检索结果-内蒙古大学图书馆

International Conference on Computer Vision and Graphics, ICCVG 2022

作者： Kuros, Sylwia Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9783031220241

Quantum Neural Networks (QNNs) are an emerging technology that can be used in many applications including computer vision. In this paper, we presented a traffic sign classification system implemented using a hybrid quantum-classical convolutional neural network. Experiments on the German Traffic Sign Recognition Benchmark dataset indicate that currently QNN do not outperform classical DCNN (Deep Convolutuional Neural Networks), yet still provide an accuracy of over 90% and are a definitely promising solution for advanced computer vision. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Hardware Acceleration of Neural Networks with Power-of-Two Quantisation

Energy Efficient Hardware Acceleration of Neural Networks wi...

引用

International Conference on Computer Vision and Graphics, ICCVG 2022

作者： Przewlocka-Rus, Dominika Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9783031220241

Deep neural networks virtually dominate the domain of most modern vision systems, providing high performance at a cost of increased computational complexity. Since for those systems it is often required to operate both in real-time and with minimal energy consumption (e.g., for wearable devices or autonomous vehicles, edge Internet of Things (IoT), sensor networks), various network optimisation techniques are used, e.g., quantisation, pruning, or dedicated lightweight architectures. Due to the logarithmic distribution of weights in neural network layers, a method providing high performance with significant reduction in computational precision (for 4-bit weights and less) is the Power-of-Two (PoT) quantisation (and therefore also with a logarithmic distribution). This method introduces additional possibilities of replacing the typical for neural networks Multiply and ACcumulate (MAC—performing, e.g., convolution operations) units, with more energy-efficient Bitshift and ACcumulate (BAC). In this paper, we show that a hardware neural network accelerator with PoT weights implemented on the Zynq UltraScale + MPSoC ZCU104 SoC FPGA can be at least 1.4x more energy efficient than the uniform quantisation version. To further reduce the actual power requirement by omitting part of the computation for zero weights, we also propose a new pruning method adapted to logarithmic quantisation. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Passivity-Based Sliding Mode controller Design for Quadrotor Using Ant Colony Optimization 5th

Passivity-Based Sliding Mode Controller Design for Quadrotor...

引用

5th International Conference on Electrical Engineering and control Applications, ICEECA 2022

作者： Bouhabza, Khedidja Guiatni, Mohamed Bouzid, Yasser Hamerlain, Mustapha Complexe Systems Control and Simulators Laboratory Ecole Militaire Polytechnique Bordj El Bahri Algeria Robotics Laboratory Head Centre de Développement des Technologies Avancées Algiers Algeria

ISBN: (纸本)9789819700448

A Passivity-based Sliding Mode controller (P-SMC) is designed in this paper to control a quadrotor (UAV) that tracks its trajectory using the Ant Colony Optimization algorithm. As a starter, feedback pacification is used to create a sliding surface, with passivity ensuring stability. A Conventional Sliding Mode method is also developed, the proposed control strategy has a faster reaching time, high accuracy, and reduces chattering. Additionally, the ant colony optimization algorithm (ACO) was used to ensure optimal performance, such as low energy consumption and small errors, finally, the validity of the proposed method is demonstrated by simulation results. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Development of Method of Generating a Reference Movement Speed of a Group of UAVs

Development of Method of Generating a Reference Movement Spe...

引用

2024 International Conference on Ocean Studies, ICOS 2024

作者： Gubankov, Anton Gornostaev, Igor Institute of Automation and Control Processes FEB RAS M.D. Ageev Institute of Marine Technology Problems Admiral G.I. Nevelskoy Maritime State University Robotics Laboratory Laboratory of Intelligent Information Systems for Marine Robots Laboratory of Marine Unmanned Aviation and Marine Aviation Systems Vladivostok Russia Institute of Automation and Control Processes FEB RAS M.D. Ageev Institute of Marine Technology Problems Admiral G.I. Nevelskoy Maritime State University Robotics Laboratory Laboratory of Robotic Systems Laboratory of Marine Unmanned Aviation and Marine Aviation Systems Vladivostok Russia

ISBN: (纸本)9798331532307

The article presents the results of the development of a method for the automatic formation of reference speeds for autonomous unmanned aerial vehicles of multirotor type, performing specified missions (such as monitoring of the sea and coastal territory in order to track populations of rare and endangered species, as well as evaluating the potential volumes of biological resources) singly or as part of a group (in formation). At the same time, the trajectories of these aircraft are set by smooth spatial curves - parametric splines of the third order, which makes it easy to adjust the specified trajectories during the mission. In order to maintain a high speed of movement of vehicles along trajectories with high accuracy of movement and saving formation, it is proposed to adjust the specified speed directly during the mission in such a way that the thrusters can ensure their required movements, taking into account the restrictions on the thrust vectors. At the same time, a simplified model of the dynamics of a quadcopter was used to calculate the values of reference speeds, taking into account the influence of wind force, environmental resistance, gravity and the total thrust vector of the propellers. The systems synthesized on the basis of this method can be implemented even on low-power onboard computing devices of unmanned aerial vehicles. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

ACO Based Optimal Integral Sliding Mode controller Design for a New Reconfigurable Unmanned Aerial Vehicle 5th

ACO Based Optimal Integral Sliding Mode Controller Design fo...

引用

5th International Conference on Electrical Engineering and control Applications, ICEECA 2022

作者： Bouhabza, Khedidja Guiatni, Mohamed Bouzid, Yasser Hamerlain, Mustapha Complexe Systems Control and Simulators Laboratory Ecole Militaire Polytechnique Bordj El Bahri Alger Algeria Robotics Laboratory Head Centre de Développement Des Technologies Avancées Algiers Algeria

ISBN: (纸本)9789819700448

The Optimized controller is established for controlling the reconfigurable UAV, which has been designed to enable various morphologies whilst keeping the performance of a standard quadrotor. These design adjustments allow the quadrotor to negotiate restricted spaces horizontally or vertically while also altering its speed to the task and surroundings and enhancing energy autonomy. The method of Ant Colony-based Optimization determines the ISM controller gains and ensures optimal exchange between errors tracking and energy consumption. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

A FIWARE based Input-Output Supervisor control Implementation 29

A FIWARE based Input-Output Supervisor Control Implementatio...

引用

29th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2024

作者： Menexis, Antonios N. Fragkoulis, Dimitrios G. Koumboulis, Fotis N. Skarpetis, Michael G. School of Science National & Kapodistrian University of Athens Robotics Automatic Control and Cyber-Physical Systems Laboratory Department of Digital Industry Technologies Euripus Campus Euboea 34400 Greece

ISBN: (纸本)9798350361230

In this paper, a FIWARE based control implementation framework for supervisory control of inputoutput models, in Discrete Event System (DES) form, will be introduced, through the case study of an industrial product transfer system having a parametric number of conveyor belts. Each conveyor belt has an actuator (motor) for the belt's clockwise move and a sensor for the detection of the presence of a product. The model of each actuator and the model of each sensor of the belt are expressed in DES form. The input-output relation between consecutive conveyor belts is formally expressed. The satisfactory cooperation between consecutive conveyor belts has been guaranteed by developing a set of two types of supervisors for each cooperative pair. The actuators and the sensors of each belt have been described as smart data models. Finally, an implementation of the proposed supervisor scheme in FIWARE has been proposed. © 2024 IEEE.

关键词： Cloud Computing Smart Data Models Supervisory control

来源：评论

学校读者我要写书评

暂无评论

Design of Gravity Compensation Scheme for Passive Lifting Method of Multi-degree Freedom Robotic Arm 18

Design of Gravity Compensation Scheme for Passive Lifting Me...

引用

18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

作者： Sun, Jing Wei, Chaoran Chen, Haotai Wang, Bin Li, Xingguang Zhang, Qiang Beijing Institute of Control Engineering Space Drive and Manipulation Mechanism Laboratory Beijing China State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350312201

Before launching a spacecraft, it is necessary to undergo micro low gravity simulations on the ground to test its reliability. The lifting method is not limited by movement time and space, and can simulate long-term low gravity environments. However, the degree of freedom of spatial mechanisms is gradually increasing, and the motion is becoming increasingly complex, making traditional lifting methods unable to meet the needs. In response to the above issues, a lifting gravity simulation scheme for a multi degree of freedom robotic arm that can achieve complex motion is proposed. The design adopts a single sling combined with a hanger to avoid interference during the motion process. Finally, simulation and experiments have proven the feasibility of the scheme - it can achieve efficient unloading without affecting the normal movement of the equipment. © 2023 IEEE.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Robust Triangular Decoupling Velocity Varying controllers for Four Wheel Steering Autonomous Vehicles 29

Robust Triangular Decoupling Velocity Varying Controllers fo...

引用

29th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2024

作者： Skarpetis, Michael G. Koumboulis, Fotis N. School of Science National and Kapodistrian University of Athens Robotics Automatic Control and Cyber-Physical Systems Laboratory Department of Digital Industry Technologies Euripus Campus Euboea 34400 Greece

ISBN: (纸本)9798350361230

This study explores the challenges of achieving triangular decoupling in a specific group of linear parameter-dependent systems that have uncertain structures, with a particular emphasis on its relevance to four-wheel steering (4WS) vehicles. A new method is presented, combining a state feedback controller that includes static and time-varying elements. The main goal of this controller design is to guarantee triangular decoupling properties and Hurwitz invariability in the face of system uncertainties. The proposed method involves developing the controller and setting solvability criteria to transform the original Parameter Dependent Uncertain System into an uncertain Linear Time-Invariant (LTI) system and subsequently meeting LTI triangular decoupling characteristics. The practical significance of the results is shown by their effective use in controlling the motion of a velocity varying four-wheel steering (4WS) car model with uncertain virtual mass and cornering stiffnesses. © 2024 IEEE.

关键词： Four wheel steering

来源：评论

学校读者我要写书评

暂无评论

Brain over Brawn: Using a Stereo Camera to Detect, Track, and Intercept a Faster UAV by Reconstructing the Intruder's Trajectory

Field Robotics

引用

Field robotics 2025年 2卷 222-240页

作者： Antonella Barišić Frano Petric Stjepan Bogdan Laboratory for Robotics and Intelligent Control Systems Faculty of Electrical Engineering and Computing University of Zagreb Unska 3 Zagreb Croatia

This paper presents our approach to intercepting a faster intruder UAV, inspired by the MBZIRC 2020 Challenge 1. By utilizing a priori knowledge of the shape of the intruder's trajectory, we can calculate an interception point. Target tracking is based on image processing by a YOLOv3 Tiny convolutional neural network, combined with depth calculation using a gimbal-mounted ZED Mini stereo camera. We use RGB and depth data from the camera, devising a noise-reducing histogram-filter to extract the target's 3D position. Obtained 3D measurements of target's position are used to calculate the position, orientation, and size of a figure-eight shaped trajectory, which we approximate using a Bernoulli lemniscate. Once the approximation is deemed sufficiently precise, as measured by the distance between observations and estimate, we calculate an interception point to position the interceptor UAV directly on the intruder's path. Our method, which we have significantly improved based on the experience gathered during the MBZIRC competition, has been validated in simulation and through field experiments. Our results confirm that we have developed an efficient, visual-perception module that can extract information describing the intruder UAV's motion with precision sufficient to support interception planning. In a majority of our simulated encounters, we can track and intercept a target that moves 30% faster than the interceptor. Corresponding tests in an unstructured environment yielded 9 out of 12 successful results.

关键词： Autonomous aerial vehicles Trajectory Target tracking Cameras Three-dimensional displays Robots Radar tracking Image reconstruction Estimation Detectors

来源：评论

学校读者我要写书评

暂无评论

Supervisors for Gas Compressor Stations with Compression and Valve Faults 8

Supervisors for Gas Compressor Stations with Compression and...

引用

8th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference, SEEDA-CECNSM 2023

作者： Fragkoulis, Dimitrios G. Koumboulis, Fotis N. Kouvakas, Nikolas D. Menexis, Antonis N. School of Science National and Kapodistrian University of Athens Robotics Automatic Control and Cyber-Physical Systems Laboratory Department of Digital Industry Technologies 34400 Greece

ISBN: (纸本)9798350383676

A Discrete Event System (DES) based approach is developed for the derivation of the model and safe performance of a gas compressor station (GCS), in the presence of all possible actuator faults. The safe performance goal is surge avoidance, despite the presence of actuator faults, and is modelled as four rules, being translated to four regular languages. The respective supervisor automata are developed to realize the four regular languages. The physical realizability and nonblocking of the synchronous product of the supervisor automata and the automaton of the system is proved. Implementation of the supervisors in the Structured Text language for PLCs is provided. © 2023 IEEE.

关键词： Discrete event simulation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：