The proceedings contain 70 papers presendted at a virtual meeting. The special focus in this conference is on intelligentcomputing Techniques for Smart Energy systems. The topics include: Comparative Analysis of Trad...
ISBN:
(纸本)9789811902512
The proceedings contain 70 papers presendted at a virtual meeting. The special focus in this conference is on intelligentcomputing Techniques for Smart Energy systems. The topics include: Comparative Analysis of Traditional and Cloud-Based Disaster Recovery Methods;Voltage Profile Enhancement Using FACTS Devices;Comparative Analysis of 10T SRAM Cell using Nanodevices;Integration of Community Solar PV and DG Set for EV Charging Station;Impact of Variation of Performance Parameters on the Efficiency of CNTFET Based 7T SRAM Cells;Performance Analysis of Oxide Capacitance at Gate-Dielectric Variation in Surrounding-Gate MOSFET Structure;solution of Fractional Kinetic Equations by using Generalized Galue Type Struve Function;current Status of Renewable Energy Sources in India and Its Utilization in Hybrid Energy System;comparative Sentiment Analysis on Stock Market News Using Machine Learning;a Case Study on Electric Vehicle Conversion from an Internal Combustion Engine Vehicle;a New Hybrid Chaotic Map-Based Image Steganography Using Spectral Graph Wavelet;a Comprehensive Review on Fast Charging Stations Deployment for Electric Vehicles;Effect of Noise on Concurrence of Compact Photonic CNOT Gate Designed Using Universal Cloner;PSO and Firefly Algorithm Application for AGC Thermal-EV Integrated System with Nonlinearities;(γ, δ)-Fuzzy Hyperideals of Γ -Hypernear Rings;A Review on Multi-Input DC-DC Converter and Its controlling for Hybrid Power System;performance Analysis of 3-D Parallel Gated Junctionless Field Effect Nanowire Transistor;Design of MAC Unit for an Artificial Neural Network Using Reversible Logic Gates;biosensor Based on Bioreceptor: A Potential Biomedical Device Toward Early Detection of Bone Cancer;solar Operated Smart Elevator.
Recent advancements in Deep Reinforcement Learning (DRL) have paved the way for novel strategies in developing intelligent autonomous quadrotors, renowned for their agility and versatility. However, obtaining agile an...
详细信息
ISBN:
(纸本)9798350349603;9798350349597
Recent advancements in Deep Reinforcement Learning (DRL) have paved the way for novel strategies in developing intelligent autonomous quadrotors, renowned for their agility and versatility. However, obtaining agile and robust flight policies that can be deployed in real hardware is still a main issue in enabling the spread of those algorithms. Moreover, deploying those policies in resource-constrained nano-drones is often unfeasible. In this paper, we address the following research problems: i) How to train a DRL policy in a dynamic environment to perform an agile flight task? ii) How does this flight strategy behave against state-of-the-art model-based methods? iii) Is implementing this neural network on a nano-drone equipped with ultra-low power computing resources feasible? To address them, we have effectively trained a Multilayer Perceptron (MLP) using the Proximal Policy Optimization (PPO) algorithm within Isaac Gym parallel simulator. We compared the MLP performance against a state-of-the-art Model Predictive control (MPC) approach enhanced with learned high-level policy in solving a highly dynamic flight task. Our approach improved the success rate in challenging environment scenarios by up to 95%. We evaluated our neural network policy inference latency and memory footprint on the AI deck, a companion computer of the Crazyflie nano-drone based on GAP8, a constrained and ultra-low power System-on-Chip (SoC). We achieved an inference latency of 2.5 mu s, making it suitable for real-time control actions. The proposed work proves the possibility of using Deep Neural Networks (DNNs) to encode complex control strategies for resource-constrained robotic platforms.
Visually impaired people encounter many challenges in their daily lives, among which the most prominent is the problem of travel. This article proposes an intelligent guide cane control system based on a single-chip m...
详细信息
We investigate motion planning algorithms for the assembly of shapes in the tilt model in which unit-square tiles move in a grid world under the influence of uniform external forces and self-assemble according to cert...
详细信息
ISBN:
(纸本)9781665491907
We investigate motion planning algorithms for the assembly of shapes in the tilt model in which unit-square tiles move in a grid world under the influence of uniform external forces and self-assemble according to certain rules. We provide sever al heuristics and experimental evaluation of their success rate, solution length, and runtime.
This article focuses on the current situation that binary files generated during the tracking process of shipborne measurement and controlsystems cannot be parsed under the Linux operating system. A binary source cod...
详细信息
With the advancements in IoT technology, cloud computing, and big data technology, smart living has become an integral part of people's lives. However, traditional intelligent data computing relies heavily on clou...
详细信息
This research aims to explore the automation design principles, technical architecture and application process of electrical controlsystems in industrial production. This paper evaluates the impact of automation desi...
详细信息
This paper addresses integrated design of engineering systems, where physical structure of the plant and controller design are optimized simultaneously. To cope with uncertainties due to noises acting on the dynamics ...
详细信息
For a class of biped robots with impulsive dynamics and a non-empty set of passive gaits (unactuated, periodic motions of the biped model), we present a method for computing continuous families of locally optimal gait...
详细信息
ISBN:
(纸本)9781665491907
For a class of biped robots with impulsive dynamics and a non-empty set of passive gaits (unactuated, periodic motions of the biped model), we present a method for computing continuous families of locally optimal gaits with respect to a class of commonly used energetic cost functions (e.g., the integral of torque-squared). We compute these families using only the passive gaits of the biped, which are globally optimal gaits with respect to these cost functions. Our approach fills in an important gap in the literature when computing a library of locally optimal gaits, which often do not make use of these globally optimal solutions as seed values. We demonstrate our approach on a well-studied two-link biped model.
Thereis an urgent need for flexible production lines and other controlsystems, such as uncertain production scale, rapid iteration and optimization of business processes and structured data packages. It is urgent to ...
详细信息
暂无评论