检索结果-内蒙古大学图书馆

Toward Learning-Based Visuomotor Navigation With Neural Radiance Fields

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2024年第6期20卷 8907-8916页

作者： Liu, Qiming Chen, Nanxi Liu, Zhe Wang, Hesheng Shanghai Jiao Tong Univ Dept Automat Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ AI Inst MoE Key Lab Artificial Intelligence Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Key Lab Syst Control & Informat Proc Shanghai Engn Res Ctr Intelligent Control & Manage Dept AutomatMinist EducKey Lab Marine Intelligen Shanghai 200240 Peoples R China

Creating memory representations is essential for developing viable navigation strategies for intelligent agents. Although neural radiance fields (NeRFs) have shown great promise as a novel method for spatial representation, their potential for integration into learning-based navigation as a memory structure has been largely overlooked in the existing literature. In this article, we introduce a navigation pipeline that incorporates NeRF into visuomotor navigation. Initially, we present a derivative radiance field that facilitates one-shot pose and depth estimation from a single query image. By assuming equivalence between density and space occupancy, we generate a geometric accessibility map based on an offline-constructed NeRF prior. Utilizing the above information, we design a global planner that decomposes long-term tasks by performing waypoint estimation and rendering. Finally, we employ an imitation-learned local controller to achieve a reliable navigation policy. Our pipeline effectively utilizes NeRF's compact spatial representation for task decomposition and action generation, enabling efficient navigation. Experimental results highlight its advantages over recent implicit and explicit memory approaches in image-goal navigation tasks. Moreover, we conduct interpretability studies and apply our algorithm in real-world scenarios to further attest to its practicality and effectiveness.

关键词： Navigation Task analysis Rendering (computer graphics) Robots Visualization Pipelines Trajectory memory structure neural radiance fields (NeRFs) visuomotor navigation

来源：评论

学校读者我要写书评

暂无评论

Light-weight configurable architecture for QRS detection

引用

IET COMPUTERS AND DIGITAL TECHNIQUES 2019年第2期13卷 70-77页

作者： Jain, Nupur Mishra, Biswajit Dhirubhai Ambani Inst Informat & Technol VLSI Design & Embedded Res Grp Gandhinagar Gujarat India

In this study, the authors present a configurable architecture having gate count of $ \simeq 3.2k$similar or equal to 3.2k and on the fly reconfigurability for low-power biomedical applications such as QRS detection, ExG processing etc. The proposed architecture is a light-weight co-processor that supports on-node digital signal and image processing functions potentially eliminating the power consumed by radios in wireless sensor node and body sensor network. The architecture consists of a 3 x 3 array of register units along with adaptive memory with configurable data path. The architecture can be configured on-the-fly for seven functions with the current memory structure. However, more number of functions can be targeted with increased memory. They demonstrate the realisation of Pan-Tompkins algorithm commonly used for QRS detection on the proposed architecture using the reconfigurability. This work offers $ \approx 4 \times $approximate to 4x reduced area and $2.3 \times $2.3x increase in performance with respect to the existing contemporary literature.

关键词： body sensor networks memory architecture medical signal processing electrocardiography coprocessors weight configurable architecture QRS detection gate count fly reconfigurability low-power biomedical applications ExG processing light-weight co-processor on-node digital signal image processing wireless sensor node body sensor network adaptive memory configurable data path on-the-fly memory structure

来源：评论

学校读者我要写书评

暂无评论

ARCHITECTURE OF A HARDWARE DATA INTERPRETER

引用

IEEE TRANSACTIONS ON COMPUTERS 1979年第2期28卷 101-109页

作者： CHU, Y Department of Computer Science University of Maryland

Data interpretation refers to the execution of the data declarations of a high-level language program which declare the data variables, the data types, and the data structures in the high-level language program. This paper introduces the direct-execution computer architecture and presents the architecture of a hardware data interpreter. The data interpreter scans the data declaration, and stores the type, structural, and referencing information about the data in an associative memory. It then interprets the data when the data name is referred to. It also performs the data operations of the data types of the high-level programming language.

关键词： memory structure Computer Architecture Data Declarations Direct Execution Computer Hardware Interpreter High Level Language Computer

来源：评论

学校读者我要写书评

暂无评论

Perceptual illusion of body-ownership within an immersive realistic environment enhances memory accuracy and re-experiencing

引用

ISCIENCE 2022年第1期25卷 103584页

作者： Iriye, Heather Ehrsson, H. Henrik Karolinska Inst Dept Neurosci S-17177 Stockholm Sweden

Our bodies provide a necessary scaffold for memories of past events. Yet, we are just beginning to understand how feelings of one's own body during the encoding of realistic events shape memory. Participants formed memories for immersive, lifelike events by watching pre-recorded 3D videos that involved a first-person view of a mannequin's body through head mounted displays. We manipulated feelings of body ownership over the mannequin using a perceptual full-body illusion. Participants completed cued recall questions and subjective ratings (i.e., degree of reliving, emotional intensity, vividness, and belief in memory accuracy) for each video immediately following encoding and one week later. Sensing the mannequin's body as one's own during encoding enhanced the following factors: memory accuracy across testing points, immediate reliving, delayed emotional intensity, vividness, and belief in memory accuracy. These findings demonstrate that a basic sense of bodily selfhood provides a crucial foundation for the accurate reliving of the past.

关键词： memory structure Machine perception

来源：评论

学校读者我要写书评

暂无评论

An interesting reconfigurable optical signal processor architecture

An interesting reconfigurable optical signal processor archi...

引用

Conference on Active and Passive Optical Components for WDM Communications III

作者： Guha, D Max Planck Inst Informat D-66123 Saarbrucken Germany

This paper delves into the fundamentals of hardware-software partitioning between an intelligent, generalized signal processor and reconfigurable hardware. A novel architecture is proposed for a RADAR control system a... 详细信息

ISBN: (纸本)0819451290

关键词： Optical Signal Processor Architecture memory structure optical Data structure (ODS)

来源：评论

学校读者我要写书评

暂无评论

Leveraging Data Lifetime for Energy-Aware Last Level Non-Volatile SRAM Caches using Redundant Store Elimination 14

Leveraging Data Lifetime for Energy-Aware Last Level Non-Vol...

引用

51st ACM/EDAC/IEEE Design Automation Conference (DAC)

作者： Tsai, Hsiang-Jen Chen, Chien-Chih Yang, Keng-Hao Yang, Ting-Chin Huang, Li-Yue Chung, Ching-Hao Chang, Meng-Fan Chen, Tien-Fu Natl Chiao Tung Univ Dept CS Hsinchu Taiwan Natl Tsing Hua Univ Dept EE Hsinchu Taiwan

ISBN: (纸本)9781450327305

NVM has commonly been used to address increasingly large last-level caches (LLCs) requirements by reducing leakage. However, frequent data-writing operations result in increased energy consumption. In this context, a promising memory technology, Non-volatile SRAM (nvSRAM), enables normal and standby operation modes which can be used to store various types of data. However, nvSRAM suffers from high dynamic energy usage due to frequent switching between operation modes. In this paper, we propose a redundant store elimination (RSE) scheme which, on average, discards 94% of needless bit-write operations. Moreover, we present a retention-aware cache management policy to reduce data updates of cache blocks, based on the correlation between data lifetime and cache types. Experimental results demonstrate that our proposal can improve energy consumption of SRAM-based and RRAM-based LLCs by 57% and 31%, respectively.

关键词： Non-volatile SRAM Redundant store elimination Energy reduction On-chip cache architecture memory structure Non-volatile memory Multi-core

来源：评论

学校读者我要写书评

暂无评论

Intel :: Databooks :: 1996 Networking

引用

2016年

[Auto Generated] PENTIUM AND PENTIUM PRO PROCESSORS AND RELATED PRODUCTS PERIPHERAL COMPONENTS ADDITIONAL LITERATURE: (Not included in handbook set) AUTOMOTIVE ,PRODUCTS COMPONENTS QUALITY/RELIABILITY EMBEDDED APPLICATIONS (1995/96) MILITARY SYSTEMS QUALITY/RELIABILITY Intel Order Number 231003 270646 272396 210830 272084 297360 280407 240800 241732 296467 231792 210997 270648 210461 231762 ISBN N/A 1-55512-248-5 1-55512-249-3 1-55512-250-7 1-55512-252-3 1-55512-256-6 1-55512-253-1 1-55512-254-X

关键词： address big endian byte command data data field databooks frame hold time intel interface local memory memory memory structure min max networking receive receive buffer receive frame setup time symbol parameter transmit

来源：评论

学校读者我要写书评

暂无评论

From action representation to action execution: exploring the links between cognitive and biomechanical levels of motor control

引用

FRONTIERS IN COMPUTATIONAL NEUROSCIENCE 2013年第SEP期7卷 127页

作者： Land, William M. Volchenkov, Dima Blaesing, Bettina E. Schack, Thomas Univ Bielefeld Dept Neurocognit & Act Biomech D-33501 Bielefeld Germany Univ Bielefeld Res Inst Cognit & Robot CoR Lab D-33501 Bielefeld Germany Univ Bielefeld Cognit Interact Technol Ctr Excellence CITEC D-33501 Bielefeld Germany Univ Bielefeld Dept Phys D-33501 Bielefeld Germany

Along with superior performance, research indicates that expertise is associated with a number of mediating cognitive adaptations. To this extent, extensive practice is associated with the development of general and task-specific mental representations, which play an important role in the organization and control of action. Recently, new experimental methods have been developed, which allow for investigating the organization and structure of these representations, along with the functional structure of the movement kinematics. In the current article, we present a new approach for examining the overlap between skill representations and motor output. In doing so, we first present an architecture model, which addresses links between biomechanical and cognitive levels of motor control. Next, we review the state of the art in assessing memory structures underlying complex action. Following we present a new spatio-temporal decomposition method for illuminating the functional structure of movement kinematics, and finally, we apply these methods to investigate the overlap between the structure of motor representations in memory and their corresponding kinematic structures. Our aim is to understand the extent to which the output at a kinematic level is governed by representations at a cognitive level of motor control.

关键词： mental representation basic action concepts kinematic structure spatio-temporal kinematic decomposition of movement structure dimensional analysis-motorics hierarchical motor control memory structure

来源：评论

学校读者我要写书评

暂无评论

Emerging Materials for Neuromorphic Devices and Systems

引用

ISCIENCE 2020年第12期23卷 101846页

作者： Kim, Min-Kyu Park, Youngjun Kim, Ik-Jyae Lee, Jang-Sik Pohang Univ Sci & Technol POSTECH Dept Mat Sci & Engn Pohang 37673 South Korea

Neuromorphic devices and systems have attracted attention as next-generation computing due to their high efficiency in processing complex data. So far, they have been demonstrated using both machine-learning software and complementary metal-oxide-semiconductor-based hardware. However, these approaches have drawbacks in power consumption and learning speed. An energy-efficient neuromorphic computing system requires hardware that can mimic the functions of a brain. Therefore, various materials have been introduced for the development of neuromorphic devices. Here, recent advances in neuromorphic devices are reviewed. First, the functions of biological synapses and neurons are discussed. Also, deep neural networks and spiking neural networks are described. Then, the operation mechanism and the neuromorphic functions of emerging devices are reviewed. Finally, the challenges and prospects for developing neuromorphic devices that use emerging materials are discussed.

关键词： Devices Electronic Materials Materials Design memory structure

来源：评论

学校读者我要写书评

暂无评论

Methodological Research on Low Power Design for Portable Mixedsignal IC

Methodological Research on Low Power Design for Portable Mix...

引用

2017 International Conference on Advances in Materials,Machinery,Electrical Engineering(AMMEE 2017)

作者： Shuirong Ju Xifeng Liu Tianshe Wang Jing Shi Jiangsu College of Information Technology

Block diagram of digital part for portable IC is given. Three ways to reduce the power consumption of digital circuit are introduced. Several circuit modules of analog part for the portable IC are listed, and low powe... 详细信息

ISBN: (纸本)9781510842915

关键词： Low Power STOP mode memory structure Voltage Reference Oscillator

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：