检索结果-内蒙古大学图书馆

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

学校读者我要写书评

暂无评论

arXiv 2022年

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

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. © 2022, CC BY.

关键词： System-on-chip

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

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

关键词： System-on-chip

Towards real-time and energy efficient Siamese tracking - a hardware-software approach

学校读者我要写书评

暂无评论

arXiv 2022年

Siamese trackers have been among the state-of-the-art solutions in each Visual Object Tracking (VOT) challenge over the past few years. However, with great accuracy comes great computational complexity: to achieve real-time processing, these trackers have to be massively parallelised and are usually run on high-end GPUs. Easy to implement, this approach is energy consuming, and thus cannot be used in many low-power applications. To overcome this, one can use energy-efficient embedded devices, such as heterogeneous platforms joining the ARM processor system with programmable logic (FPGA). In this work, we propose a hardware-software implementation of the well-known fully connected Siamese tracker (SiamFC). We have developed a quantised Siamese network for the FINN accelerator, using algorithm-accelerator co-design, and performed design space exploration to achieve the best efficiency-to-energy ratio (determined by FPS and used resources). For our network, running in the programmable logic part of the Zynq UltraScale+ MPSoC ZCU104, we achieved the processing of almost 50 frames-per-second with tracker accuracy on par with its floating point counterpart, as well as the original SiamFC network. The complete tracking system, implemented in ARM with the network accelerated on FPGA, achieves up to 17 fps. These results bring us towards bridging the gap between the highly accurate but energy-demanding algorithms and energy-efficient solutions ready to be used in low-power, edge systems. © 2022, CC BY.

关键词： Energy efficiency

Towards real-time and energy efficient Siamese tracking - a hardware-software approach

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

关键词： Field programmable gate arrays (FPGA)

Semantic-Based Reasoning Engine for Service Orchestration in Mass Customization Manufacturing 4

学校读者我要写书评

暂无评论

Semantic-Based Reasoning Engine for Service Orchestration in...

2022 4th International Conference on Electronic Engineering and Informatics, EEI 2022

作者： Liu, Yang Zhang, Tianshi Zhao, Yanling Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110000 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China Tsinghua University Beijing100084 China

ISBN: (纸本)9783800759231

In the mass customization manufacturing environment, manufacturing companies can connect to the customers directly via Internet and receive users manufacturing request to adjust the production resource and patterns. In this new situation, the allocation of manufacturing resources and the adjustment of production configuration should have the capability of timely responsing the demands from a large amount of customers. Therefore, efficient matching and processing of dynamic data from customer requirement and customized rules become increasingly important. This paper presents a semantic-based reasoning engine (hereinafter referred to as SBRE) in improving performance of rule engine. The paper uses a BP neural network to classify customer parameters from users requirements based on the semantic web interface. In this stage, for the customer parameters, in order to find a suitable rule engine, a semantic matching method is proposed, which can greatly mitigate complexity and improve the efficiency of matching compared with traditional matching process. The experiment results show that the method can be performed efficiently and flexibly with high data throughput. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Data handling

Serial Chain Hinge Support for Soft, Robust and Effective Grasp

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Stuhne, Dario Vuletić, Jelena Car, Marsela Orsag, Matko LARICS Laboratory for Robotics and Intelligent Control Systems University of Zagreb Faculty of Electrical Engineering and Computing Unska 3 Zagreb10000 Croatia

This paper presents a serial chain hinge support, a rigid but flexible structure that improves the mechanical performance and robustness of soft-fingered grippers. Gravity can reduce the integrity of soft fingers in horizontal approach, resulting in lower maximum payload caused by a large deflection of fingers. To substantiate our claim we performed several experiments on payload and deflection of the SofIA gripper under both horizontal and vertical approach. In addition, we show that this reinforcement does not impede the original compliant behavior of the gripper, maintaining the original kinematic model functionality. We showcase the proprioceptive and exteroceptive capabilities (RGB-D camera and flex sensor) for two opposing manipulation problems: grasping small and large objects. Finally, we validated the improved SofIA gripper in agricultural and everyday activities. © 2022, CC BY.

关键词： Grippers

Towards Open-Source and Modular Space systems with ATMOS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Roque, Pedro Phodapol, Sujet Krantz, Elias Lim, Jaeyoung Verhagen, Joris Jiang, Frank J. Dörner, David Mao, Huina Tibert, Gunnar Siegwart, Roland Stenius, Ivan Tumova, Jana Fuglesang, Christer Dimarogonas, Dimos V. Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm Sweden School of Engineering Sciences KTH Royal Institute of Technology Stockholm Sweden Autonomous Systems Laboratory ETH Zürich Zürich Switzerland Division of Robotics Perception and Learning KTH Royal Institute of Technology Stockholm Sweden

In the near future, autonomous space systems will compose many of the deployed spacecraft. Their tasks will involve autonomous rendezvous and proximity operations with large structures, such as inspections, assembly, and maintenance of orbiting space stations, as well as human-assistance tasks over shared workspaces. To promote replicable and reliable scientific results for autonomous control of spacecraft, we present the design of a space robotics laboratory based on open-source and modular software and hardware. The simulation software provides a software-in-the-loop architecture that seamlessly transfers simulated results to the hardware. Our results provide an insight into such a system, including comparisons of hardware and software results, as well as control and planning methodologies for controlling free-flying platforms. Copyright © 2025, The Authors. All rights reserved.

关键词： Space stations

Playing cards and bidding calls detection for automatic registration of a duplicate bridge game

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

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

In this work, the implementation of a playing cards and bidding calls detection system for the automatic registration of a duplicate bridge game is presented. For this purpose, two YOLOv4 deep convolutional neural networks were used. During the training process, which was carried out using an automatically generated dataset, we obtained a detector characterised by more than 99.9% accuracy on the test set. The prepared system has been evaluated on videos collected during bridge competitions and is characterised by high accuracy. The application has been implemented and evaluated on a CPU and an embedded GPU. © 2022, CC BY.

关键词： Deep neural networks

Time Synchronization in Industrial Internet of Things: A Survey

学校读者我要写书评

暂无评论

Time Synchronization in Industrial Internet of Things: A Sur...

IEEE Information Technology, Networking, Electronic and Automation control Conference

作者： Ke Zhou Xiaoming Wang Shijie Cui Electric Power Research Institute of Guangxi Power Grid Co. Ltd. Nanning China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Liaoning China

ISBN: (数字)9798350370805

ISBN: (纸本)9798350370812

Time synchronization is a fundamental strategy for many operations such as data synchronous collection, timely fault tracking, distributed control, and real-time communication in Industrial Internet of Things (IIoT). Over the years, a wide variety of protocols and technologies have been proposed for different application scenarios. The accuracy, security, robustness, low cost, and so on, are the main focus for the design of time synchronization protocol. However, so far, there is no relatively unified standard for time synchronization in IIoT. To clarify the development of time synchronization technology, this paper surveys the latest research for time synchronization in various types of networks including Precision Time Protocol and wireless sensor networks. The future development of time synchronization in IIoT is also investigated.

关键词： Surveys Wireless sensor networks Protocols Accuracy Reviews Robustness Synchronization Security Standards Industrial Internet of Things