检索结果-内蒙古大学图书馆

第33届中国控制与决策会议

作者： Wan Dai Hongpeng Wang Yulin Song Yunwei Xin College of Computer Science Nankai University Tianjin Key Laboratory of Intelligent Robotics College of Artificial Intelligence Nankai University Research Laboratory of Machine Learning and Pervasive Computing Nankai University

ISBN: (纸本)9781665431293

Visual tele-observation is an effective way for intelligent monitoring and protection of ecology and the natural *** from pedestrian or rigid body detection,wildlife detection in natural scenes face more complex problems,such as the existence of wild background clutter,local or global vegetation occlusion of animals,small object,rotation,deformation,and other interfering *** this paper,We mainly propose a novel method for the small object *** our small object wild species data set,we use an SSD detector for object ***,the K-means algorithm is used to adjust the anchor box of the SSD ***,for the situation that SSD is not good for small object detection,in conv4 layers of SSD,the feature enhancement module is ***,aiming at the size of a small object,the network level of SSD is *** have proved the feasibility of each of the three methods through experiments and combined with the three methods to verify,the recognition rate of the small target has increased by 2.67%.

关键词： anchor feature enhancement hierarchical design wildlife detection

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Robotic Testbench for Analyzing Pincer Grip Execution in Human Specimen Hands

Design and Implementation of a Robotic Testbench for Analyzi...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Nikolas Wilhelm Claudio Glowalla Sami Haddadin Julian Schote Hannes Höppner Patrick van der Smagt Maximilian Karl Rainer Burgkart Department of Orthopedics and Sports Orthopedics Klinikum Rechts der Isar School of Medicine Munich Germany Munich Institute of Robotics and Machine Intelligence Technical University of Munich Munich Germany Humanoid Robotics Laboratory Berliner Hochschule für Technik Berlin Germany Machine Learning Research Lab Volkswagen Group Munich Germany

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

This study presents an innovative test rig engineered to explore the kinematic and viscoelastic characteristics of human specimen hands. The rig features eight force-controlled motors linked to muscle tendons, enabling precise stimulation of hand specimens. Hand movements are monitored through an optical tracking system, while a force-torque sensor quantifies the resultant fingertip loads. Employing this setup, we successfully demonstrated a pincer grip using a cadaver hand and measured both muscle forces and grip strength. Our results reveal a nonlinear relationship between tendon forces and grip strength, which can be modeled by an exponential fit. This investigation serves as a nexus between biomechanical and robotics-focused research, providing critical insights for the advancement of robotic hand actuation and therapeutic interventions.

关键词： Biomechanics Technological innovation Tracking Stimulated emission Biological system modeling Muscles Motors

来源：评论

学校读者我要写书评

暂无评论

Full Shot Predictions for the DIII-D Tokamak via Deep Recurrent Networks

arXiv

引用

arXiv 2024年

作者： Char, Ian Chung, Youngseog Abbate, Joseph Kolemen, Egemen Schneider, Jeff Machine Learning Department Carnegie Mellon University United States Princeton Plasma Physics Laboratory United States Department of Mechanical and Aerospace Engineering Princeton Plasma Physics Laboratory Princeton University United States Robotics Institute Carnegie Mellon University United States

Although tokamaks are one of the most promising devices for realizing nuclear fusion as an energy source, there are still key obstacles when it comes to understanding the dynamics of the plasma and controlling it. As such, it is crucial that high quality models are developed to assist in overcoming these obstacles. In this work, we take an entirely data driven approach to learn such a model. In particular, we use historical data from the DIII-D tokamak to train a deep recurrent network that is able to predict the full time evolution of plasma discharges (or "shots"). Following this, we investigate how different training and inference procedures affect the quality and calibration of the shot predictions. © 2024, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Synchronization in interacting networks of Hodgkin-Huxley neurons

Synchronization in interacting networks of Hodgkin-Huxley ne...

引用

Saratov Fall Meeting 2021: Computational Biophysics and Nanobiophotonics

作者： Andreev, Andrey V. Maksimenko, Vladimir A. Neuroscience and Cognivite Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Universitetskaya Str. 1 Innopolis 420500 Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University A. Nevskogo ul. 14 Kaliningrad236016 Russia

ISBN: (数字)9781510653702

ISBN: (纸本)9781510653696

We consider a network of networks consisting of small input neural network and four small-world subnetworks Hodgkin-Huxley neurons. Input network receives an external signal and transfers it to subnetworks via excita-tory couplings while the subnets interact with each other via inhibitory couplings. We show that the subnets are divided into 2 clusters under the influence of an inhibitory couplings between them. The synchronization indexes of subnetworks periodically change in time. We found that SIs can oscillate either in-phase or anti-phase depending on the couplings between subnetworks. © 2022 SPIE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

learning Barrier-Certified Polynomial Dynamical Systems for Obstacle Avoidance with Robots

Learning Barrier-Certified Polynomial Dynamical Systems for ...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Martin Schonger Hugo T. M. Kussaba Lingyun Chen Luis Figueredo Abdalla Swikir Aude Billard Sami Haddadin Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University of Munich (TUM) Germany School of Computer Science University of Nottingham UK Omar Al-Mukhtar University (OMU) Albaida Libya Learning Algorithms and Systems Laboratory EPFL Switzerland

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Established techniques that enable robots to learn from demonstrations are based on learning a stable dynamical system (DS). To increase the robots’ resilience to perturbations during tasks that involve static obstacle avoidance, we propose incorporating barrier certificates into an optimization problem to learn a stable and barrier-certified DS. Such optimization problem can be very complex or extremely conservative when the traditional linear parameter-varying formulation is used. Thus, different from previous approaches in the literature, we propose to use polynomial representations for DSs, which yields an optimization problem that can be tackled by sum-of-squares techniques. Finally, our approach can handle obstacle shapes that fall outside the scope of assumptions typically found in the literature concerning obstacle avoidance within the DS learning framework. Supplementary material can be found at the project webpage: https://***/abc-ds

关键词： Shape Scalability Perturbation methods Polynomials Collision avoidance Dynamical systems Task analysis

来源：评论

学校读者我要写书评

暂无评论

Source-level analysis of brain activity in the process of learning and retrieving new information 5

Source-level analysis of brain activity in the process of le...

引用

5th Scientific School on Dynamics of Complex Networks and their Applications, DCNA 2021

作者： Makarov, Vladimir Grubov, Vadim Kurkin, Semen Smirnov, Nikita Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia

ISBN: (纸本)9781665442824

In this paper, we discovered the increase in EEG power in the theta frequency range in the occipital cortex during a visual analysis of new information and the power decrease in the alpha range in the temporal lobe during retaining information. The revealed increase in theta power correlates with the response time and errors rate. The alpha power correlates with response time. Summarizing the above, the detected cluster of theta-activity during information perception may reflect the increased concentration of attention. © 2021 IEEE

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Quasi-movements as an intermediate type of motion 5

Quasi-movements as an intermediate type of motion

引用

5th Scientific School on Dynamics of Complex Networks and their Applications, DCNA 2021

作者： Smirnov, Nikita M. Kurkin, Semen Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia

ISBN: (纸本)9781665442824

This paper discusses the three distinct types of motor activity, namely quasi, real, and imagery. Quasi-motion is voluntary movements that are minimized to the point that finally become undetectable by objective measures. This type of motion is particular from the point of difficulty of classifying it as real or imaginary. In this paper, we are aiming to show it from the sensor- and source-level perspectives. © 2021 IEEE

关键词： Dynamics Complex networks

来源：评论

学校读者我要写书评

暂无评论

Biomarkers of brain activity for the performance evaluation in the process of solving cognitive tasks 5

Biomarkers of brain activity for the performance evaluation ...

引用

5th Scientific School on Dynamics of Complex Networks and their Applications, DCNA 2021

作者： Badarin, Artem Smirnov, Nikita Kurkin, Semen Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia

ISBN: (纸本)9781665442824

In this paper, we analyze the brain activity during the execution by the subject of simple cognitive tasks associated with visual attention and symbol perception. We obtain biomarkers of brain activity in the process of solving cognitive tasks. These biomarkers make it possible to relate the quality and speed of execution of the tasks offered to the subject with the brain’s activity of the cortical network. We use a combination of time-frequency and statistical analysis to calculate activity characteristics. The results obtained can be used to develop neural interfaces for training attention and adjusting the learning process. © 2021 IEEE

关键词： Biomarkers

来源：评论

学校读者我要写书评

暂无评论

Comparison on brain activity for mechanical imagery and execution: a brief review 5

Comparison on brain activity for mechanical imagery and exec...

引用

5th Scientific School on Dynamics of Complex Networks and their Applications, DCNA 2021

作者： Chepurova, Alla Kurkin, Semen Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia

ISBN: (纸本)9781665442824

With this review we summarize the current state of scientific studies in the field of MI (motor imagery) and ME (motor execution). We composed brain map and description which correlate different brain areas with type of movements it is responsible for. That gives a more complete and systematic picture of human brain functionality in a case of ME and MI. Also we found the research gap and possible improvements for the further researches in this field. © 2021 IEEE

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Exploration via planning for information about the optimal trajectory 22

Exploration via planning for information about the optimal t...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Viraj Mehta Ian Char Joseph Abbate Rory Conlin Mark D. Boyer Stefano Ermon Jeff Schneider Willie Neiswanger Robotics Institute Machine Learning Department Carnegie Mellon University Princeton University Princeton Plasma Physics Laboratory Computer Science Department Stanford University

ISBN: (纸本)9781713871088

Many potential applications of reinforcement learning (RL) are stymied by the large numbers of samples required to learn an effective policy. This is especially true when applying RL to real-world control tasks, e.g. in the sciences or robotics, where executing a policy in the environment is costly. In popular RL algorithms, agents typically explore either by adding stochasticity to a reward-maximizing policy or by attempting to gather maximal information about environment dynamics without taking the given task into account. In this work, we develop a method that allows us to plan for exploration while taking both the task and the current knowledge about the dynamics into account. The key insight to our approach is to plan an action sequence that maximizes the expected information gain about the optimal trajectory for the task at hand. We demonstrate that our method learns strong policies with 2x fewer samples than strong exploration baselines and 200x fewer samples than model free methods on a diverse set of low-to-medium dimensional control tasks in both the open-loop and closed-loop control settings.

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：