检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Guo, Sicen Li, Jiahang Feng, Yi Zhou, Dacheng Zhang, Denghuang Chen, Chen Su, Shuai Zhu, Xingyi Chen, Qijun Fan, Rui Group The College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China The Department of Control Science & Engineering Tongji University Shanghai201804 China The College of Electronics & Information Engineering Tongji University Shanghai201804 China The Department of Road & Airport Engineering The Key Laboratory of Road & Traffic Engineering of Ministry of Education Tongji University Shanghai200092 China

In the nascent domain of urban digital twins (UDT), the prospects for leveraging cutting-edge deep learning techniques are vast and compelling. Particularly within the specialized area of intelligent road inspection (IRI), a noticeable gap exists, underscored by the current dearth of dedicated research efforts and the lack of large-scale well-annotated datasets. To foster advancements in this burgeoning field, we have launched an online open-source benchmark suite, referred to as UDTIRI. Along with this article, we introduce the road pothole detection task, the first online competition published within this benchmark suite. This task provides a well-annotated dataset, comprising 1,000 RGB images and their pixel/instance-level ground-truth annotations, captured in diverse real-world scenarios under different illumination and weather conditions. Our benchmark provides a systematic and thorough evaluation of state-of-the-art object detection, semantic segmentation, and instance segmentation networks, developed based on either convolutional neural networks or Transformers. We anticipate that our benchmark will serve as a catalyst for the integration of advanced UDT techniques into IRI. By providing algorithms with a more comprehensive understanding of diverse road conditions, we seek to unlock their untapped potential and foster innovation in this critical domain. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Polynomial-Based Linear Programming Relaxation of Sensor Network Localization Problem 12

Polynomial-Based Linear Programming Relaxation of Sensor Net...

引用

12th International Conference on Information Technology and Electrical engineering, ICITEE 2020

作者： Tamba, Tua A. Nazaruddin, Yul Y. Parahyangan Catholic University Center for Control Automation Systems Engineering Department of Electrical Engineering Bandung Indonesia Institut Teknologi Bandung Instrumentation Control Research Group Indonesia

ISBN: (纸本)9781728110974

One important task in the deployment of a wireless sensor network is solving the sensor network localization problem to assure location awareness of each sensor node in the network. The sensor network localization can be formulated as a global optimization problem that aims to minimize the squared inter-sensor distances under the constraint that such distances equal to some given numbers. The corresponding optimization formulation is generally nonsmooth, nonconvex, and NP-hard problem, and thus prior works have proposed approximate solution using relaxation methods such as semidefinite or conic programming. In this paper, a linear programming relaxation approach is proposed to solve such an optimization problem using the concept of Handelman's representation of nonnegative polynomial functions over polytopic set. Numerical simulation results are given to illustrate the promising potential of the proposed approach. © 2020 IEEE.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

Discretization of the Super-Twisting Algorithm Using Variational Integrators

Discretization of the Super-Twisting Algorithm Using Variati...

引用

IEEE Conference on Decision and control

作者： Florian Weissenberger Lars Watermann Stefan Koch Markus Reichhartinger Christina Hettiger Lukas Eisenzopf Kiran Kumari Johann Reger Martin Horn Control Engineering Group Technische Universit¨at Ilmenau Ilmenau Germany Christian Doppler Laboratory for Model-Based Control of Complex Test Bed Systems Institute of Automation and Control Graz University of Technology Graz Austria Institute of Automation and Control Graz University of Technology Graz Austria

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

In this paper, a new framework for the discretization of the super-twisting algorithm is developed. The proposed discretization scheme is not based on the underlying differential equations, but uses the variational formulation of the problem. Discrete-time versions derived in the proposed fashion exhibit a great tracking of the continuous-time energy decay rate and give a good approximation of the continuous-time system. Furthermore, the paper presents a stability proof for an exemplary algorithm, a semi-implicit version of the super-twisting algorithm derived by using variational integrators.

关键词： Asymptotic stability Computational modeling Differential equations Approximation algorithms Stability analysis Trajectory Noise measurement

来源：评论

学校读者我要写书评

暂无评论

NARX Identification using Derivative-Based Regularized Neural Networks

NARX Identification using Derivative-Based Regularized Neura...

引用

IEEE Conference on Decision and control

作者： L.H. Peeters G.I. Beintema M. Forgione M. Schoukens Department of Electrical Engineering Control Systems group Eindhoven University of Technology The Netherlands IDSIA Dalle Molle Institute for Artificial Intelligence USI-SUPSI Lugano-Viganello Switzerland

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

This work presents a novel regularization method for the identification of Nonlinear Autoregressive eXogenous (NARX) models. The regularization method promotes the exponential decay of the influence of past input samples on the current model output. This is done by penalizing the sensitivity of the NARX model simulated output with respect to the past inputs. This promotes the stability of the estimated models and improves the obtained model quality. The effectiveness of the approach is demonstrated through a simulation example, where a neural network NARX model is identified with this novel method. Moreover, it is shown that the proposed regularization approach improves the model accuracy in terms of simulation error performance compared to that of other regularization methods and model classes.

关键词： Training Sensitivity Neural networks Estimation Stability analysis

来源：评论

学校读者我要写书评

暂无评论

NARX Identification using Derivative-Based Regularized Neural Networks

arXiv

引用

arXiv 2022年

作者： Peeters, L.H. Beintema, G.I. Forgione, M. Schoukens, Maarten Control Systems Group Department of Electrical Engineering Eindhoven University of Technology Netherlands IDSIA Dalle Molle Institute for Artificial Intelligence USI-SUPSI Lugano-Viganello Switzerland

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Safe Reinforcement Learning via Confidence-Based Filters

arXiv

引用

arXiv 2022年

作者： Curi, Sebastian Lederer, Armin Hirche, Sandra Krause, Andreas Learning & Adaptive Systems Group Department of Computer Science ETH Zurich Switzerland Information-oriented Control Department of Electrical and Computer Engineering Technical University of Munich Germany

— Ensuring safety is a crucial challenge when deploying reinforcement learning (RL) to real-world systems. We develop confidence-based safety filters, a control-theoretic approach for certifying state safety constraints for nominal policies learnt via standard RL techniques, based on probabilistic dynamics models. Our approach is based on a reformulation of state constraints in terms of cost functions, reducing safety verification to a standard RL task. By exploiting the concept of hallucinating inputs, we extend this formulation to determine a "backup" policy which is safe for the unknown system with high probability. Finally, the nominal policy is minimally adjusted at every time step during a roll-out towards the backup policy, such that safe recovery can be guaranteed afterwards. We provide formal safety guarantees, and empirically demonstrate the effectiveness of our approach. © 2022, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Towards 6D MCL for LiDARs in 3D TSDF Maps on Embedded systems with GPUs

arXiv

引用

arXiv 2023年

作者： Eisoldt, Marc Mock, Alexander Porrmann, Mario Wiemann, Thomas Computer Engineering Group Osnabrück University Osnabrück Germany Knowledge-based Systems Group Osnabrück University Osnabrück Germany Robotics in Computer Science Fulda University of Applied Sciences Fulda Germany DFKI Niedersachsen Plan-based Robot Control Osnabrück Germany

Monte Carlo Localization is a widely used approach in the field of mobile robotics. While this problem has been well studied in the 2D case, global localization in 3D maps with six degrees of freedom has so far been too computationally demanding. Hence, no mobile robot system has yet been presented in literature that is able to solve it in real-time. The computationally most intensive step is the evaluation of the sensor model, but it also offers high parallelization potential. This work investigates the massive parallelization of the evaluation of particles in truncated signed distance fields for three-dimensional laser scanners on embedded GPUs. The implementation on the GPU is 30 times as fast and more than 50 times more energy efficient compared to a CPU implementation. Copyright © 2023, The Authors. All rights reserved.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Tailored neural networks for learning optimal value functions in MPC

arXiv

引用

arXiv 2021年

作者： Teichrib, Dieter Darup, Moritz Schulze Control and Cyber-physical Systems Group Faculty of Mechanical Engineering TU Dortmund University Germany

Learning-based predictive control is a promising alternative to optimization-based MPC. However, efficiently learning the optimal control policy, the optimal value function, or the Q-function requires suitable function approximators. Often, artificial neural networks (ANN) are considered but choosing a suitable topology is also non-trivial. Against this background, it has recently been shown that tailored ANN allow, in principle, to exactly describe the optimal control policy in linear MPC by exploiting its piecewise affine structure. In this paper, we provide a similar result for representing the optimal value function and the Q-function that are both known to be piecewise quadratic for linear MPC. © 2021, CC BY-NC-ND.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid Unmanned Aerial Underwater Vehicles: A Survey on Concepts and Technologies

SSRN

引用

SSRN 2023年

作者： Pinheiro, Pedro Miranda Dias de Oliveira Evald, Paulo Jefferson Grando, Ricardo Bedin Neto, Armando Alves Jorge Drews, Paulo Lilles Intelligent Robotics and Automation Group Federal University of Rio Grande Rio Grande Brazil Intelligent Systems and Control Group Federal University of Pelotas Pelotas Brazil Department of Robotics Technological University of Uruguay Rivera Uruguay Department of Electronic Engineering Federal University of Minas Gerais Belo Horizonte Brazil

Hybrid Unmanned Aerial Underwater Vehicle (HUAUV) is a class of multi-modal mobile robots characterized by the ability to fly and navigate underwater, as well as being able to perform the transition between both environments. The development of modern vehicles of this class is driven by the enhancement of mobile robotic systems, sensors, and control techniques. However, the class definition and hierarchy for these vehicles are still vague and undefined. Therefore, this work presents a survey of concepts and prototypes of HUAUVs, developed from 2010 until 2022. The search for works was performed in relevant international conference proceedings and journals. We present a classification of state-of-the-art concepts and prototypes of HUAUVs based on specific main features of vehicles, allowing the identification of trends in HUAUV development, and an actuator-based taxonomy for HUAUVs. Hence, our categorization provides a more cohesive background for future works, as well as a better understanding of the main features of hybrid vehicles. Finally, a pragmatic approach to future applications is provided, given the current trends in Mobile Robotics, focusing on unmanned aerial/underwater vehicles. © 2023, The Authors. All rights reserved.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Towards 6D MCL for LiDARs in 3D TSDF Maps on Embedded systems with GPUs

Towards 6D MCL for LiDARs in 3D TSDF Maps on Embedded System...

引用

IEEE International Conference on Robotic Computing (IRC)

作者： Marc Eisoldt Alexander Mock Mario Porrmann Thomas Wiemann Computer Engineering Group Osnabrück University Osnabrück Germany Knowledge-based Systems Group Osnabrück University Osnabrück Germany Robotics in Computer Science Fulda University of Applied Sciences Fulda Germany DFKI Niedersachsen Plan-based Robot Control Osnabrück Germany

Monte Carlo Localization is a widely used approach in the field of mobile robotics. While this problem has been well studied in the 2D case, global localization in 3D maps with six degrees of freedom has so far been too computationally demanding. Hence, no mobile robot system has yet been presented in the literature that is able to solve it in realtime. The computationally most intensive step is the evaluation of the sensor model, but it also offers high parallelization potential. This work investigates the massive parallelization of the evaluation of particles in truncated signed distance fields for three-dimensional laser scanners on embedded GPUs. The implementation on the GPU is 30 times as fast and more than 50 times more energy efficient compared to a CPU implementation.

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：