检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Mishani, Itamar Feddock, Hayden Likhachev, Maxim The Robotics Institute School of Computer Science Carnegie Mellon University PittsburghPA United States Electrical and Computer Engineering Department Pittsburgh University United States

Robotic manipulators are essential for future autonomous systems, yet limited trust in their autonomy has confined them to rigid, task-specific systems. The intricate configuration space of manipulators, coupled with the challenges of obstacle avoidance and constraint satisfaction, often makes motion planning the bottleneck for achieving reliable and adaptable autonomy. Recently, a class of constant-time motion planners (CTMP) was introduced. These planners employ a preprocessing phase to compute data structures that enable online planning provably guarantee the ability to generate motion plans, potentially sub-optimal, within a user defined time bound. This framework has been demonstrated to be effective in a number of time-critical tasks. However, robotic systems often have more time allotted for planning than the online portion of CTMP requires, time that can be used to improve the solution. To this end, we propose an anytime refinement approach that works in combination with CTMP algorithms. Our proposed framework, as it operates as a constant time algorithm, rapidly generates an initial solution within a user-defined time threshold. Furthermore, functioning as an anytime algorithm, it iteratively refines the solution's quality within the allocated time budget. This enables our approach to strike a balance between guaranteed fast plan generation and the pursuit of optimization over time. We support our approach by elucidating its analytical properties, showing the convergence of the anytime component towards optimal solutions. Additionally, we provide empirical validation through simulation and real-world demonstrations on a 6 degree-of-freedom robot manipulator, applied to an assembly domain. Copyright © 2023, The Authors. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

AV Navigation in 3D Urban Environments with Curriculum-based Deep Reinforcement Learning

AV Navigation in 3D Urban Environments with Curriculum-based...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Kevin Braathen de Carvalho Iure Rosa L. de Oliveira Alexandre S. Brandão Department of Electrical Engineering Graduate Program in Computer Science Nucleus of Specialization in Robotics Universidade Federal de Viçosa Viçosa MG Brazil Department of Electrical Engineering Federal University of Viçosa Viçosa MG Brazil

Unmanned Aerial Vehicles (UAVs) are widely used in various applications, from inspection and surveillance to transportation and delivery. Navigating UAVs in complex 3D environments is a challenging task that requires robust and efficient decision-making algorithms. This paper presents a novel approach to UAV navigation in 3D environments using a Curriculum-based Deep Reinforcement Learning (DRL) approach. The proposed method utilizes a deep neural network to model the UAV’s decision-making process and to learn a mapping from the state space to the action space. The learning process is guided by a reinforcement signal that reflects the performance of the UAV in terms of reaching its target while avoiding obstacles and with energy efficiency. Simulation results show that the proposed method has a positive trade off when compared to the baseline algorithm. The proposed method was able to perform well in environments with a state space size of 22 millions, allowing the usage in big environments or in maps with high resolution. The results demonstrate the potential of DRL for enabling UAVs to operate effectively in complex environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras

arXiv

引用

arXiv 2024年

作者： Niu, Junkai Zhong, Sheng Lu, Xiuyuan Shen, Shaojie Gallego, Guillermo Zhou, Yi School of Robotics Hunan University Changsha China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong TU Berlin The Science of Intelligence Excellence Cluster The Robotics Institute Germany Einstein Center Digital Future Berlin Germany

Event-based visual odometry is a specific branch of visual Simultaneous Localization and Mapping (SLAM) techniques, which aims at solving tracking and mapping sub-problems (typically in parallel), by exploiting the special working principles of neuromorphic (i.e., event-based) cameras. Due to the motion-dependent nature of event data, explicit data association (i.e., feature matching) under large-baseline viewpoint changes is difficult to establish, making direct methods a more rational choice. However, state-of-the-art direct methods are limited by the high computational complexity of the mapping sub-problem and the degeneracy of camera pose tracking in certain degrees of freedom (DoF) in rotation. In this paper, we tackle these issues by building an event-based stereo visual-inertial odometry system on top of a direct pipeline [1]. Specifically, to speed up the mapping operation, we propose an efficient strategy for sampling contour points according to the local dynamics of events. The mapping performance is also improved in terms of structure completeness and local smoothness by merging the temporal stereo and static stereo results. To circumvent the degeneracy of camera pose tracking in recovering the pitch and yaw components of general 6-DoF motion, we introduce IMU measurements as motion priors via pre-integration. To this end, a compact back-end is proposed for continuously updating the IMU bias and predicting the linear velocity, enabling an accurate motion prediction for camera pose tracking. The resulting system scales well with modern high-resolution event cameras and leads to better global positioning accuracy in large-scale outdoor environments. Extensive evaluations on five publicly available datasets featuring different resolutions and scenarios justify the superior performance of the proposed system against five state-of-the-art methods. Compared to ESVO [1], our new pipeline significantly reduces the camera pose tracking error by 40%–80% and 20%—80%

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Distance-based Formation-Motion Control for Unicycle Agents

Distance-based Formation-Motion Control for Unicycle Agents

引用

American Control Conference (ACC)

作者： Jin Chen Bayu Jayawardhana Hector Garcia de Marina Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen The Netherlands Department of Computer Engineer Automation and Robotics and With CITIC The University of Granada Spain

We present a distance-based distributed formation-motion control law for unicycle agents that are required to move together at a constant reference speed. The distributed control law consists of the standard distance-based formation gradient control law, which is projected to the longitudinal and angular velocity inputs of the unicycle, and of a linear term that depends on the reference speed. The main contribution of this paper is to realize the consistency of unicycle agents’ orientations without orientation measurement, thereby reducing the possibility of significant orientation measurement errors in real-world applications. We prove and show numerically the local exponential convergence of the unicycle agents to the desired formation, where they eventually move in unison at a constant reference speed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparison of Coherent and Incoherent Donut Beams for Deep Tissue STED Microscopy

Comparison of Coherent and Incoherent Donut Beams for Deep T...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Shanavas, Thariq McLeod, Robert R. Siemens, Mark E. Gopinath, Juliet T. Department of Physics University of Colorado BoulderCO80309 United States Department of Electrical Computer and Energy Engineering University of Colorado BoulderCO80309 United States Department of Physics University of Denver DenverCO80204 United States Materials Science Engineering Program University of Colorado BoulderCO80309 United States

We numerically compare the null quality for STED microscopy generated by Laguerre-Gaussian beams with orbital angular momentum and donut beams generated by incoherent addition of orthogonal Hermite Gaussian beams when... 详细信息

ISBN: (纸本)9781957171258

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

AirShot: Efficient Few-Shot Detection for Autonomous Exploration

AirShot: Efficient Few-Shot Detection for Autonomous Explora...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Zihan Wang Bowen Li Chen Wang Sebastian Scherer Institute for Imaging Data and Communications School of Engineering The University of Edinburgh UK AirLab Robotics Institute Carnegie Mellon University Pittsburgh PA USA Department of Computer Science and Engineering Spatial AI & Robotics (SAIR) Lab Institute for Artificial Intelligence and Data Science University at Buffalo NY USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Few-shot object detection has drawn increasing attention in the field of robotic exploration, where robots are required to find unseen objects with a few online provided examples. Despite recent efforts have been made to yield online processing capabilities, slow inference speeds of low-powered robots fail to meet the demands of real-time detection-making them impractical for autonomous exploration. Existing methods still face performance and efficiency challenges, mainly due to unreliable features and exhaustive class loops. In this work, we propose a new paradigm AirShot, and discover that, by fully exploiting the valuable correlation map, AirShot can result in a more robust and faster few-shot object detection system, which is more applicable to robotics community. The core module Top Prediction Filter (TPF) can operate on multi-scale correlation maps in both the training and inference stages. During training, TPF supervises the generation of a more representative correlation map, while during inference, it reduces looping iterations by selecting top-ranked classes, thus cutting down on computational costs with better performance. Surprisingly, this dual functionality exhibits general effectiveness and efficiency on various off-the-shelf models. Exhaustive experiments on COCO2017, VOC2014, and SubT datasets demonstrate that TPF can significantly boost the efficacy and efficiency of most off-the-shelf models, achieving up to 36.4% precision improvements along with 56.3% faster inference speed. Code and Data are at: https://***/ImNotPrepared/AirShot.

关键词： Training Correlation Codes Computational modeling Atmospheric modeling Object detection Real-time systems Computational efficiency Intelligent robots Faces

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Detecting and Predicting Knee Osteoarthritis Severity

Deep Learning Approaches for Detecting and Predicting Knee O...

引用

Recent Advances in Information Technology for Sustainable Development (ICRAIS), International Conference on

作者： Shilpa Karegoudra Veeresha R K Vamsidhar Yendapalli Department of Computer Science and Engineering NMAM Institute of Technology (NMAMIT) Nitte (Deemed to be University) Udupi India Department of Robotics and Artificial Intelligence NMAM Institute of Technology (NMAMIT) Nitte (Deemed to be University) Udupi India Department of Computer Science and Engineering GITAM School of Technology Bengaluru GITAM University Karnataka India

ISBN: (数字)9798350354461

ISBN: (纸本)9798350354522

Knee osteoarthritis stands as one of the most prevalent musculoskeletal ailments globally. Its initial signs include joint stiffness, discomfort, and limitations in functionality, marking it as a significant joint disorder. Older adults are more likely to have arthritis, and it normally gets worse with age. If there are no early, effective therapies used, it can lead to impairment in older people. Therapy must be started as soon as possible; otherwise, a full knee replacement may be necessary. The very subjective nature of the standard procedures creates a barrier to early illness progression detection. This study involves in-depth exploration and examination of the application of deep learning techniques for knee osteoarthritis detection and severity prediction. In this work EfficientNet-B6 was chosen for its superior performance in balancing accuracy, speed, and resource efficiency. Unlike models such as MobileNet or ResNet, X-ray images are used to train the model to predict the severity of knee osteoarthritis. The model classifies the data with an accuracy of 87%. A website for OA prediction is developed, the user needs to drag and drop an X-ray image in the dialog box given. The predicted output along with the severity will be shown within a few seconds. This website is very easy to use.

关键词： Deep learning Accuracy Medical treatment Predictive models Planning Osteoarthritis Sustainable development Older adults X-ray imaging Standards

来源：评论

学校读者我要写书评

暂无评论

Neurocognitive assessment under various human-robot teaming environments

Neurocognitive assessment under various human-robot teaming ...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Anna L. Packy Jayesh Jayahankar Arya Teymourlouei Joshua Stone Hyuk Oh Garrett E. Katz James A. Reggia Rodolphe J. Gentili Neuroscience and Cognitive Science Program University of Maryland College Park USA Department of Computer Science University of Maryland College Park USA Department of Electrical & Computer Engineering University of Maryland College Park USA Department of Kinesiology University of Maryland College Park USA Department of Electrical Engineering & Computer Science Syracuse University Syracuse USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Human-robot teaming has become increasingly important with the advent of intelligent machines. Prior efforts suggest that performance, mental workload, and trust are critical elements of human-robot dynamics that can be altered by the robot’s behavior. Most prior human-robot teaming studies used behavioral analyses, but a limited number used neural markers, without the use of physical robots and complex tasks. Here we combine behavioral and EEG cortical dynamics to examine cognitive-motor processes when individuals complete a complex task under various team environments with a robot. The results revealed that altering the robot quality affected both behavioral and EEG dynamics. Task completion with an experienced robot led to greater team performance and human trust along with lower mental workload compared to an inexperienced teammate or when individuals performed alone. EEG changes suggest that different attentional processes were engaged when humans worked with the robot and performed alone, and that visual processing was more prominent when teaming with an inexperienced teammate. This work can inform human cognitive-motor processes and the design of robotic controllers in human-robot teams.

关键词： Visualization Process control Humanoid robots Collaboration Human factors Control systems Electroencephalography Behavioral sciences engineering in medicine and biology Robots

来源：评论

学校读者我要写书评

暂无评论

Intelligent Accident Recognition and Notification System using Hybrid Deep Learning and IoT

Intelligent Accident Recognition and Notification System usi...

引用

Soft Computing for Security Applications (ICSCSA), International Conference on

作者： P. Sathish Kumar Ramesh Singh Rawat Manish Shrimali Swapnil Parikh Harshal Patil Ramya Maranan Department of Robotics & Automation United Institute of Technology Coimbatore Tamil Nadu India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Computer Science and IT Janardan Rai Nagar Rajasthan Vidyapeeth (Deemed to be University) Udaipur Rajasthan India Department of Computer Science and Engineering Parul Institute of Engineering and Technology Parul University Gujarat India Computer Science and Engineering Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune Maharashtra India Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India

ISBN: (数字)9798331515720

ISBN: (纸本)9798331515737

Ensuring the safety of individuals should be a top priority. Everyone wants to return home safely. Many riders continue to disregard safety constraints, increasing the chance of accidents that result in death. It is critical to incorporate the latest technology into road monitoring systems to make cities smarter and to ensure rider safety. For this research, Deep Learning (DL) and the Internet of Things (IoT) were chosen for effective road surveillance and alert systems. The primary goal of the study is to detect and inform riders about accidents that occur along their path and to provide details about the location of the detected accident. Additionally, the system provides the vehicle's speed. To identify automobile accidents in the footage, a hybrid DL model that includes Convolutional Neural Network - Bidirectional Long Short-Term Memory (CNN-Bi-LSTM) is suggested. For the model's training, both accident and non-accident data were collected. The model is evaluated using three metrics: accuracy, loss, and execution time. The next step is to upload the recommended model to the ThingSpeak cloud. A Graphical User Interface (GUI) is being created in the ThingSpeak cloud. The GUI displays the vehicle's speed, accident images, and the precise location of the accident scene using the Raspberry Pi, speed sensor, Pi-camera, and Global Positioning System (GPS) module. An LED is also integrated into the GUI to alert the user. A real-world test is conducted on the designed system. The proposed solution has many advantages and will ensure driver safety.

关键词： Deep learning Training Cloud computing Accuracy Roads Surveillance Feature extraction Safety Accidents Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Tracking the Dynamic Neural Connectivity via Conjugate Gradient Optimization*

Tracking the Dynamic Neural Connectivity via Conjugate Gradi...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Mingdong Li Shuhang Chen Zhijia Zhao Yiwen Wang Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology (Guangzhou) Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology School of Mechanical and Electrical Engineering Guangzhou University Department of Electronic and Computer Engineering The Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology

Neural connectivity describes how neuron populations coordinate and create cognitive and behavioral functions. Neural connectivity performs dynamics where its population spiking responses to stimuli or intention change over time. Brain-machine interface (BMI) provides a framework for studying dynamical neural connectivity. In BMI, point process is a powerful technique in analyzing the single neuronal tuning. And generalized linear mode (GLM) as an encoding model can incorporate the tuning in kinematics and the neural connectivity. Quantification and tracking of dynamic neural connectivity can contribute to the elucidation of the generation of brain functions in a computational way. However, most of the previous work focused on single neuronal adaptation to kinematics. When a neuron is significantly modulated by some other neurons in some tasks, the shape of the log likelihood function for single neuronal observations can be narrowed in some dimensions. And the existing gradient-based methods are not able to reach the optimum in a fast and adaptive searching way. In this work, to maximize the likelihood of observations and obtain the dynamic neural connectivity tuning parameters, we proposed a conjugate gradient-based encoding model (CGE). We illustrate CGE for likelihood function using the real experimental data under manual control and brain control. The results show that the proposed CGE has better performance in tracking the dynamic neural connectivity tuning parameters and modeling neural *** Relevance— Not directly related.

关键词：

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：