This study presents a location and mapping system for a mobile robot with adaptive 2 -wheel drive using ROS. The Karto SLAM technique was chosen to generate 2D maps after evaluating the efficiency of other 2D laser SL...
详细信息
ISBN:
(数字)9798331505042
ISBN:
(纸本)9798331505059
This study presents a location and mapping system for a mobile robot with adaptive 2 -wheel drive using ROS. The Karto SLAM technique was chosen to generate 2D maps after evaluating the efficiency of other 2D laser SLAM algorithms. The D* Lite method is employed for global route optimization in robot planning. The DWA algorithm is used for local route planning for real-time obstacle avoidance. Consequently, once the target destination is set, the robot can autonomously and efficiently navigate towards it. The accuracy of the robot’s localization was verified through comprehensive testing in various scenarios, demonstrating its robust performance even in challenging conditions with moving obstacles. Additionally, the system’s modular architecture allows for easy integration of additional sensors or algorithms, making it adaptable and suitable for diverse applications and environments.
Silicon carbide (SiC) power transistors have been steadily gaining popularity in power electronics applications as they have improved properties over silicon based devices, namely silicon MOSFETs and IGBTs. However, b...
Silicon carbide (SiC) power transistors have been steadily gaining popularity in power electronics applications as they have improved properties over silicon based devices, namely silicon MOSFETs and IGBTs. However, because of very high switching speed which results in lower losses, in general application their use is often a concern because of electromagnetic interference (EMI). In order to fully utilise the potential of SiC based devices, a careful design of power stage, commutation loop and gate drive is needed. Because of this reason, this paper presents a review of existing gate drive methods for performance improvement of SiC devices. A special emphasis is given to the gate drive concepts, as it is an important element for the further advancement of SiC-based converters. With improved switching, specifically active gate driving techniques a compromise between EMI and switching losses can be achieved.
Unlike centralized versions, a distributed self-healing system (SHS) for electrical distributed systems is less vulnerable to single-point failures (or attacks), requires less information from the agents, and is more ...
Unlike centralized versions, a distributed self-healing system (SHS) for electrical distributed systems is less vulnerable to single-point failures (or attacks), requires less information from the agents, and is more scalable. However, optimality is challenging to achieve because binary variables are used in the modelling of the distributed service restoration problem. To deal with this challenge, this paper proposes an enhanced alternating direction method of multipliers (ADMM)based algorithm used to developed a fully distributed SHS in electrical distribution networks. Hereby, three ADMM-based heuristics are executed in parallel to improve the chances of obtaining a feasible solution. However, if none of the heuristics converge within given reasonable time, the proposed distributed SHS uses a basic restoration plan that is feasible in terms of topology and operational constraints. Results using the IEEE 123node system show that the proposed distributed SHS is reliable and it always provides a feasible solution.
Power profiling is important for upper-level models used in applications for analysis of low voltage (LV) distribution grids. Characteristic profiles that use energy-related information coming from the metering infras...
Power profiling is important for upper-level models used in applications for analysis of low voltage (LV) distribution grids. Characteristic profiles that use energy-related information coming from the metering infrastructure with low reporting rates (e.g., 1hour, 30-, or 15-minutes) are usually assumed, depending on the application type for which they serve as input. The advancement of smart metering using higher reporting rates (e.g., 1 frame/s or 1 frame/min) may enhance the assessment of details in power profiling for LV distribution grids. An analytical-based framework for quality assessment of power profiles in LV distribution grids is proposed in this study. The framework is useful to quantify the adequacy of an assumed power profile model, especially for applications dealing with the operation and planning of microgrids or energy communities.
Deep Reinforcement Learning (DRL) techniques have received significant attention in control and decision-making algorithms. Most applications involve complex decision-making systems, justified by the algorithms' c...
详细信息
ISBN:
(数字)9798350374261
ISBN:
(纸本)9798350374278
Deep Reinforcement Learning (DRL) techniques have received significant attention in control and decision-making algorithms. Most applications involve complex decision-making systems, justified by the algorithms' computational power and cost. While model-based versions are emerging, model-free DRL approaches are intriguing for their independence from models, yet they remain relatively less explored in terms of performance, particularly in applied control. This study conducts a thorough performance analysis comparing the data-driven DRL paradigm with a classical state feedback controller, both designed based on the same cost (reward) function of the linear quadratic regulator (LQR) problem. Twelve additional performance criteria are introduced to assess the controllers' performance, independent of the LQR problem for which they are designed. Two Deep Deterministic Policy Gradient (DDPG)-based controllers are developed, leveraging DDPG's widespread reputation. These controllers are aimed at addressing a challenging setpoint tracking problem in a Non-Minimum Phase (NMP) system. The performance and robustness of the controllers are assessed in the presence of operational challenges, including disturbance, noise, initial conditions, and model uncertainties. The findings suggest that the DDPG controller demonstrates promising behavior under rigorous test conditions. Nevertheless, further improvements are necessary for the DDPG controller to outperform classical methods in all criteria. While DRL algorithms may excel in complex environments owing to the flexibility in the reward function definition, this paper offers practical insights and a comparison framework specifically designed to evaluate these algorithms within the context of control engineering.
The problem of reconstructing a sequence of independent and identically distributed symbols from a set of equal size, consecutive, fragments, as well as a dependent reference sequence, is considered. First, in the reg...
详细信息
In this paper, an approach to augment action recognition time series datasets, devoted to improving the accuracy of deep learning classifiers, is proposed. In the introduced method, two operators are sequentially intr...
详细信息
In this paper, an approach to augment action recognition time series datasets, devoted to improving the accuracy of deep learning classifiers, is proposed. In the introduced method, two operators are sequentially introduced that perform linear and nonlinear modifications in the time scale of the input time series. The resulting data samples contribute to the variability within classes and allow a deep learning-based classifier to better capture their boundaries, leading to a significant improvement in the classification accuracy. The extensive experiments performed on eight publicly available action recognition datasets using the popular Bidirectional Long Short-Term Memory (BiLSTM) classifier reveal the superiority of the proposed algorithm over related approaches.
Due to the high restrictions of the global COVID-19 on society, economy and production, the electrical supply-demand balance is facing a great challenge. This paper proposes a short-term load forecasting (STLF) method...
详细信息
Modern communications are undergoing a historically significant shift, which is evident in a wide range of technology. One of these innovations that has significantly impacted a variety of businesses is unmanned aeria...
Modern communications are undergoing a historically significant shift, which is evident in a wide range of technology. One of these innovations that has significantly impacted a variety of businesses is unmanned aerial vehicles (UAVs). In the field of wireless communications, UAVs are employed to better serve users. For better performance, Non-Orthogonal Multiple Access (NOMA) technologies are included. In this research, we suggest using Machine Learning (ML) and optimum approaches to choose the appropriate height for a UAV-assisted NOMA in order to give the greatest service to consumers while taking into consideration UAV *** find that the best performance with o.0899 average root mean square (RMSE) by Ananaya then, artificial neural network (ANN) with average RMSE 0.0931 better than ElasticNet, support vector regression (SVR), Lasso and regression (LR).
This paper presents the development of an advanced system that has the ability to recognize hand gestures and also maps new ways for users to access the interfaces, using as main libraries OpenCV, but also a microfram...
详细信息
暂无评论