检索结果-内蒙古大学图书馆

2022 IEEE International Conference on systems, Man, and Cybernetics, SMC 2022

作者： Xu, Jiahua Lin, Yunhan Zhou, Haotian Min, Huasong Wuhan University of Science and Technology College of Computer Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan430065 China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan430081 China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Reinforcement Learning (RL), a method of learning skills through trial-and-error, has been successfully used in many robotics applications in recent years. We combine manipulation primitives (MPs), behavior trees (BTs), and reinforcement learning to propose an algorithm for peg-in-hole tasks, which speeds up the convergence of the RL model and enhance the adaptability of the dynamic environment. Manipulation primitives are used as actions for RL, which can reduce the gap between control instruction and robotic actions and speed up the convergence of the RL model. Behavior trees are used as robot behavior control, which makes robots can actively adapt to the changes in the environment. In experiments, RL-BT, from the combination of RL and BT, is designed for the peg-in-hole task in the Gazebo simulation environment by using UR5 as the actuator. The experiments are conducted on a simple peg and a complex multi-hole peg by three aspects, which include convergence speed verification experiment, adaptability of dynamic environment experiment, and algorithm robustness experiment. The experiment result proves that our RL-BT can speed up the convergence and adapt to the changes in the environment. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

PL-TD3: A Dynamic Path Planning Algorithm of Mobile Robot

PL-TD3: A Dynamic Path Planning Algorithm of Mobile Robot

引用

2022 IEEE International Conference on systems, Man, and Cybernetics, SMC 2022

作者： Tan, Yijian Lin, Yunhan Liu, Tong Min, Huasong Wuhan University of Science and Technology College of Computer Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan430065 China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan430081 China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

In this paper, Prioritized Experience Replay (PER) strategy and Long Short Term Memory (LSTM) neural network are introduced to the path planning process of mobile robots, which solves the problems of slow convergence and inaccurate perception of dynamic obstacles with the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm. We dubbed this new method as PL-TD3. Firstly, we improve the convergence speed of the algorithm by introducing PER strategy. Secondly, we use LSTM neural network to achieve the improvement of the algorithm for dynamic obstacle perception. In order to verify the method of this paper, we design static environment, dynamic environment and adaptability to dynamic experiments to compare and analyze the methods before and after improvement. The experimental results show that PL-TD3 outperforms TD3 in terms of execution time and execution path length in all environments. © 2022 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Multi-stage Objective Function Optimized Hand-Eye Self-calibration of Robot in Autonomous Environment 1

引用

17th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2022

作者： Liu, Kaibo Zheng, Wangli Min, Huasong Lin, Yunhan School of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Hubei Wuhan430065 China State Grid Electric Power Research Institute Jiangsu Nanjing211106 China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Hubei Wuhan430081 China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

In the application scenario of robot autonomous tasks, the robot needs to be able to complete calibration online and automatically to achieve self-maintenance, which differs from traditional robot hand-eye calibration in that the traditional robot hand-eye calibration requires a dedicated calibration board to assist offline completion. Aiming at the problem that the existing self-calibration methods cannot be optimized as a whole, which leads to low accuracy and instability of the solution, a multi-stage objective function optimization self-calibration algorithm is proposed, which describes the solution of hand-eye self-calibration as a minimization objective function problem involving multiple stages. An optimization method based on the minimization of re-projection error is designed to compensate for the results, which uses an efficient Oriented fast and rotated brief (ORB) feature extraction algorithm and introduces a scoring mechanism to retain more correct matching points in the feature matching stage. Two different types of experiments were designed to validate our method. One is a single camera dataset experiment, which shows that our method is more accurate and robust than the existing self-calibration method;the other is an application platform experiment, which verifies the feasibility and availability of our method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Efficient 2D Simulators for Deep-Reinforcement-Learning-based Training of Navigation Approaches

Efficient 2D Simulators for Deep-Reinforcement-Learning-base...

引用

International Conference on Ubiquitous Robots (UR)

作者： Huajian Zeng Linh Kästner Jens Lambrecht The Chair of Robotics Artificial Intelligence and Real-time Systems Technical University Munich (TUM) Germany The Chair of Industry Grade Networks and Clouds Faculty of Electrical Engineering and Computer Science Berlin Institute of Technology Berlin Germany

In recent years, Deep Reinforcement Learning (DRL) has emerged as a competitive approach for mobile robot navigation. However, training DRL agents often comes at the cost of difficult and tedious training procedures in which powerful hardware is required to conduct oftentimes long training runs. Especially, for complex environments, this proves to be a major bottleneck for widespread adoption of DRL approaches into industries. In this paper we integrate an efficient 2D simulator into the Arena-Rosnav framework of our previous work as an alternative simulation platform to train and develop DRL agents. Therefore, we utilized the provided API to integrate necessary components into the ecosystem of Arena-Rosnav. We evaluated our simulator by training a DRL agent within that platform and compared the training and navigational performance against the baseline 2D simulator Flatland, which is the default simulating platform of Arena-Rosnav. Results demonstrate that using our Arena2D simulator results in substantially faster training times and in some scenarios better agents. This proves to be an important step towards resource-efficient DRL training, which accelerates training times and improve the development cycle of DRL agents for navigation tasks. We made our simulator openly available at https://***/Arena-Rosnav/arena2d.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis and Performance Evaluation of Delayed Bilateral Telerobotic systems over a Lossy Communication Channel

引用

Journal of systems Science & Complexity 2021年第1期34卷 157-179页

作者： BAKHSHI Ali ALFI Alireza TALEBI Heidar Ali SOURATGAR Amir Aboulfazl YOUSEFI Mahdi Faculty of Electrical and Robotic Engineering Shahrood University of TechnologyShahrood 36199-95161Iran Power Plants Control Systems Technology Development Plan Department of monitoring and ControlNiroo Research InstituteTehran 14665-517Iran Real-Time and Robotics system Laboratory Faculty of Electrical EngineeringAmirkabir University of TechnologyHafez AvenueTehran 15914Iran Electrical and Computer Engineering Department The University of British Columbia2385East MallVan couverBC V6T 1Z4Canada

The focus of this paper is to address a novel control technique for stability and transparency analysis of bilateral telerobotic systems in the presence of data loss and time delay in the communication channel. Different control strategies have been reported to compensate the effects of time delay in the communication channel;however, most of them result in poor performance under data loss. First, a model for data loss is proposed using a finite series representation of a set of periodic continuous *** improve the performance and data reconstruction, a holder circuits is also introduced. The passivity of the overall system is provided via the wave variable technique based on the proposed model for the data loss. The stability analysis of the system is then derived using the Lyapunov theorem under the time delay and the data loss. Finally, experimental results are given to illustrate the capability of the proposed control technique.

关键词： Lossy channel passivity stability telerobotic transparency

来源：评论

学校读者我要写书评

暂无评论

Efficient TD3 based path planning of mobile robot in dynamic environments using prioritized experience replay and LSTM

引用

Scientific reports 2025年第1期15卷 18331页

作者： Yunhan Lin Zhijie Zhang Yijian Tan Hao Fu Huasong Min School of Computer Science and Technology Wuhan University of Science and Technology Wuhan 430081 China. Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan 430081 China. Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan 430081 China. Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan 430081 China. mhuasong@***.

To address the challenges of sample utilization efficiency and managing temporal dependencies, this paper proposes an efficient path planning method for mobile robot in dynamic environments based on an improved twin delayed deep deterministic policy gradient (TD3) algorithm. The proposed method, named PL-TD3, integrates prioritized experience replay (PER) and long short-term memory (LSTM) neural networks, which enhance both sample efficiency and the ability to handle time-series data. To verify the effectiveness of the proposed method, simulation and practical experiments were designed and conducted. In the simulation experiments, both static and dynamic obstacles were included in the test environment, along with experiments to assess generalization capabilities. The algorithm demonstrated superior performance in terms of both execution time and path efficiency. The practical experiments, based on the assumptions from the simulation tests, further confirmed that PL-TD3 has improved the effectiveness and robustness of path planning for mobile robot in dynamic environments.

关键词： Long short-term memory (LSTM ) Path planning in dynamic environment Prioritized experience replay (PER) Reinforcement learning Twin delayed deep deterministic policy gradient (TD3) algorithm

来源：评论

学校读者我要写书评

暂无评论

A General Gray Code Quantized Method of Binary Feature Descriptors for Fast and Efficient Keypoint Matching

A General Gray Code Quantized Method of Binary Feature Descr...

引用

International Conference on Intelligent Autonomous systems (ICoIAS)

作者： Yunhan Lin Yalan Sun Huasong Min College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial Systems Wuhan China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan China

In this paper, a general Gray code quantized method of binary feature descriptors is proposed for fast and efficient keypoint matching on 3D point clouds. In our method, it includes 2 variable L and N. L is rule variable which can be used to set the encoding group length according to the feature of the real-valued descriptor, and N is bits variable which can be used to set the number of Gray code bits according to the actual system requirements. Be different from the exist method, such as B-SHOT, our proposed method has the advantages of reasonable and flexible. As an example, our method is applied on the feature descriptor SHOT and tested in a standard benchmark dataset, different variable combinations of L and N are tested in the Gray code quantized processes, the best combination of L and N is dubbed as GRAY-SHOT through performance comparison. At last, GRAY-SHOT is compared with the state-of-the-art binary 3D feature descriptor B-SHOT, experimental evaluation result shows that GRAY-SHOT offers better keypoint matching performances to B-SHOT on a standard benchmark dataset with a slight more memory footprint and time consumption.

关键词： Three-dimensional displays Reflective binary codes Encoding Histograms Feature extraction Standards Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Studying bioluminescence flashes with the ANTARES deep Sea neutrino telescope

arXiv

引用

arXiv 2021年

作者： Reeb, Nico Hutschenreuter, S. Zehetner, P. Ensslin, T. Albert, A. Alves, S. André, M. Anghinolfi, M. Anton, G. Ardid, M. Aubert, J.-J. Aublin, J. Baret, B. Basa, S. Belhorma, B. Bendahman, M. Bertin, V. Biagi, S. Bissinger, M. Boumaaza, J. Bouta, M. Bouwhuis, M.C. Brânzaş, H. Bruijn, R. Brunner, J. Busto, J. Caiffi, B. Capone, A. Caramete, L. Carr, J. Carretero, V. Celli, S. Chabab, M. Chau, T.N. Chiarusi, T. Circella, M. Coleiro, A. Colomer-Molla, M. Coniglione, R. Coyle, P. Creusot, A. Díaz, A.F. de Wasseige, G. Deschamps, A. Distefano, C. Di Palma, I. Domi, A. Donzaud, C. Dornic, D. Drouhin, D. van Eeden, T. Enzenhöfer, A. Fermani, P. Ferrara, G. Filippini, F. Fusco, L. Gatelet, Y. Gay, P. Glotin, H. Gozzini, R. Ruiz, R. Gracia Graf, K. Guidi, C. Hallmann, S. van Haren, H. Heijboer, A.J. Hello, Y. Hernández-Rey, J.J. Hößl, J. Hofestädt, J. Huang, F. Illuminati, G. James, C.W. Jisse-Jung, B. de Jong, M. de Jong, P. Jongen, M. Kadler, M. Kalekin, O. Katz, U. Khan-Chowdhury, N.R. Kouchner, A. Kreykenbohm, I. Kulikovskiy, V. Lahmann, R. Le Breton, R. Lefèvre, D. Leonora, E. Levi, G. Lincetto, M. Lopez-Coto, D. Loucatos, S. Maderer, L. Manczak, J. Marcelin, M. Margiotta, A. Marinelli, A. Martínez-Mora, J.A. Melis, K. Migliozzi, P. Moussa, A. Muller, R. Nauta, L. Navas, S. Nezri, E. Fearraigh, B.Ó. Organokov, M. Pavalaş, G.E. Pellegrino, C. Perrin-Terrin, M. Piattelli, P. Pieterse, C. Poirè, C. Popa, V. Pradier, T. Randazzo, N. Reck, S. Riccobene, G. Romanov, A. Sánchez-Losa, A. Greus, F. Salesa Samtleben, D.F.E. Sanguineti, M. Sapienza, P. Schnabel, J. Schumann, J. Schüssler, F. Spurio, M. Stolarczyk, Th. Taiuti, M. Tingay, S.J. Vallage, B. van Elewyck, V. Versari, F. Viola, S. Vivolo, D. Wilms, J. Zavatarelli, S. Zegarelli, A. Zornoza, J.D. Zúñiga, J. Information Field Theory Group Max Planck Institute for Astrophysics Garching Germany Informatics 6 Chair of Robotics Artificial Intelligence and Real time Systems Technical University of Munich Garching Germany Department of Astrophysics IMAPP Radboud University Nijmegen Nijmegen Netherlands Department of Physics Ludwig-Maximilians University Munich Germany CERN Geneva Switzerland Université de Strasbourg CNRS IPHC UMR 7178 StrasbourgF-67000 France Université de Haute Alsace MulhouseF-68200 France IFIC - Instituto de Física Corpuscular CSIC Universitat de València c/ Catedrático José Beltrán 2 Paterna ValenciaE-46980 Spain Technical University of Catalonia Laboratory of Applied Bioacoustics Rambla Exposició Vilanova i la Geltrú Barcelona08800 Spain INFN - Sezione di Genova Via Dodecaneso 33 Genova16146 Italy Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Centre for Astroparticle Physics Erwin-Rommel-Str. 1 Erlangen91058 Germany Universitat Politècnica de València C/ Paranimf 1 Gandia46730 Spain Aix Marseille Univ CNRS IN2P3 CPPM Marseille France Université de Paris CNRS Astroparticule et Cosmologie ParisF-75013 France Aix Marseille Univ CNRS CNES LAM Marseille France National Center for Energy Sciences and Nuclear Techniques B.P.1382 RabatR. P. 10001 Morocco University Mohammed V in Rabat Faculty of Sciences 4 av. Ibn Battouta B.P. 1014 R.P. Rabat10000 Morocco Via S. Sofia 62 Catania95123 Italy University Mohammed I Laboratory of Physics of Matter and Radiations B.P.717 Oujda6000 Morocco Nikhef Science Park Amsterdam Netherlands Institute of Space Science Bucharest MagureleRO-077125 Romania Universiteit van Amsterdam Instituut voor Hoge-Energie Fysica Science Park 105 Amsterdam1098 XG Netherlands INFN - Sezione di Roma P.le Aldo Moro 2 Roma00185 Italy Dipartimento di Fisica Università La Sapienza P.le Aldo Moro 2 Roma00185 Italy LPHEA Faculty of Science - Semlali Cadi Ayyad University P.O

We develop a novel technique to exploit the extensive data sets provided by underwater neutrino telescopes to gain information on bioluminescence in the deep sea. The passive nature of the telescopes gives us the unique opportunity to infer information on bioluminescent organisms without actively interfering with them. We propose a statistical method that allows us to reconstruct the light emission of individual organisms, as well as their location and movement. A mathematical model is built to describe the measurement process of underwater neutrino telescopes and the signal generation of the biological organisms. The Metric Gaussian Variational Inference algorithm is used to reconstruct the model parameters using photon counts recorded by the neutrino detectors. We apply this method to synthetic data sets and data collected by the ANTARES neutrino telescope. The telescope is located 40 km off the French coast and fixed to the sea floor at a depth of 2475 m. The runs with synthetic data reveal that we can reliably model the emitted bioluminescent flashes of the organisms. Furthermore, we find that the spatial resolution of the localization of light sources highly depends on the configuration of the telescope. Precise measurements of the efficiencies of the detectors and the attenuation length of the water are crucial to reconstruct the light emission. Finally, the application to ANTARES data reveals the first precise localizations of bioluminescent organisms using neutrino telescope data. © 2021, CC BY.

关键词： Bioluminescence

来源：评论

学校读者我要写书评

暂无评论

A system for facial reconstruction using distraction and symmetry considerations

引用

International Congress Series 2001年第C期1230卷 62-67页

作者： Burgert, O. Salb, T. Gockel, T. Dillmann, R. Hassfeld, S. Brief, J. Krempien, R. Walz, S. Mühling, J. Institute of Real-Time Computer Systems and Robotics University of Karlsruhe D-76128 Karlsruhe Gebaude 07.21 Kaiserstr. 12 Germany Department of Oral and Maxillofacial Surgery University of Heidelberg D-69120 Heidelberg Germany Department of Radiology University of Heidelberg D-69120 Heidelberg Germany

The goal of the system presented in this paper is to support several facial surgeries that are aiming to transform an unsymmetrical face to a symmetric one. There are two main techniques to achieve this goal: distraction of the lower jaw and adding or removing tissue or bone at certain facial regions. Both planning tasks are done based on segmented CT or MRI data. The distraction of the lower jaw is simulated by cutting the jaw, moving it in 3D along a distraction axis and choosing a distractor for this procedure after determining, which is the best result. Furthermore, we are working on consideration of soft tissue movement so the patient can see what he or she will look like after the surgery. For supporting implants in craniofacial surgery, we are proposing a tool based on symmetry considerations. Nowadays, if implants have to be fitted to the patient's bone, they are handmade while the surgery is running. This is quite time consuming and it would be helpful to shorten this procedure by producing the implants preoperatively. Our system allows to determine regions where implants should be set and proposes an initial contour for the implants. © 2001 Elsevier Science B.V.

关键词： Distraction Face Symmetry

来源：评论

学校读者我要写书评

暂无评论

Robot assistant for dental implantology 4th

引用

4th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2001

作者： Boesecke, R. Brief, J. Raczkowsky, J. Schorr, O. Daueber, S. Krempien, R. Treiber, M. Wetter, T. Hassfeld, S. TaMed GmbH Hufschmiedstr. ¼ WieslochD-69168 Germany Department of Oral and Maxillofacial Surgery University Hospital Heidelberg Germany Department of Radiology University Hospital Heidelberg Germany Institute of Real-Time Computer Systems and Robotics University of Karlsruhe Germany Department of Medical Informatics University Hospital Heidelberg Germany

ISBN: (纸本)3540426973

We introduce a method to apply a preoperative 3D plan for inserting dental implants with an assisting medical robot. The treatment plan is based on the 3D visualization of the CT data of the patient.s maxilla and mandible, and supplies the location of the implants in the patient.s coordinates. The plan is then transferred to the surgical robot.s coordinate system. The robot guides the tool, a drill guide. Position, orientation, and depth of the initial drilling is defined with the tool held by the robot while the surgeon drills. The robot assists the dentist, and the optimal treatment plan will be applied directly to the patient. © Springer-Verlag Berlin Heidelberg 2001.

关键词： Drills

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：