By the end of 2020, China's property management industry total market size of about 33 billion square meters, the market is broad. In the traditional sense, most of the property cleaning work is based on manual wo...
详细信息
Continuum robots, which often rely on interdisciplinary and multimedia collaborations, have been increasingly recognized for their potential to revolutionize the field of human-computer interaction (HCI) in varied app...
详细信息
Over the last two decades, as microprocessors have evolved to achieve higher computational performance, their power density has also increased at an accelerated rate. Improving energy efficiency and reducing power con...
详细信息
Over the last two decades, as microprocessors have evolved to achieve higher computational performance, their power density has also increased at an accelerated rate. Improving energy efficiency and reducing power consumption are therefore critically important to modern computing systems. One effective technique for improving energy efficiency is dynamic voltage and frequency scaling (DVFS). With the emergence of integrated voltage regulators (IVRs), the speed of DVFS can reach microsecond (mu s) timescales. However, a practical and effective strategy to guide fast DVFS remains a challenge. In this article, we propose F-LEMMA: a fast, learning-based, hierarchical DVFS framework consisting of a global power allocator in the kernel space, a reinforcement learning-based power management scheme at the architecture level, and a swift controller at the digital circuit level. This hierarchical approach leverages computation at the system and architecture levels with the short response time of the swift controller to achieve effective and rapid mu s-level power management supported by the IVR. Our experimental results demonstrate that F-LEMMA can achieve significant energy savings (35.2%) across a broad range of workloads. Conservatively compared with existing state-ofthe-art DVFS-based power management schemes that can only operate at millisecond timescales, F-LEMMA can provide notable (up to 11%) energy-delay product (EDP) improvements across benchmarks. Compared with state-of-the-art nonlearning-based power management, our method has a universally positive effect on evaluated benchmarks, proving its adaptability.
This paper studies the algorithm design, systemdesign and experimental verification of unmanned surface vehicle path tracking. Firstly, a path tracking control algorithm for unmanned surface vehicles combining adapti...
详细信息
ISBN:
(纸本)9798350387780;9798350387797
This paper studies the algorithm design, systemdesign and experimental verification of unmanned surface vehicle path tracking. Firstly, a path tracking control algorithm for unmanned surface vehicles combining adaptive LOS line-of-sight guidance method and fuzzy PID method was proposed. Then, the unmanned surface vehicles shore-based host computersystem and the ship-borne controlsystem were built, which were written in a multi-threaded frame structure. Finally, the adaptive fuzzy control algorithm for unmanned surface vehicles path tracking proposed in this paper has good control effect through real boat experiments on the lake, and the designed software and hardware system has strong real-time performance, and the stability and accuracy of unmanned surface vehicle path tracking can be improved.
The need for environmental protection and energy conservation in the twenty-first century has highlighted the urgency of advancing Electric Vehicle (EV) technology. This research study contributes to this trajectory b...
详细信息
In this paper, subject to pipe constraints and unknown time-varying external disturbance, a prescribed performance control scheme combined with reference governor is proposed for the Quadrotor UAV system. Taking into ...
详细信息
At present, there is a labor-intensive problem in transportation industries such as supermarkets, which leads to low work efficiency. In order to improve the current situation of the transportation industry, it is nec...
详细信息
End-to-end stochastic computing (SC) emerges as a promising paradigm for efficient neural acceleration. However, existing serial SC accelerators face serious accuracy challenges due to errors in addition, limited acti...
详细信息
This study focuses on the intelligence of urban traffic management, aiming to solve the increasingly severe urban traffic congestion and safety problems by integrating computer vision, deep learning technology, and In...
详细信息
In view of the existing security products limited use scenarios, deployment and use is not flexible, limited performance and other problems, design and implementation of intelligent video surveillance system based on ...
详细信息
暂无评论