检索结果-内蒙古大学图书馆

Achievable fixed rate capacity in emerging wireless systems (invited paper) 2

学校读者我要写书评

暂无评论

Achievable fixed rate capacity in emerging wireless systems ...

2nd International Conference on Advanced Communication Technologies and Networking, CommNet 2019

作者： Sofotasios, Paschalis C. Yoo, Seong Ki Muhaidat, Sami Cotton, Simon L. Lopez-Martinez, F. Javier Romero-Jerez, Juan M. Mezher, Kahtan Karagiannidis, George K. Department of Electrical Engineering Tampere University TampereFI-33101 Finland UQeen's University Belfast Institute of Electronics Communications and Information Technology BelfastBT3 9DT United Kingdom University of Surrey Institute for Communication Systems GuildfordGU2 7XH United Kingdom Departmento de Ingenieria de Comunicaciones Universidad de Malaga Campus de Excelencia Internacional Andalucia Tech. Malaga29071 Spain Department of Electrical Engineering and Computer Science Khalifa University Center for Cyber-Physical Systems Abu Dhabi127788 United Arab Emirates Department of Electrical and Computer Engineering Aristotle University of Thessaloniki ThessalonikiGR-51124 Greece

ISBN: (纸本)9781538683170

The F composite fading model was recently proposed as an accurate and tractable statistical model for the characterization of the simultaneous occurrence of multipath fading and shadowing conditions encountered in realistic wireless communication scenarios. In the present contribution we capitalize on the distinct properties of this composite model to derive the achievable capacity over F composite fading channels assuming fixed rate quality of service requirements. To this end, novel exact and tractable analytic expressions are derived for both the exact and the truncated channel inversion strategies. This also enables the derivation of additional simplified approximate and asymptotic expressions for these cases, which provide meaningful insights on the effect of fading conditions on the overall system performance. This is particularly useful in the context of numerous emerging wireless applications of interest that exhibit stringent fixed rate requirements such as vehicular communications, body area networks and telemedicine, among others. © 2019 IEEE.

关键词： Quality of service

Model-Free Non-Stationary RL: Near-Optimal Regret and Applications in Multi-Agent RL and Inventory Control

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Mao, Weichao Zhang, Kaiqing Zhu, Ruihao Simchi-Levi, David Başar, Tamer Department of Electrical and Computer Engineering Coordinated Science Laboratory University of Illinois Urbana-Champaign UrbanaIL61801 United States Laboratory for Information & Decision Systems Massachusetts Institute of Technology CambridgeMA02139 United States Cornell SC Johnson College of Business IthacaNY14853 United States Institute for Data Systems and Society Department of Civil and Environmental Engineering Operations Research Center Massachusetts Institute of Technology CambridgeMA02139 United States

We consider model-free reinforcement learning (RL) in non-stationary Markov decision processes. Both the reward functions and the state transition functions are allowed to vary arbitrarily over time as long as their cumulative variations do not exceed certain variation budgets. We propose Restarted Q-Learning with Upper Confidence Bounds (RestartQ-UCB), the first model-free algorithm for non-stationary RL, and show that it outperforms existing solutions in terms of dynamic regret. Specifically, RestartQ-UCB with Freedman-type bonus terms achieves a dynamic regret bound of (formula presented ), where S and A are the numbers of states and actions, respectively, ∆ > 0 is the variation budget, H is the number of time steps per episode, and T is the total number of time steps. We further present a parameter-free algorithm named Double-Restart Q-UCB that does not require prior knowledge of the variation budget. We show that our algorithms are nearly optimal by establishing an information-theoretical lower bound of (formula presented ), the first lower bound in non-stationary RL. Numerical experiments validate the advantages of RestartQ-UCB in terms of both cumulative rewards and computational efficiency. We demonstrate the power of our results in examples of multi-agent RL and inventory control across related products. Copyright © 2020, The Authors. All rights reserved.

关键词： Reinforcement learning

Re-Identification With Consistent Attentive Siamese Networks

学校读者我要写书评

暂无评论

Re-Identification With Consistent Attentive Siamese Networks

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Meng Zheng Srikrishna Karanam Ziyan Wu Richard J. Radke Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Troy NY Siemens Corporate Technology Princeton NJ

ISBN: (纸本)9781728132945

We propose a new deep architecture for person re-identification (re-id). While re-id has seen much recent progress, spatial localization and view-invariant representation learning for robust cross-view matching remain key, unsolved problems. We address these questions by means of a new attention-driven Siamese learning architecture, called the Consistent Attentive Siamese Network. Our key innovations compared to existing, competing methods include (a) a flexible framework design that produces attention with only identity labels as supervision, (b) explicit mechanisms to enforce attention consistency among images of the same person, and (c) a new Siamese framework that integrates attention and attention consistency, producing principled supervisory signals as well as the first mechanism that can explain the reasoning behind the Siamese framework's predictions. We conduct extensive evaluations on the CUHK03-NP, DukeMTMC-ReID, and Market-1501 datasets and report competitive performance.

关键词： siamese elastic frame Reasoning

Real-time Detection, Tracking, and Classification of Moving and Stationary Objects using Multiple Fisheye Images

学校读者我要写书评

暂无评论

Real-time Detection, Tracking, and Classification of Moving ...

2018 IEEE Intelligent Vehicles Symposium, IV 2018

作者： Baek, Iljoo Davies, Albert Yan, Geng Rajkumar, Ragunathan Raj Department of Electrical and Computer Engineering Carnegie Mellon University PittsburghPA15213 United States Robotics Institute Carnegie Mellon University PittsburghPA15213 United States Department of Electrical and Computer Engineering Robotics Institute Carnegie Mellon University PittsburghPA15213 United States

ISBN: (纸本)9781538644522

The ability to detect pedestrians and other moving objects is crucial for an autonomous vehicle. This must be done in real-time with minimum system overhead. This paper discusses the implementationof a surround view system to identify moving as well as static objects that are close to the ego vehicle. The algorithm works on 4 views captured by fisheye cameras which are merged into a single frame. The moving object detection and tracking solution uses minimal system overhead to isolate regions of interest (ROIs) containing moving objects. These ROIs are then analyzed using a deep neural network (DNN) to categorize the moving object. With deployment and testing on a real car in urban environments, we have demonstrated the practical feasibility of the solution.11The video demos of our algorithm have been uploaded to Youtube: https://***/vpoCfC724iA, https://***/2X4aqH2bMBs. © 2018 IEEE.

关键词： Deep neural networks

RGB-to-TSDF: Direct TSDF Prediction from a Single RGB Image for Dense 3D Reconstruction

学校读者我要写书评

暂无评论

RGB-to-TSDF: Direct TSDF Prediction from a Single RGB Image ...

2019 IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Hanjun Kim Jiyoun Moon Beomhee Lee Department of Electrical and Computer Engineering Automation and Systems Research Institute (ASRI) Seoul National University Seoul Republic of Korea

In this paper, we present a novel method to predict 3D TSDF voxels from a single image for dense 3D reconstruction. 3D reconstruction with RGB images has two inherent problems: scale ambiguity and sparse reconstruction. With the advent of deep learning, depth prediction from a single RGB image has addressed these problems. However, as the predicted depth is typically noisy, de-noising methods such as TSDF fusion should be adapted for the accurate scene reconstruction. To integrate the two-step processing of depth prediction and TSDF generation, we design an RGB-to-TSDF network to directly predict 3D TSDF voxels from a single RGB image. The TSDF using our network can be generated more efficiently in terms of time and accuracy than the TSDF converted from depth prediction. We also use the predicted TSDF for a more accurate and robust camera pose estimation to complete scene reconstruction. The global TSDF is updated from TSDF prediction and pose estimation, and thus dense isosurface can be extracted. In the experiments, we evaluate our TSDF prediction and camera pose estimation results against the conventional method.

关键词：

Event-triggered add-on safety for connected and automated vehicles using road-side network infrastructure

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Mamduhi, Mohammad H. Hashemi, Ehsan Baras, John S. Johansson, Karl H. Division of Decision and Control Systems School of Electrical Engineering and Computer Science Royal Institute of Technology Stockholm10044 Sweden Mechanical and Mechatronics Engineering Department University of Waterloo ON Canada Institute of Systems Research Department of Electrical and Computer Engineering University of Maryland College ParkMD20742 United States

This paper proposes an event-triggered add-on safety mechanism to adjust the control parameters for timely braking in a networked vehicular system while maintaining maneuverability. Passenger vehicle maneuverability is significantly affected by the combined-slip friction effect, in which larger longitudinal tire slips result in considerable drop in lateral tire forces. This is of higher importance when unexpected dangerous situations occur on the road and immediate actions, such as braking, need to be taken to avoid collision. Harsh braking can lead to high-slip and loss of maneuverability;hence, timely braking is essential to reduce high-slip scenarios. In addition to the vehicles own active safety systems, the proposed event-triggered add-on safety is activated upon being informed about dangers by the road-side infrastructure. The aim is to incorporate the add-on safety feature to adjust the automatic control parameters for smooth and timely braking such that a collision is avoided while vehicle's maneuverability is maintained. We study two different wireless technologies for communication between the infrastructure and the vehicles, the Long-Term Evolution (LTE) and the fifth generation (5G) schemes. The framework is validated through high-fidelity software simulations and the advantages of including the add-on feature to augment the safety margins for each communication technology is evaluated. Copyright © 2019, The Authors. All rights reserved.

关键词： 5G mobile communication systems

A hybrid compositional approach to optimal mission planning for multi-rotor UAVs using metric temporal logic

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Fiaz, Usman A. Baras, John S. Department of Electrical and Computer Engineering Institute for Systems Research University of Maryland College ParkMD20742 United States

— This paper investigates a hybrid compositional approach to optimal mission planning for multi-rotor Unmanned Aerial Vehicles (UAVs). We consider a time critical search and rescue scenario with two quadrotors in a constrained environment. Metric Temporal Logic (MTL) is used to formally describe the task specifications. In order to capture the various modes of UAV operation, we utilize a hybrid model for the system with linearized dynamics around different operating points. We divide the mission into several sub-tasks by exploiting the invariant nature of various task specifications i.e., the mutual independence of safety and timing constraints along the way, and the different modes (i,e., dynamics) of the robot. For each sub-task, we translate the MTL formulae into linear constraints, and solve the associated optimal control problem for desired path using a Mixed Integer Linear Program (MILP) solver. The complete path is constructed by the composition of individual optimal sub-paths. We show that the resulting trajectory satisfies the task specifications, and the proposed approach leads to significant reduction in computational complexity of the problem, making it possible to implement in real-time. Copyright © 2019, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

Quantitative Evaluation of Endoscopic SLAM Methods: EndoSLAM Dataset

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ozyoruk, Kutsev Bengisu Incetan, Kagan Coskun, Gulfize Gokceler, Guliz Irem Almalioglu, Yasin Mahmood, Faisal Durr, Nicholas J. Curto, Eva Perdigoto, Luis Oliveira, Marina Araujo, Helder Alexandrino, Henrique Gilbert, Hunter B. Turan, Mehmet Institute of Biomedical Engineering Bogazici University Computer Science Department University of Oxford Oxford United Kingdom Department of Pathology Harvard Medical School BostonMA United States Department of Biomedical Engineering Johns Hopkins University BaltimoreMD United States Institute for Systems and Robotics University of Coimbra Portugal Faculty of Medicine Clinical Academic Center of Coimbra University of Coimbra Coimbra Portugal Department of Mechanical and Industrial Engineering Louisiana State University Baton RougeLA United States

Deep learning techniques hold promise to improve dense topography reconstruction and pose estimation, as well as simultaneous localization and mapping (SLAM). However, currently available datasets do not support effective quantitative benchmarking. With this paper, we introduce a comprehensive endoscopic SLAM dataset containing both capsule and standard endoscopy recordings. A Panda robotic arm, two different commercially available high precision 3D scanners, two different commercially available capsule endoscopes with different camera properties and two different conventional endoscopy cameras were employed to collect data from eight ex-vivo porcine gastrointestinal (GI)-tract organs. In total, 35 sub-datasets are provided: 18 sub-datasets for colon, 12 sub-datasets for stomach and five sub-datasets for small intestine, while four of these contain polyp-mimicking elevations carried out by an expert gastroenterologist. To exemplify the use-case, SC-SfMLearner was comprehensively benchmarked. The codes and the link for the dataset are publicly available at https://***/CapsuleEndoscope/EndoSLAM. A video demonstrating the experimental setup and procedure is available at https://***/watch?v=G_LCe0aWWdQ. Copyright © 2020, The Authors. All rights reserved.

关键词： computer vision

Predictive Inverse Kinematics: optimizing Future Trajectory through Implicit Time Integration and Future Jacobian Estimation

学校读者我要写书评

暂无评论

Predictive Inverse Kinematics: optimizing Future Trajectory ...

2019 IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Ko Ayusawa Wael Suleiman Eiichi Yoshida CNRS-AIST JRL (Joint Robotics Laboratory) UMI13218/RL Intelligent Systems Research Institute National Institute of Advanced Industrial Science and Technology (IS-AIST) Japan Electrical and Computer Engineering Department Faculty of Engineering University of Sherbrooke Canada

This paper presents an inverse kinematics (IK) method which can control future velocities and accelerations for multi-body systems. The proposed IK method is formulated as a quadratic programing (QP) that optimizes future joint trajectories. The features of the proposed IK are: (1) the evaluation of accelerations at future time instances, (2) the trajectory representation that can implicitly integrate the time integral formula into QP, (3) the computation of future Jacobian matrices based on the comprehensive theory of differential kinematics proposed in our previous work. Those features enable a stable and fast IK computation while evaluating the future accelerations. We also conducted thorough numerical studies to show the efficiency of the proposed method.

关键词：