This paper investigates the use of a hybrid Recurrent Neural network to reproduce the behavior of a nonlinear long-horizon Model Predictive controller (MPC) used in traction motor drive systems. The goal is to assess ...
详细信息
Model-free reinforcement learning is a promising approach for autonomously solving challenging robotics control problems, but faces exploration difficulty without information about the robot's morphology. The unde...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
Model-free reinforcement learning is a promising approach for autonomously solving challenging robotics control problems, but faces exploration difficulty without information about the robot's morphology. The under-exploration of multiple modalities with symmetric states leads to behaviors that are often unnatural and sub-optimal. This issue becomes particularly pronounced in the context of robotic systems with morphological symmetries, such as legged robots for which the resulting asymmetric and aperiodic behaviors compromise performance, robustness, and transferability to real hardware. To mitigate this challenge, we can leverage symmetry to guide and improve the exploration in policy learning via equivariance / invariance constraints. We investigate the efficacy of two approaches to incorporate symmetry: modifying the network architectures to be strictly equivariant / invariant, and leveraging data augmentation to approximate equivariant / invariant actor-critics. We implement the methods on challenging loco-manipulation and bipedal locomotion tasks and compare with an unconstrained baseline. We find that the strictly equivariant policy consistently outperforms other methods in sample efficiency and task performance in simulation. Additionaly, symmetry-incorporated approaches exhibit better gait quality, higher robustness and can be deployed zero-shot to hardware.
internet of Underwater Things (IoUT) is the underwater network of connected objects and systems that have a wide range of applications, ranging from undersea critical infrastructure monitoring and marine biodiversity ...
详细信息
Batteries, which are collections of electrochemical cells, produce electricity to run electrical equipment. Batteries continuously transform chemical energy into electrical energy, and for optimum performance, they ne...
详细信息
Grid-tied solar photovoltaic-based distributed generation systems are required to provide consistent and controlled levels of active and reactive power to the grid. However, the intermittent nature of the solar resour...
详细信息
ISBN:
(纸本)9798350377958;9798350377941
Grid-tied solar photovoltaic-based distributed generation systems are required to provide consistent and controlled levels of active and reactive power to the grid. However, the intermittent nature of the solar resource available to PV systems makes the use of energy storage system indispensable for enhancing balance of supply and demand and reliability. The PV inverter controller plays a pivotal role in ensuring the proportional percentage output of the active and reactive power, contributing to system stability. Most of the research in the literature focuses on the design and control of small-scale power converters to enhance performance, however, ongoing research persists regarding the practical integration of these converters onto the grid. Upon integration of the system with the grid, the voltages at the point of common coupling synchronize with those of the grid. This paper evaluates the potential of regulating the voltage level of grid coupled solar system and upholding the power quality within a medium voltage distribution network. The control of active and reactive power was achieved through manipulation of the dq-component of the grid current. No additional PI loop is used to regulate the DC-side voltage, which is another advantage of this configuration.
Millimeter wave communication systems offer a new perspective for addressing bandwidth congestion, but their high hardware cost and power consumption limit their application in internet of Things (IoT) devices. A wire...
详细信息
ISBN:
(纸本)9798350387414
Millimeter wave communication systems offer a new perspective for addressing bandwidth congestion, but their high hardware cost and power consumption limit their application in internet of Things (IoT) devices. A wireless beam modulation (WBM) system has been proposed as a cost-effective alternative. The patch antenna array on the IoT nodes formulates two transmit beams with different directions. Information bits are transmitted through the energy difference of aligned beams by WBM. However, challenges arise from the random emission of beams and the avoidance of complex data processing, resulting in signal attenuation and reduced communication quality. In this paper, the optimal precoding scheme is first derived, and then we design a manifold optimization-based precoding scheme that directly handles the constant modulus constraint of the precoding vectors. Simulation results show that the proposed precoding scheme achieves a significant performance improvement over existing ones and performs close to the theoretical upper bound when the gains of the different paths in the channel are fairly consistent.
With the continuous advancement of communication technology, GEO (geostationary orbit) satellite has shown significant advantages in the field of long-distance communication, and will be an important part of the futur...
详细信息
The goal of the work is to identify the possibility of using machine learning algorithms with a multiclass approach to detect attacks in internet of Things (IoT) networks, determine their type, improve the security of...
详细信息
Edge sensing supported by wireless transmission is one of the core enabling technologies for flexibly implementing the Industrial internet of Things (IIoT). Balancing network resource consumption and sensing accuracy ...
详细信息
ISBN:
(纸本)9798350310900
Edge sensing supported by wireless transmission is one of the core enabling technologies for flexibly implementing the Industrial internet of Things (IIoT). Balancing network resource consumption and sensing accuracy under dynamic network conditions is a critical challenge. In this work, we bridge the gap between edge sensing performance and transmission design through observability analysis and learning-based methods. Particularly, utilizing observability probability as the key metric, we design the network resource reservation for specific sensing performance demands including stability based on our derived upper and lower probability bounds. Then, to further reduce the overall cost of edge sensing and transmission, an intelligent transmission scheduling method (ITSM) based on deep reinforcement learning is provided, which dynamically schedules the number of transmissions for each sensor. In ITSM, the action space is determined according to the amount of our reserved resources, and both the states of sensing error and fading channel are taken into account. Finally, the superiority of our proposed methods is fully demonstrated through numerical simulations in a typical IIoT system of industrial hot rolling.
The rapid increase in the deployment of internet-of-Things (IoT) devices necessitates robust intrusion detection systems. This study evaluates the effectiveness of machine learning models, including Decision Tree, Ran...
详细信息
暂无评论