检索结果-内蒙古大学图书馆

International Conference on Neuromorphic Systems (ICONS)

作者： Hajizada, Elvin Berggold, Patrick Iacono, Massimiliano Glover, Arren Sandamirskaya, Yulia Tech Univ Munich Neuromorph Comp Lab Intel Labs Chair Cognit Syst Munich Germany Tech Univ Munich Chair Computat Modeling & Simulat Munich Germany Ist Italiano Tecnol Event Driven Percept Robot Grp Genoa Italy Intel Labs Neuromorph Comp Lab Munich Germany

ISBN: (纸本)9781450397896

intelligent robots need to recognize objects in their environment. This task is conceptually different from the typical image classification task in computer vision. robots need to recognize particular object instances, not classes of objects, which makes these tasks simpler. However, these instances need to be recognized under different viewing angles, poses, and lighting conditions reliably. Moreover, for many application, robots need the capability to learn new objects quickly, e.g., in an interactive session with the user, and adapt object representations if conditions change and mistakes are made. This scenario creates a demand for object learning that (1) is continual, i.e. new objects can be added at any time without causing forgetting, (2) requires a small amount of data that can be acquired in a short interactive session with the user, and (3) stays open to later adaptation. deep neural networks trained with slow gradient-based backpropagation, despite of their excellent performance on image processing tasks, are not well-suited for interactive robotic learning tasks. We thus explore smaller neural architectures and increase autonomy of the learning process by a neuronal state machine (NSM). The NSM regulates learning in the network and enables continual adaptation of the learned object prototypes. We implement this model as a spiking neural network in Intel's neuromorphic research chip Loihi and test it on a custom event-based camera dataset generated in a simulated 3d environment. Our spiking neuronal network uses simple feature extraction layers and a single plastic layer that stores visual patterns using online, on-chip local learning rules. This network reaches 96.55 +/- 2.02% of testing accuracy on sets of 8 3d objects with 8 different views per object in interactive, on-demand learning experiments;it demonstrates up to x300 energy efficiency and better or on par latency compared to other online learning methods. This work contributes to neuronal-netw

关键词： Neuromorphic computing spiking neuronal networks event-based vision continual learning Hebbian-learning on-chip learning local learning online learning robot vision prototype-based approaches interactive learning

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning with Generalizable Gaussian Splatting

Reinforcement Learning with Generalizable Gaussian Splatting

引用

IEEE/RSJ International Conference on intelligent robots and Systems (IROS)

作者： Jiaxu Wang Qiang Zhang Jingkai Sun Jiahang Cao Gang Han Wen Zhao Weining Zhang Yecheng Shao Yijie Guo Renjing xu The Hong Kong University of Science and Technology (Guangzhou) China Beijing Innovation Center of Humanoid Robotics Co. Ltd. Center for X-Mechanics Zhejiang University China Institute of Applied Mechanics Zhejiang University China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

An excellent representation is crucial for reinforcement learning (RL) performance, especially in vision-based reinforcement learning tasks. The quality of the environment representation directly influences the achievement of the learning task. Previous vision-based RL typically uses explicit or implicit ways to represent environments, such as images, points, voxels, and neural radiance fields. However, these representations contain several drawbacks. They cannot either describe complex local geometries or generalize well to unseen scenes, or require precise foreground masks. Moreover, these implicit neural representations are akin to a "black box", significantly hindering interpretability. 3d Gaussian Splatting (3dGS), with its explicit scene representation and differentiable rendering nature, is considered a revolutionary change for reconstruction and representation methods. In this paper, we propose a novel Generalizable Gaussian Splatting framework to be the representation of RL tasks, called GSRL. Through validation in the RoboMimic environment, our method achieves better results than other baselines in multiple tasks, improving the performance by 10%, 44%, and 15% compared with baselines on the hardest task. This work is the first attempt to leverage generalizable 3dGS as a representation for RL.

关键词： Geometry Visualization Three-dimensional displays Reinforcement learning Rendering (computer graphics) Prediction algorithms neural radiance field Optimization intelligent robots Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

deep Q-network implementation for simulated autonomous vehicle control

引用

IET intelligent TRANSPORT SYSTEMS 2021年第7期15卷 875-885页

作者： Quek, Yang Thee Koh, Li Ling Koh, Ngiap Tiam Tso, Wai Ann Woo, Wai Lok Republ Polytech Sch Engn 9 Woodlands Ave 9 Singapore 738964 Singapore Newcastle Univ Int Singapore Sch Elect & Elect Engn 172A Ang Mo Kio Ave 8 05-01 Singapore 567739 Singapore Northumbria Univ Dept Comp & Informat Sci Newcastle Upon Tyne Tyne & Wear England

deep reinforcement learning is poised to be a revolutionised step towards newer possibilities in solving navigation and autonomous vehicle control tasks. deep Q-network (dQN) is one of the more popular methods of deep reinforcement learning that allows the agent that controls the vehicle to learn through its mistakes based on its actions and interactions with the environment. This paper presents the implementation of dQN to an autonomous self-driving vehicle control in two different simulated environments;first environment is in Python which is a simple 2d environment and then advanced to Unity software separately which is a 3d environment. Based on the scores and pixel inputs, the agent in the vehicle learns and adapts to its surrounding. It develops the best solution strategy to direct itself in the environment where its task is to manoeuvre the vehicle from point to point on a simulated highway scenario. The implemented dQN technique approximates the action value function with convolutional neural network. This evaluates the Q-function for the Q-learning architecture and updates the action value function. This paper shows that dQN is an effective learning method for the agent of an autonomous vehicle. In both simulated environments, the autonomous vehicle gradually learnt the manoeuvre operations and progressively gained the ability to successfully navigate itself and avoid obstacles without prior information of the surrounding.

关键词： Optical, image and video signal processing neural nets (theory) Learning in AI (theory) Road-traffic system control Mobile robots computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

PCA-Based Visual Servoing Using Optical Coherence Tomography

引用

IEEE ROBOTICS ANd AUTOMATION LETTERS 2020年第2期5卷 3430-3437页

作者： dahroug, Bassem Tamadazte, Brahim Andreff, Nicolas Univ Bourgogne Franche Comte FEMTO ST Inst AS2M Dept CNRSENSMM F-25000 Besancon France Univ Sorbonne Inst Intelligent Syst & Robot F-75005 Paris France

This letter deals with the development of a vision-based control law to achieve high-accuracy automatic six degrees of freedom (doF) positioning tasks. The objective of this work is to be able to replace a biological sample under an optical device for a non-invasive depth examination at any given time (i.e., performing repetitive and accurate optical characterizations of the sample). The optical examination, also called optical biopsy, is performed thanks to an optical coherence tomography (OCT) system. The OCT device is used to perform a 3-dimensional optical biopsy, and as a sensor to control the robot motion during the repositioning process. The proposed visual servoing controller uses the 3d pose of the studied biological sample estimated directly from the C-scan OCT images using a Principal Component Analysis (PCA) framework. The proposed materials and methods were experimentally validated using a spectral-domain OCT and a 6-doF robotic platform. The obtained results have demonstrated the pertinence of such methods which offer a positioning accuracy around 0.052 +/- 0.03 mm (mean error +/- standard deviation) for linear errors and 0.41 +/- 0.16 degrees for angular ones over a 8 x 9 x 3.5 mm(3) workspace.

关键词： Medical robots and systems computer vision for medical robotics visual servoing

来源：评论

学校读者我要写书评

暂无评论

人工智能应用于腰椎间盘突出症诊疗:推动诊治手段向规范化、高效化、精准化

引用

中国组织工程研究 2025年第29期29卷 6269-6276页

作者：张子瑜陈龙豪盛威吕涵哲沈颖王炳豪吕智桢吕立江浙江中医药大学附属第三医院浙江省杭州市310000 浙江中医药大学第三临床医学院浙江省杭州市310000 浙江中医药大学推拿(脊柱病)研究所浙江省杭州市310000

背景:近年来人工智能技术越来越多地被用于腰椎间盘突出症的诊治,提高了腰椎间盘突出症诊断的准确率及效率,丰富了腰椎间盘突出症的治疗手段,成为研究焦点。目的:从诊断与治疗角度全面展现人工智能在腰椎间盘突出症中的应用现状,分析相... 详细信息

背景:近年来人工智能技术越来越多地被用于腰椎间盘突出症的诊治,提高了腰椎间盘突出症诊断的准确率及效率,丰富了腰椎间盘突出症的治疗手段,成为研究焦点。目的:从诊断与治疗角度全面展现人工智能在腰椎间盘突出症中的应用现状,分析相应技术的局限性。方法:应用计算机检索PubMed、中国知网、万方数据库及维普数据库建库至2024年8月发表的关于人工智能在腰椎间盘突出症诊治中应用的相关文献,英文检索词为“Lumbar disc Herniation,Artificial Intelligence,Machine Learning,deep Learning,Big data,Robot,neural Network,Model,Algorithm”,中文检索词为“腰椎间盘突出症,人工智能,机器学习,深度学习,大数据,机器人,神经网络,模型,算法”,按入组标准梳理最终筛选出101篇文献进行综述。结果与结论:人工智能的不同技术推动了腰椎间盘突出症的智能化治疗,在未来的发展中凸显出巨大潜力。深度学习技术基于先进的算法,通过相应学习模型的构建对x射线片、CT及MRI影像进行优化处理,实现对退变腰椎间盘的精确定位、识别与分析,提高了自动化诊断的精度。大数据技术利用数据平台,通过分析海量医疗数据模拟疾病发展趋势,为病情评估与预测提供了新的视角。手术机器人结合机械臂、3d高清视觉系统及5G通信技术为远程精确手术操作提供支持,展现显著的技术优势。未来人工智能对腰椎间盘突出症的诊治将通过算法的持续优化和数据平台的专业化发展,推动诊治手段向规范化、高效化、精准化方向演进。

关键词：人工智能腰椎间盘突出症深度学习机器学习大数据机器人工程化组织构建

来源：评论

学校读者我要写书评

暂无评论

Binocular depth estimation using convolutional neural network with siamese branches

Binocular depth estimation using convolutional neural networ...

引用

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： Liu, Guodong Jiang, Guolai xiong, Rong Ou, Yongsheng Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergic Systems Shenzhen Institutes of Advanced Technology Shenzhen518055 China

ISBN: (纸本)9781728163215

Binocular depth estimation is a hot research topic in computer vision. Traditional methods need high precision camera calibration and key point matching, but the results are not ideal. In this paper, we introduce an approach of binocular depth estimation method based on deep learning. A new convolutional neural network is designed, which consists of two sub-networks. The first sub-network is a deep network with Siamese branches and 3d convolutional layer, it learns parallax and global information and generates a global depth estimation result in low resolution. The second is a fully convolutional deep network, which reconstructions the depth map to original resolution. The two sub-networks are connected by a pool pyramid. Experiments are taken on the Middlebury Stereo dataset show that the proposed method can generate much more accurate depth image than traditional methods. © 2019 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A new neural networks based 3-d object recognition system

A new neural networks based 3-D object recognition system

引用

Conference on intelligent robots and computer vision xVI - Algorithms, Techniques, Active vision, and Materials Handling

作者： Abolmaesumi, P Jahed, M Department of Electrical Engineering Sharif University of Technology Tehran P.O. Box 11365/9363 Iran

ISBN: (纸本)0819426407

3-d object recognition has always been one of the challenging fields in computer vision. In recent years, Ulman and Basri (1991) have proposed that this task can be done by using a database of 2-d views of the objects. The main problem in their proposed system is that the correspondent points should be known to interpolate the views. On the other hand, their system should have a supervisor to decide which class does the represented view belongs to. In this paper, we propose a new Momentum-Fourier descriptor that is invariant to scale, translation, and rotation. This descriptor provides the input feature vectors to our proposed system. By using the dystal network, we show that the objects can be classified with over 95% precision. We have used this system to classify the objects like cube, cone, sphere, torus, and cylinder. Because of the nature of the dystal network, this system reaches to its stable point by a single representation of the view to the system. This system can also classify the similar views to a single class (e.g., for the cube, the system generated 9 different classes for 50 different input views), which can be used to select an optimum database of training views. The system is also very flexible to the noise and deformed views.

关键词： object recognition Momentum-Fourier descriptor dystal network

来源：评论

学校读者我要写书评

暂无评论

Learning to Predict Visibility and Invisibility from Occlusion Events 8

Learning to Predict Visibility and Invisibility from Occlusi...

引用

8th International Conference on neural Information Processing Systems, NIPS 1995

作者： Marshall, Jonathan A. Alley, Richard K. Hubbard, Robert S. Department of Computer Science CB 3175 Sitterson Hall University of North Carolina Chapel HillNC27599-3175 United States

Visual occlusion events constitute a major source of depth information. This paper presents a self-organizing neural network that learns to detect, represent, and predict the visibility and invisibility relationships that arise during occlusion events, after a period of exposure to motion sequences containing occlusion and disocclusion events. The network develops two parallel opponent channels or "chains" of lateral excitatory connections for every resolvable motion trajectory. One channel, the "On" chain or 'Visible" chain, is activated when a moving stimulus is visible. The other channel, the "Off" chain or "invisible" chain, carries a persistent, amodal representation that predicts the motion of a formerly visible stimulus that becomes invisible due to occlusion. The learning rule uses disinhibition from the On chain to trigger learning in the Off chain. The On and Off chain neurons can learn separate associations with object depth ordering. The results are closely related to the recent discovery (Assad & Maunsell, 1995) of neurons in macaque monkey posterior parietal cortex that respond selectively to inferred motion of invisible stimuli. © NIPS 1995: Proceedings of the 8th International Conference on neural Information Processing Systems. All rights reserved.

关键词： Visibility

来源：评论

学校读者我要写书评

暂无评论

intelligent robots and computer vision xI: biological, neural Net, and 3-d methods

Intelligent Robots and Computer Vision XI: Biological, Neura...

引用

intelligent robots and computer vision xI: biological, neural Net, and 3-d methods

This conference proceedings contains 50 papers. The topics discussed are wavelets, multiresolution, and Gabor techniques;neural net methods in robotics and computer vision;neuromorphology of biological vision as a bas... 详细信息

ISBN: (纸本)0819410276

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

intelligent robots and computer vision x : neural,biological,and 3-d methods : 14-15 November 1991, Boston, Massachusetts / david P. Casasent, chair/editor;sponsored and published by SPIE--the Inter

Intelligent robots and computer vision X : neural,biological...

引用

1992年

作者： david P. Casasent chair/editor sponsored and published by SPIE--the International Society for Optical Engineering.

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：