, DRL approaches have shown superior performance in dynamic obstacle avoidance. However, these learning-based approaches are often developed in specially designed simulation environments and are hard to test against conventional planning approaches. Furthermore, the integration and deployment of these approaches into real robotic platforms are not yet completely solved. In this paper, we present Arena-bench, a benchmark suite to train, test, and evaluate navigation planners on different robotic platforms within 3D environments. It provides tools to design and generate highly dynamic evaluation worlds, scenarios, and tasks for autonomous navigation and is fully integrated into the robot operating system. To demonstrate the functionalities of our suite, we trained a DRL agent on our platform and compared it against a variety of existing different model-based and learning-based navigation approaches on a variety of relevant metrics. Finally, we deployed the approaches towards real robots and demonstrated the reproducibility of the results. The code is publicly available at ***/igncresearch/arena-bench. © 2022, CC BY.

关键词： Benchmarking

Imagination-augmented Navigation Based on 2D Laser Sensor Observations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Shen, Zhengcheng Kästner, Linh Yordanova, Magdalena Lambrecht, Jens Industry Grade Networks and Clouds Faculty of Electrical Engineering and Computer Science Berlin Institute of Technology Berlin Germany

Autonomous navigation of mobile robots is an essential task for various industries. Sensor data is crucial to ensure safe and reliable navigation. However, sensor observations are often limited by different factors. Imagination can assist to enhance the view and aid navigation in dangerous or unknown situations where only limited sensor observation is available. In this paper, we propose an imagination-enhanced navigation based on 2D semantic laser scan data. The system contains an imagination module, which can predict the entire occupied area of the object. The imagination module is trained in a supervised manner using a collected training dataset from a 2D simulator. Four different imagination models are trained, and the imagination results are evaluated. Subsequently, the imagination results are integrated into the local and global cost map to benefit the navigation procedure. The approach is validated on three different test maps, with seven different paths for each map. The quality and numeric results showed that the agent with the imagination module could generate more reliable paths without passing beneath the object, with the cost of a longer path and slower velocity. © 2022, CC BY.

关键词： Navigation

RATIONAL DIOPHANTINE SEXTUPLES WITH STRONG PAIR

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dujella, Andrej Kazalicki, Matija Petričević, Vinko Department of Mathematics Faculty of Science University of Zagreb Bijenička cesta 30 Zagreb10000 Croatia Faculty of Electrical Engineering Computer Science and Information Technology Osijek Josip Juraj Strossmayer University of Osijek Kneza Trpimira 2B OsijekHR-31000 Croatia

A set of m distinct nonzero rationals {a1, a2, . . ., am} such that aiaj + 1 is a perfect square for all 1 ≤ i i2 + 1 is a perfect square for 1 ≤ i ≤ m, then we say the m-tuple is strong. In this paper, we construct infinite families of rational Diophantine sextuples containing a strong Diophantine pair. © 2024, CC BY.

关键词：

Study and prediction of prostate cancer using fuzzy inference system

学校读者我要写书评

暂无评论

Materials Today: Proceedings 2022年 56卷 157-164页

作者： Boadh, Rahul Aarya, Deo Datta Dahiya, Mamta Rathee, Rakesh Rathee, Sarita Kumar, Ajay Jain, Sarika Rajoria, Yogendra Kumar Department of the Mathematics School of Basic and Applied Science K. R. Mangalam University Sohna Road Haryana Gurugram122103 India Department of the Mathematics Acharya Narendra Dev College University of Delhi India Department of Computer Science & Engineering Faculty of Engineering and Technology Shree Guru Govind Singh Tricentenary University Haryana Gurugram122103 India University Institute of Engineering & Technology Maharshi Dayanand University Haryana 124001 Rohtak India Department of Electrical Engineering DPG Institute of Technology and Management Haryana Gurgaon122001 India Department of Mechanical Engineering Faculty of Engineering and Technology Shree Guru Govind Singh Tricentenary University Haryana Gurugram122103 India Department of Mathematics Amity School of Applied Sciences Amity University Haryana Gurugram122413 India

The essential driver of passing among men on the planet is prostate disease. In the chief stage, for early identification of the prostate disease by applying Fuzzy Inference System (FIS) has been depicted in this study. The age of the patient, Prostate Volume (PV), % Free PSA (FPSA) and Prostate Specific Antigen (PSA) are utilized as input parameters in FIS for computing the risk factor of the prostate cancer. In this study Mamdani method is used for evaluation and analysis of the Prostate Cancer Risk (PCR). The present FIS additionally required the base estimation decreases horribleness lessens dismalness, mortality and more dependable from other system. It can likewise be considered in medicine to decrease manual assignments and human mistake. This review advocate that, this FIS might consequence on work on the productivity to recognized the distinctive kind of the malignant growths just as lessening the expense of care of the patients. © 2022

关键词： Risk assessment

Image Classification of Lotus in Nong Han Chaloem Phrakiat Lotus Park Using Convolutional Neural Networks

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Phattaraworamet, Thanawat Sangsuriyun, Sawinee Kutchomsri, Phoempol Chokphoemphun, Susama Department of Electrical and Computer Engineering Faculty of Science and Engineering Kasetsart University Chalermphrakiat Sakonnakhon Province Campus Sakon Nakhon Thailand Department of Computer and Information Science Faculty of Science and Engineering Kasetsart University Chalermphrakiat Sakonnakhon Province Campus Sakon Nakhon Thailand

In the era of technological advancement, this study investigated the concept of smart learning in the Nong Han Chaloem Phrakiat Lotus Park by using a convolutional neural network (CNN) for the classification of lotus plants leading to the development of a mobile application. The scope of this study was to classify 11 species of lotus plants using the proposed CNN model with different techniques (Augmentation, Dropout, L2) and hyper parameters (dropout and epoch number). The expectation outcome was to obtain a high-performance CNN model with reduced total parameters compared to using three different pre-trained CNN models (Inception V3, VGG16 and VGG19) as benchmarks. The performance of the model was presented in terms of accuracy, F1-score, precision, and recall values. The results showed that the CNN model with the Augmentation, Dropout, and L2 techniques at a dropout value of 0.4 and an epoch number of 30 provided the highest testing accuracy of 0.9954. The best proposed model was more accurate than the pre-trained CNN models, especially compared to Inception V3. In addition, the number of total parameters was reduced by approximately 1.80–2.19 times. © 2022, The Authors. All rights reserved.

关键词： Neural network models

Human-Following and -guiding in Crowded Environments using Semantic Deep-Reinforcement-Learning for Mobile Service Robots

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kästner, Linh Fatloun, Bassel Shen, Zhengcheng Gawrisch, Daniel Lambrecht, Jens Industry Grade Networks and Clouds Faculty of Electrical Engineering and Computer Science Berlin Institute of Technology Berlin Germany

Assistance robots have gained widespread attention in various industries such as logistics and human assistance. The tasks of guiding or following a human in a crowded environment such as airports or train stations to carry weight or goods is still an open problem. In these use cases, the robot is not only required to intelligently interact with humans, but also to navigate safely among crowds. Thus, especially highly dynamic environments pose a grand challenge due to the volatile behavior patterns and unpredictable movements of humans. In this paper, we propose a Deep-Reinforcement-Learning-based agent for human-guiding and -following tasks in crowded environments. Therefore, we incorporate semantic information to provide the agent with high-level information like the social states of humans, safety models, and class types. We evaluate our proposed approach against a benchmark approach without semantic information and demonstrated enhanced navigational safety and robustness. Moreover, we demonstrate that the agent could learn to adapt its behavior to humans, which improves the human-robot interaction significantly. © 2022, CC BY.

关键词： Reinforcement learning

Improving Energy Consumption In IoT Networks: Reducing Sensors Energy By Timing Control

学校读者我要写书评

暂无评论

Improving Energy Consumption In IoT Networks: Reducing Senso...

Communication and Information Technology (AICCIT), Al-Sadiq International Conference on

作者： Ali Hameed Luaibi Al-Taie Mustafa S. Aljumaily A. M. Ayal Ahmed Al-Khaleefa Adel Manaa Dakhil Ali Alsalamy Computer Engineering Department Faculty of Engineering Shahid Chamran University of Ahvaz Ahvaz Iran Electrical Engineering and Computer Science Department University of Tennessee Knoxville Tennessee USA University of Misan Maysan Iraq Department of Physics Faculty of Education University of Misan Maysan Iraq Department of Electrical Engineering College of Engineering University of Misan Maysan Iraq Department of Computer Technical Engineering College of Information Technology Imam Ja’afar Al-Sadiq University Al-Muthanna Iraq

The number of sensors is constantly increasing as a result of the urgent need for smart homes, factories, hospitals, military facilities, etc. Consequently, the energy consumption of these mostly battery-driven devices has increased, and due to their continuous work without stopping, it became necessary to think about and study to reduce energy consumption. In this paper, we are suggesting reducing energy consumption by establishing a schedule to turn the IoT sensors on and off according to the user demand and under their control. This research proposed a different On/Off time scenario when sensors are distributed as groups, each connected to gateways (Microcontrollers), which in turn are connected to the main server via a wireless connection, the Microcontrollers continuously check the readings sent by these sensors. The results showed the proposed algorithm increased the residual energy of the network by assigning sleeping intervals depending on the covered area and the number of neighboring nodes.

关键词：

Industrial Digital Twins Powered by Artificial Intelligence Solutions for Enhanced Product Life-Cycle Development 4

学校读者我要写书评

暂无评论

Industrial Digital Twins Powered by Artificial Intelligence ...

4th International Symposium on Agents, Multi-Agents Systems and Robotics, ISAMSR 2021

作者： Hlayel, Mohammed Jawad, Mohammed Saeed Mahdin, Hairulnizam Mostafa, Salama A. Mohammed Alduais, Nayef Abdulwahab Abd Wahab, Mohd Helmy Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Johor Malaysia Faculty of Electrical and Electronic Engineering Universiti Tun Hussein Onn Malaysia Johor Malaysia

ISBN: (纸本)9781728166544

Digital-Twin technology can be considered as a giant step toward Industry 4.0. Automated product life-cycle development that can be achieved by digital-twin and AI solutions is of a high concern recently both in academia and industry and it is highly expected to witness a raid growth in the coming few years. This paper investigating the different enhancements can be achieved by digital twin powered-AI technology in each product-life cycle development. This includes the design phase, the build phase and the operational phase of the modern product-life cycle development. The aim of such investigation study is to clearly identify how digital twin technology and AI solutions can enhance each phase of product-life cycle. This allows organizations to clearly understand the contributions of digital twins and AI technologies in their plans and objectives towards successful industrial digital transformation with high return of investments. © 2021 IEEE.

关键词： Industry 4.0

Multi-FEAT: Multi-Feature Edge AlignmenT for Targetless Camera-LiDAR Calibration

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Bichi Rajan, Raj Thilak The Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft2628CD Netherlands

The accurate environment perception of automobiles and UAVs (Unmanned Ariel Vehicles) relies on the precision of onboard sensors, which require reliable in-field calibration. This paper introduces a novel approach for targetless camera-LiDAR extrinsic calibration called Multi-FEAT (Multi-Feature Edge AlignmenT). Multi-FEAT uses the cylindrical projection model to transform the 2D(Camera)-3D(LiDAR) calibration problem into a 2D-2D calibration problem, and exploits various LiDAR feature information to supplement the sparse LiDAR point cloud boundaries. In addition, a feature matching function with a precision factor is designed to improve the smoothness of the solution space. The performance of the proposed Multi-FEAT algorithm is evaluated using the KITTI dataset, and our approach shows more reliable results, as compared with several existing targetless calibration methods. We summarize our results and present potential directions for future work. © 2022, CC BY-NC-SA.

关键词： Cameras