检索结果-内蒙古大学图书馆

16th EAI International Conference on Simulation Tools and Techniques, SIMUTools 2024

作者： Trejos-Hernández, Diógenes Cerezuela-Escudero, Elena Linares-Barranco, Alejandro Robotics and Technology of Computers Lab ETSII-EPS I3US SCORE Universidad de Sevilla Seville Spain

ISBN: (纸本)9783031873447

The development of software simulators for robotic applications involves many advantages such as faster trajectory planning in virtual worlds, savings in energy consumption, reduction in the purchase of real robots, feasibility in collecting datasets for AI model training, etc. Commercial, free-access, open-source simulators for any type of robot can be found on the Internet and in the literature. Some of them allow the implementation of specific or new control models. For a behavior closer to the real world, the following must be taken into account: kinematics and dynamics, gravity, masses, etc. This paper proposes a new simulator for a neuromorphic robotic arm (modified Scorbot ER-VII) whose hardware controllers are based on Field Programmable Logic Arrays (FPGA) to allow the implementation of neuro-inspired motor controllers, such as Spiking Proportional-Integral-Derivative (SPID), to manage each joint of the robot. This simulator is developed in Matlab.and Simulink and is availab.e to the public. The simulator allows for the evaluation of different trajectories with two controllers, an Independent Joint Control (IJC) and a Computerized Torque Control (CTC). It has been tested for square and lemniscate trajectories with a small number of internally interpolated points to create reference trajectories with more points. RSME improvements of more than 10x have been measured for CTC over IJC, requiring less than 13 ms per point evaluated for a 3.6 GHz i7 computer and 32 GB RAM. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2025.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

On Implementing the Sparse Events Closed-Loop Control Theory for the CartPoleSimulation 16th

On Implementing the Sparse Events Closed-Loop Control Theor...

引用

16th EAI International Conference on Simulation Tools and Techniques, SIMUTools 2024

作者： Díaz-Romero, Santiago Paluch, Marcin Linares-Barranco, Alejandro Rios-Navarro, Antonio Robotics and Technology of Computers Lab. ETSII-EPS I3US SCORE Universidad de Sevilla Seville Spain Institute of NeuroInformatics UZH-ETHZ Zurich Switzerland

ISBN: (纸本)9783031873447

Event-based or neuro-inspired motor control systems communicate information through pulses, instantaneous bursts of electrical current that encode information very efficiently, as occurs in biological organisms. This work proposes a software implementation for sparse events closed-loop neuromorphic motor control theory (SECLOC) in a software tool. The control algorithm has been included in a simulator developed in Python, and publicly availab.e, of a robotic cart controlling an inverted pendulum. The proposed implementations can be easily ported to any FPGA or microcontroller-based board and allow control of the real robotic cart. We have tested and verified the functionality using the algorithm to generate control events for proportional-integral-derivative (PID) and linear-quadratic-regulator (LQR) controllers and obtained the parameters equivalent to the proportionality, integrative, and derivative constants for these pulsing controllers. The empirical results demonstrate the validity of both the theory in simulation and its test in an actual robot in the pulsed domain. In the simulation, for angle control using a PID, with a minimum reaction time of 1 ms from the controller, the pendulum remains in equilibrium along the cart pole travel for more than 5 min, registering the 0-degree passage more than 2800 times. For the real pendulum used, the LQR controller, and the optimal control constants, with a minimum reaction time of 6 ms of the controller, the pendulum remains in equilibrium along the carriage path, as well as under slight and moderate perturbations without dropping during all experiments performed over a simulated period of almost 3.5 days. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2025.

关键词： Two term control systems

来源：评论

学校读者我要写书评

暂无评论

Towards spiking analog hardware implementation of a trajectory interpolation mechanism for smooth closed-loop control of a spiking robot arm

arXiv

引用

arXiv 2025年

作者： Casanueva-Morato, Daniel Wu, Chenxi Indiveri, Giacomo Dominguez-Morales, Juan P. Linares-Barranco, Alejandro Robotics and Technology of Computers Lab. ETSII-EPS Universidad de Sevilla Sevilla Spain I3US Universidad de Sevilla Spain SynSense AG Corporation Zurich Switzerland Institute of Neuroinformatics University of Zurich and ETH Zurich Switzerland

Neuromorphic engineering aims to incorporate the computational principles found in animal brains, into modern technological systems. Following this approach, in this work we propose a closed-loop neuromorphic control system for an event-based robotic arm. The proposed system consists of a shifted Winner-Take-All spiking network for interpolating a reference trajectory and a spiking comparator network responsible for controlling the flow continuity of the trajectory, which is fed back to the actual position of the robot. The comparator model is based on a differential position comparison neural network, which governs the execution of the next trajectory points to close the control loop between both components of the system. To evaluate the system, we implemented and deployed the model on a mixed-signal analog-digital neuromorphic platform, the DYNAPSE2, to facilitate integration and communication with the ED-Scorbot robotic arm platform. Experimental results on one joint of the robot validate the use of this architecture and pave the way for future neuro-inspired control of the entire robot. © 2025, CC BY-NC-SA.

关键词： Comparators (optical)

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Neuromorphic Robotic-Arm Lemniscate Trajectories Dataset for Learning-Based Applications

A Hybrid Neuromorphic Robotic-Arm Lemniscate Trajectories Da...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： E. Piñero-Fuentes D.A. Curra-Sosa D. Cascado S. Canas A. Rios-Navarro F. Gomez-Rodriguez A. Jimenez-Fernandez A. Linares-Barranco Robotics and Technology of Computers Lab. ETSH-EPS. I3US. SCORE. Universidad de Sevilla Seville Spain

ISBN: (数字)9798350377200

ISBN: (纸本)9798350377217

In this work, an all-in-one neuromorphic motors controller system with reduced latency and power consumption for a robotic arm is used to record a dataset of trajectories for learning applications. Unlike human-created encoding systems, biological neural ones use neurons and spikes to process the information and make weighted decisions based on a continuous learning process. A central pattern generator is a biological structure that orchestrates the activity of motor neurons, causing muscle fibers to elongate and contract through signals generated by spikes. This process allows for the replication of learned movement patterns or trajectories. The Event-Driven Scorbot platform (ED-Scorbot) consists of a six Degrees of Freedom (DoF) robotic arm, whose controller implements a Spiking Proportional-Integrative-Derivative (SPID) algorithm, mimicking biological systems. In this paper, the ED-Scorbot is used to record a series of lemniscate trajectories drawn by the end-effector in the Cartesian space. These trajectories have been produced with different heights, widths, foci distances and orientation angles within the robot's working area. Different weights at the end-effector are used to enrich the dataset. MP4 videos, internal spiking activity, joint sensors output and target trajectory are included in this hybrid dataset. For its validation, the spiking activity has been used to train and test a recurrent Spiking Neural Networks (SNN) to classify the weight attached to the gripper with an accuracy of 83.3% on test samples.

关键词： Neuromorphics Neurons Kinematics Robot sensing systems Motors Control systems End effectors Trajectory Biological information theory Videos

来源：评论

学校读者我要写书评

暂无评论

Learning-to-learn enables rapid learning with phase-change memory-based in-memory computing

arXiv

引用

arXiv 2024年

作者： Ortner, Thomas Petschenig, Horst Vasilopoulos, Athanasios Renner, Roland Brglez, Špela Limbacher, Thomas Piñero, Enrique Barranco, Alejandro Linares Pantazi, Angeliki Legenstein, Robert IBM Research Europe - Zurich Säumerstrasse 4 Rüschlikon8803 Switzerland Institute of Theoretical Computer Science Graz University of Technology Inffeldgasse 16b Graz8010 Austria Robotics and Tech. of Computers Lab. EPS-ETSII Universidad de Sevilla Av. Reina Mercedes Seville41012 Spain

There is a growing demand for low-power, autonomously learning artificial intelligence (AI) systems that can be applied at the edge and rapidly adapt to the specific situation at deployment site. However, current AI models struggle in such scenarios, often requiring extensive fine-tuning, computational resources, and data. In contrast, humans can effortlessly adjust to new tasks by transferring knowledge from related ones. The concept of learning-to-learn (L2L) mimics this process and enables AI models to rapidly adapt with only little computational effort and data. In-memory computing neuromorphic hardware (NMHW) is inspired by the brain's operating principles and mimics its physical co-location of memory and compute. In this work, we pair L2L with in-memory computing NMHW based on phase-change memory devices to build efficient AI models that can rapidly adapt to new tasks. We demonstrate the versatility of our approach in two scenarios: a convolutional neural network performing image classification and a biologically-inspired spiking neural network generating motor commands for a real robotic arm. Both models rapidly learn with few parameter updates Deployed on the NMHW, they perform on-par with their software equivalents. Moreover, meta-training of these models can be performed in software with high-precision, alleviating the need for accurate hardware models. Copyright © 2024, The Authors. All rights reserved.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Data-driven color augmentation for H&E stained images in computational pathology

引用

Journal of Pathology Informatics 2023年 14卷 100183-100183页

作者： Marini, Niccolò Otalora, Sebastian Wodzinski, Marek Tomassini, Selene Dragoni, Aldo Franco Marchand-Maillet, Stephane Morales, Juan Pedro Dominguez Duran-Lopez, Lourdes Vatrano, Simona Müller, Henning Atzori, Manfredo Information Systems Institute University of Applied Sciences Western Switzerland (HES-SO Valais) Sierre Switzerland Centre Universitaire d'Informatique University of Geneva Geneva Switzerland Support Center for Advanced Neuroimaging University Institute of Diagnostic and Interventional Neuroradiology Bern Switzerland Department of Measurement and Electronics AGH University of Science and Technology Krakow Poland Department of Information Engineering Engineering Faculty Università Politecnica delle Marche Ancona Italy Robotics and Technology of Computers Lab ETSII-EPS Universidad de Sevilla Sevilla Spain SCORE Lab I3US Universidad de Sevilla Spain Pathology Unit Gravina Hospital Caltagirone ASP Catania Italy Medical Faculty University of Geneva Geneva Switzerland Department of Neurosciences University of Padua Padua Italy

Computational pathology targets the automatic analysis of Whole Slide Images (WSI). WSIs are high-resolution digitized histopathology images, stained with chemical reagents to highlight specific tissue structures and scanned via whole slide scanners. The application of different parameters during WSI acquisition may lead to stain color heterogeneity, especially considering samples collected from several medical centers. Dealing with stain color heterogeneity often limits the robustness of methods developed to analyze WSIs, in particular Convolutional Neural Networks (CNN), the state-of-the-art algorithm for most computational pathology tasks. Stain color heterogeneity is still an unsolved problem, although several methods have been developed to alleviate it, such as Hue-Saturation-Contrast (HSC) color augmentation and stain augmentation methods. The goal of this paper is to present Data-Driven Color Augmentation (DDCA), a method to improve the efficiency of color augmentation methods by increasing the reliability of the samples used for training computational pathology models. During CNN training, a database including over 2 million H&E color variations collected from private and public datasets is used as a reference to discard augmented data with color distributions that do not correspond to realistic data. DDCA is applied to HSC color augmentation, stain augmentation and H&E-adversarial networks in colon and prostate cancer classification tasks. DDCA is then compared with 11 state-of-the-art baseline methods to handle color heterogeneity, showing that it can substantially improve classification performance on unseen data including heterogeneous color variations. © 2022 The Authors

关键词： Color augmentation Computational pathology Deep learning Digital pathology Histopathology Stain variability

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：