Achieving simultaneous and proportional control of individual fingers in prosthetic hands remains a challenge in myoelectric control, particularly due to variability in muscle activation patterns and actuation speeds....
详细信息
ISBN:
(数字)9798331519018
ISBN:
(纸本)9798331519025
Achieving simultaneous and proportional control of individual fingers in prosthetic hands remains a challenge in myoelectric control, particularly due to variability in muscle activation patterns and actuation speeds. Existing models struggle with speed variations, limiting real-world performance. To address this, we introduce a custom electromyography (EMG) data collection protocol designed to improve model robustness against speed changes. The dataset incorporates complementary sensors, including accelerometers, to enhance predictive *** validate the protocol, we propose a synergy-based convolutional neural network (CNN) that extracts neuromuscular coordination features from EMG and accelerometer data, enabling intuitive and adaptive prosthetic control. The dataset captures controlled variations in finger actuation speed using optical hand models, improving generalizability. Our framework achieves state-of-the-art performance, with a correlation coefficient of 0.92 on unseen test data, ensuring precise real-time finger movements without *** leveraging synergy-based features, the proposed model and dataset protocol facilitate robust, simultaneous, and proportional control of individual finger motions at varying speeds. These findings advance next-generation myoelectric controllers, paving the way for real-time deployment on embedded prosthetic systems.
In the near future, substations will consist of networks that perform various operational tasks beyond protection, automation, and control, including data analytics, remote access, remote testing, situational awarenes...
ISBN:
(数字)9781837243167
In the near future, substations will consist of networks that perform various operational tasks beyond protection, automation, and control, including data analytics, remote access, remote testing, situational awareness, and other non-operational missions. Substation network monitoring, when utilized effectively, can enhance conventional protection operations. Using IEC 61850, available in most substations today, it becomes feasible to monitor protection system performance for each protection action and store these values in a time-series database for further analysis. Monitoring protection setting consistency ensures unintended setting changes do not occur. This paper explores reducing maintenance protection tests while ensuring constant supervision of protection settings and circuits. Additionally, IEC 61850’s role in integrated asset management systems is discussed. Monitoring complements offline test results, enabling comprehensive switchgear health analysis and condition-based maintenance planning for primary assets.
Manipulators have been widely adopted in realistic scenarios like industrial manufacturing, given their many degrees of freedom and extendability. However, under non-ideal environments, the autonomous human-machine in...
详细信息
ISBN:
(数字)9798331507886
ISBN:
(纸本)9798331507893
Manipulators have been widely adopted in realistic scenarios like industrial manufacturing, given their many degrees of freedom and extendability. However, under non-ideal environments, the autonomous human-machine interaction of manipulators is still a challenging problem. Moreover, despite numerous advanced methods for environmental perception and planning control, deploying these intricate methods directly to manipulators with limited resources remains difficult. This paper proposes Doodbot, an edge computing assisted manipulator system for human-machine chess-playing. Under the hood, Doodbot makes a geometric model for the manipulator and adopts a model predictive control method to realize the rolling optimal control of the manipulator. Furthermore, Doodbot deploys a hybrid chess-board recognition algorithm combining traditional line detection and convolutional neural network-based image recognition, thus enjoying both the adaptiveness of the conventional method and the high recognition performance of the deep neural network. These computing tasks are offloaded to an edge node in proximity for computing capability augmentation, avoiding long-delayed execution on resource-limited manipulators. The feasibility and robustness of Doodbot are verified through realistic prototype system implementation. The experimental results show that Doodbot has improved the accuracy of chessboard perception by up to 31%. In addition, it can also correctly plan the motion trajectory of the robotic arm and reduce control errors by 36%. A video demo of Doodbot on a real robotic arm can be found on https://***/***/s/9q2qH4RajdDffPB.
In this paper, we consider the problem of differentially private federated learning with statistical data heterogeneity. More specifically, users collaborate with the parameter server (PS) to jointly train a machine l...
详细信息
ISBN:
(纸本)9781665417969
In this paper, we consider the problem of differentially private federated learning with statistical data heterogeneity. More specifically, users collaborate with the parameter server (PS) to jointly train a machine learning model using their local datasets that are non-i.i.d. across users. The PS is assumed to be honest-but-curious so that the data at users need to be kept private from the PS. More specifically, interactions between the PS and users must satisfy differential privacy (DP) for each user. In this work, we propose a differentially private mechanism that simultaneously deals with user-drift caused by non-i.i.d. data and the randomized user participation in the training process. Specifically, we study SCAFFOLD, a popular federated learning algorithm, that has shown better performance on dealing with non-i.i.d. data than previous federated averaging algorithms. We study the convergence rate of SCAFFOLD under differential privacy constraint. Our convergence results take into account time-varying perturbation noises used by the users, and data and user sampling. We propose two time-varying noise allocation schemes in order to achieve better convergence rate and satisfy a total DP privacy budget. We also conduct experiments to confirm our theoretical findings on real world dataset.
Recent advances in learning-based perception systems have led to drastic improvements in the performance of robotic systems like autonomous vehicles and surgical robots. These perception systems, however, are hard to ...
详细信息
ISBN:
(纸本)9781665441971
Recent advances in learning-based perception systems have led to drastic improvements in the performance of robotic systems like autonomous vehicles and surgical robots. These perception systems, however, are hard to analyze and errors in them can propagate to cause catastrophic failures. In this paper, we consider the problem of synthesizing safe and robust controllers for robotic systems which rely on complex perception modules for feedback. We propose a counterexample-guided synthesis framework that iteratively builds simple surrogate models of the complex perception module and enables us to find safe control policies. The framework uses a falsifier to find counterexamples, or traces of the systems that violate a safety property, to extract information that enables efficient modeling of the perception modules and errors in it. These models are then used to synthesize controllers that are robust to errors in perception. If the resulting policy is not safe, we gather new counterexamples. By repeating the process, we eventually find a controller which can keep the system safe even when there is a perception failure. We demonstrate our framework on two scenarios in simulation, namely lane keeping and automatic braking, and show that it generates controllers that are safe, as well as a simpler model of a deep neural network-based perception system that can provide meaningful insight into operations of the perception system.
This paper proposes a novel spectral normalized neural networks funnel control approach for servo system with unknown dynamics. The approach introduces spectral normalization technology into the funnel controller desi...
This paper proposes a novel spectral normalized neural networks funnel control approach for servo system with unknown dynamics. The approach introduces spectral normalization technology into the funnel controller design to address the unknown dynamics. Spectral normalization techniques can restrict the spectral norm of the weight matrices of the neural networks, leading to more stable and robust networks. The spectral normalized neural network exhibits strong generalization ability and can adapt to offline learning strategies, which significantly reduce the system's computation cost. Moreover, based on the funnel control architecture, the system output is constrained to remain within an acceptable boundary, optimizing transient performance and guaranteeing satisfactory controlperformance. All signals of the closed-loop system are bounded based on Lyapunov stability analysis. Finally, simulation results demonstrate that this approach provides commendable tracking performance and superior generalization capabilities.
For solar-photovoltaic (PV)-battery system, a synchronization control based on variable fractional delay filter is analysed here along-with the presence of a battery for ensuring reliable power to critical loads. In c...
详细信息
ISBN:
(纸本)9781665425360
For solar-photovoltaic (PV)-battery system, a synchronization control based on variable fractional delay filter is analysed here along-with the presence of a battery for ensuring reliable power to critical loads. In compliance with the IEEE-519 standard, the grid currents are obtained without harmonics thereby guaranteeing satisfactory performance along-with reduction in losses of the distribution network. Moreover, during the grid outage or islanded mode of operation, a voltage controller is utilized for power transfer between the PV array, battery and loads. The performance is validated though the simulation results and the system behaviour is observed for weak grid conditions along with grid outage conditions.
This paper proposes a novel integral reinforcement learning (IRL) based DC-link voltage control method for three-phase AC/DC converter. The proposed IRL control autonomously updates the optimal control gains using onl...
This paper proposes a novel integral reinforcement learning (IRL) based DC-link voltage control method for three-phase AC/DC converter. The proposed IRL control autonomously updates the optimal control gains using online data trained neural network. It produces superior controlperformance without the knowledge of system model parameters. Compared with the existing control approaches for three-phase AC/DC converter, it offers the benefits of model independence and autonomous gain tuning. The effectiveness of the proposed IRL method is verified by simulation results.
As computing systems approach the limits of traditional silicon technology, the diminishing returns in performance per watt present a significant barrier to sustaining growth in HPC. From a large-scale scientific supe...
详细信息
ISBN:
(纸本)9798350355543
As computing systems approach the limits of traditional silicon technology, the diminishing returns in performance per watt present a significant barrier to sustaining growth in HPC. From a large-scale scientific supercomputing facility point of view, we propose a multifaceted strategy toward specialized hardware and architectures that are optimized for energy efficiency in specific applications. We also emphasize the need for integrating energy-aware practices across all levels of HPC, from system design and software development to operational policies. We discuss strategic opportunities such as the adoption of application-specific accelerators, the development of energy-efficient algorithms, and the implementation of data-driven operational analytics. Our goal is to develop a comprehensive roadmap ensuring that future leadership systems at OLCF can meet scientific demands while operating within stringent energy budgets, thereby supporting sustainable computing growth.
This paper proves the computing capability of a recently proposed spiking neuron circuit. The novelty of the neuron resides in being based in a subthreshold-operated ring oscillator that is indirectly powered by the i...
This paper proves the computing capability of a recently proposed spiking neuron circuit. The novelty of the neuron resides in being based in a subthreshold-operated ring oscillator that is indirectly powered by the input spikes. This allows a very efficient power usage. In the paper, we derive an analytical model of the neuron. The neuron is then co-simulated using the analytical model along with a transistor-level circuit to check the model accuracy. Afterward, the analytical model is used to construct an spiking neural network that can be trained to 98% of accuracy on the MNIST data set, proving equivalent performance than other contemporary circuits. As an advantage, the estimated power for a LeNet-5 implementation is 114.90pJ/inference, which is competitive with the state-of-the-art.
暂无评论