检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wang, Luming Shi, Hao Yin, Xiaoting Yang, Kailun Wang, Kaiwei Bai, Jian State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University China School of Robotics Hunan University China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China

Egocentric gesture recognition is a pivotal technology for enhancing natural human-computer interaction, yet traditional RGB-based solutions suffer from motion blur and illumination variations in dynamic scenarios. While event cameras show distinct advantages in handling high dynamic range with ultra-low power consumption, existing RGB-based architectures face inherent limitations in processing asynchronous event streams due to their synchronous frame-based nature. Moreover, from an egocentric perspective, event cameras record data that includes events generated by both head movements and hand gestures, thereby increasing the complexity of gesture recognition. To address this, we propose a novel network architecture specifically designed for event data processing, incorporating (1) a lightweight CNN with asymmetric depthwise convolutions to reduce parameters while preserving spatiotemporal features, (2) a plug-and-play state-space model as context block that decouples head movement noise from gesture dynamics, and (3) a parameter-free Bins-Temporal Shift Module (BSTM) that shifts features along bins and temporal dimensions to fuse sparse events efficiently. We further establish the EgoEvGesture dataset, the first large-scale dataset for egocentric gesture recognition using event cameras. Experimental results demonstrate that our method achieves 62.7% accuracy tested on unseen subjects with only 7M parameters, 3.1% higher than state-of-the-art approaches. Notable misclassifications in freestyle motions stem from high interpersonal variability and unseen test patterns differing from training data. Moreover, our approach achieved a remarkable accuracy of 97.0% on the DVS128 Gesture, demonstrating the effectiveness and generalization capability of our method on public datasets. The dataset and models are made available at https://***/3190105222/EgoEv_Gesture. Copyright © 2025, The Authors. All rights reserved.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Design of a Variable Stiffness Spring with Human-Selectable Stiffness

arXiv

引用

arXiv 2023年

作者： Mathews, Chase W. Braun, David J. Advanced Robotics and Control Laboratory within the Center for Rehabilitation Engineering and Assistive Technology Department of Mechanical Engineering Vanderbilt University NashvilleTN37235 United States

Springs are commonly used in wearable robotic devices to provide assistive joint torque without the need for motors and batteries. However, different tasks (such as walking or running) and different users (such as athletes with strong legs or the elderly with weak legs) necessitate different assistive joint torques, and therefore, springs with different stiffness. Variable stiffness springs are a special class of springs which can exert more or less torque upon the same deflection, provided that the user is able to change the stiffness of the spring. In this paper, we present a novel variable stiffness spring design in which the user can select a preferred spring stiffness similar to switching gears on a bicycle. Using a leg-swing experiment, we demonstrate that the user can increment and decrement spring stiffness in a large range to effectively assist the hip joint during leg oscillations. Variable stiffness springs with human-selectable stiffness could be key components of wearable devices which augment locomotion tasks, such as walking, running, and swimming. © 2023, CC BY-NC-ND.

关键词： Stiffness

来源：评论

学校读者我要写书评

暂无评论

A New Kinematics Modeling Method of Parallel Mechanisms: Applicate to Obtain Full Attitude Space and Evaluate Performance

SSRN

引用

SSRN 2023年

作者： He, Yufan Fang, Hairong Jin, Zhengxian Robotics Research Center Beijing Jiaotong University Beijing100044 China School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing100044 China

In this study, a new kinematic analysis method of parallel mechanism is proposed, which can obtain the full attitude space in a single calculation model. Compared with the traditional method based on inverse kinematics, the new method can significantly improve computational efficiency. The performance evaluation system of the method is established. Under the conditions of the same number of calculations and the same iteration step, the ℜ value as the performance evaluation indexes obtained by synthesizing the calculation time, the maximum CPU occupancy rate and the workspace point density. The classical PPU-3RUS parallel mechanism and the new 3UCU-RU parallel mechanism proposed in this paper are selected as the analysis objects, and the kinematics solution model is established by using the new method to prove the effectiveness and applicability of the method. The two mechanisms are analyzed by the new method and the traditional method respectively. The results show that the new method has the characteristics of high computational efficiency, less resource occupation and high accuracy of solution. © 2023, The Authors. All rights reserved.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Vehicle Tracking Method Based on Attention-YOLOv5 and Optimized DeepSort Models 11

Vehicle Tracking Method Based on Attention-YOLOv5 and Optimi...

引用

11th IEEE Data Driven control and Learning Systems Conference, DDCLS 2022

作者： Li, Zhuang Tian, Xincheng Liu, Yan Shi, Xiaorui Shandong University Center for Robotics School of Control Science and Engineering Jinan250061 China Engineering Research Center of Intelligent Unmanned System Ministry of Education Jinan250061 China Sinotruk Jinan Power Co. Ltd. Sinotruk Industry Park Zhangqiu Jinan250220 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

Vehicle tracking plays a vital role in traffic management and autonomous driving. In order to further improve the accuracy of vehicle tracking, reduce the number of ID-Switch and enhance the anti-interference ability to the outside world, we propose a vehicle detection and tracking model based on Attention-YOLOv5 and optimized DeepSort. Firstly, YOLOv5 with attention mechanism was used as the front-end target detector, that is, add CBAM and ECA attention mechanisms to the backbone network of the benchmark YOLOv5 separately to improve the feature extraction ability. Then use the transfer learning idea to train it on the BDD dataset, it is concluded that ECA-YOLOv5 has the highest detection accuracy. Further we optimize the DeepSort algorithm, in order to overcome the disadvantages of the pre-training model not targeting traffic vehicles, we improve the re-recognition network structure and optimize the VeRi re-identification dataset, next perform re-identification pre-training on the Improved-VeRi dataset based on transfer learning. In order to make the vehicle features evenly distributed around the center of the class and improve feature resolution, a loss function L/CL combining the Softmax loss function and center loss function is proposed. In the experimental part, collecting some highway traffic videos of different scenes. At first, conduct visual analysis, then perform ablation experiments, and evaluate by using MOTA, MOTP and ID-Switch. Compared with the benchmark algorithm, the tracking performance is significantly improved. © 2022 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Optimal Stabilization of Periodic Orbits

引用

IFAC-PapersOnLine 2023年第2期56卷 7509-7515页

作者： Fabian Beck Noboru Sakamoto Institute of Robotics and Mechatronics German Aerospace Center (DLR) 82234 Wessling Germany Department of Mechanical Engineering and System Control Nanzan University Yamzato-cho 18 Showa-ku Nagoya 466-8673 Japan

In this contribution the optimal stabilization problem of periodic orbits is studied in a symplectic geometry setting. For this, the stable manifold theory for the point stabilization case is generalized to the case of periodic orbit stabilization. Sufficient conditions for the existence of a normally hyperbolic invariant manifold (NHIM) of the Hamiltonian system are derived. It is shown that the optimal control problem has a solution if the related periodic Riccati equation has a unique periodic solution. For the analysis of the stable and unstable manifold a coordinate transformation is used which is moving along the orbit. As an example, an optimal control problem is considered for a spring-mass oscillator system, which should be stabilized at a certain energy level.

关键词： Hamiltonian Dynamics Nonlinear control Periodic Orbit Optimal control

来源：评论

学校读者我要写书评

暂无评论

Application of Combined Finite-time State-Dependent Riccati Equation Terminal Sliding Mode control to Robotic Manipulators

Application of Combined Finite-time State-Dependent Riccati ...

引用

Conference on Artificial Intelligence and robotics and Asia-Pacific International Symposium

作者： Neda Nasiri Ahmad Fakharian Mohammad Bagher Menhaj Department. of Electrical Engineering Qazvin Branch Islamic Azad University Qazvin Iran Department of Electrical Engineering The Center of Excelence on Control and Robotics Amirkabir University of Technology (Tehran Polytechnic) Tehran Iran

This paper investigates application of the terminal sliding mode control (TSMC) in conjunction with state-dependent differential Riccati equation (SDDRE) for robotic manipulators in finite time. Due to nature of the terminal sliding mode control, considering finite time as an input control parameter is impossible. Hence, the convergence time could not be determined before completing the task. However, in this method, finite-time gain which is obtained through partitioning and making symmetric positive definite SDDRE control gain is inserted into the sliding surface. This leads to completing the control task in the desired predetermined time. To highlight superiority of the finite-time SDRE-terminal sliding mode control as a robust optimal scheme, we compared with TSMC as a robust control through applying both methods to 3-DoF articulated-joint manipulator. Simulation results are fully discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Actor-Critic Reinforcement Learning Scheme for Reactive 3D Optimal Motion Planning Based on Fluid Dynamics

An Actor-Critic Reinforcement Learning Scheme for Reactive 3...

引用

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

作者： Marios Malliaropoulos Panagiotis Rousseas Charalampos P. Bechlioulis Kostas J. Kyriakopoulos School of Mechanical Engineering Control Systems Laboratory National Technical University of Athens Department of Electrical and Computer Engineering University of Patras Center of AI & Robotics (CAIR) New York University Abu Dhabi

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This work proposes a novel and provably correct method for three-dimensional optimal motion planning in complex environments. Our approach models the 3D motion planning problem by solving streamlines of the potential fluid flow, filling a gap in traditional motion planning techniques by guaranteeing a closed-loop, smooth and natural-looking navigation solution. Special emphasis is given to an inherent challenge of artificial potential field (APF) methods, namely establishing proofs of safety and stability over the entire optimization process. A model-based actor-critic reinforcement learning algorithm is introduced to approximate the optimal solution to the Hamilton-Jacobi-Bellman equation and update the controller parameters in a deterministic manner. Through a series of ROS-Gazebo software-in-the-loop simulations the proposed methodology demonstrates robustness and outperforms widely used methods such as the RRT ∗ , highlighting its contribution to the field of 3D optimal motion planning.

关键词： Solid modeling Three-dimensional displays Navigation Reinforcement learning Mathematical models Stability analysis Robustness Planning Safety Optimization

来源：评论

学校读者我要写书评

暂无评论

Research on Robot Path Planning Algorithm for Filter Plate Cleaning of Plate and Frame Filter Press

Research on Robot Path Planning Algorithm for Filter Plate C...

引用

Artificial Intelligence and Intelligent Manufacturing (AIIM), International Symposium on

作者： Jie Xu Long Cui Yongguo Zhao Xincheng Tian Center for Robotics School of Control Science and Engineering Shandong University Jinan China Engineering Research Center of Intelligent Unmanned System Ministry of Education Jinan China Shandong Academy of Sciences Institute of Automation Qilu University of Technology Jinan China

ISBN: (数字)9798331541729

ISBN: (纸本)9798331541736

Plate and frame filter press is an important solid-liquid separation equipment that plays an important role in many fields. The filter plate is one of the core components of the frame filter press, and its main function is to support the filter cloth and form a filter chamber. After the filtration process of the filter press is completed, a large number of impurities are often attached to the filter plate, so it is of great value to study the impurity cleaning problem of the filter plate of the plate and frame filter press. In this paper, aiming at the cleaning process of the filter plate of the plate and frame filter press, the image information of the filter plate is obtained by visual means, and then the image is analyzed and processed to obtain the position information of the impurities of the filter plate, the path planning of the obtained position information is carried out, and finally the robot is made to complete the cleaning task efficiently and accurately according to the planned path, which has certain practical value.

关键词： Presses Visualization Impurities Image processing Filtering algorithms Information filters Cleaning Path planning Manufacturing Robots

来源：评论

学校读者我要写书评

暂无评论

Autonomous Exploration of Unknown 3D Environments Using a Frontier-Based Collector Strategy

Autonomous Exploration of Unknown 3D Environments Using a Fr...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Iván D. Changoluisa Caiza Ana Milas Marco A. Montes Grova Francisco Javier Pérez-Grau Tamara Petrovic University of Zagreb Faculty of Electrical Engineering and Computing LARICS Laboratory for Robotics and Intelligent Control Systems Zagreb Croatia Advanced Center for Aerospace Technologies (CATEC) Aerospace Technology Park of Andalusia Seville Spain

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Autonomous exploration using unmanned aerial vehicles (UAVs) is essential for various tasks such as building inspections, rescue operations, deliveries, and warehousing. However, there are two main limitations to previous approaches: they may not be able to provide a complete map of the environment and assume that the map built during exploration is accurate enough for safe navigation, which is usually not the case. To address these limitations, a novel exploration method is proposed that combines frontier-based exploration with a collector strategy that achieves global exploration and complete map creation. In each iteration, the collector strategy stores and validates frontiers detected during exploration and selects the next best frontier to navigate to. The collector strategy ensures global exploration by balancing the exploitation of a known map with the exploration of unknown areas. In addition, the online path replanning ensures safe navigation through the map created during motion. The performance of the proposed method is verified by exploring 3D simulation environments in comparison with the state-of-the-art methods. Finally, the proposed approach is validated in a real-world experiment.

关键词： Three-dimensional displays Video on demand Navigation Warehousing Buildings Inspection Web sites

来源：评论

学校读者我要写书评

暂无评论

On Networked Dynamical Systems with Heterogeneous Constraints:Equilibrium Points and Stability 41

On Networked Dynamical Systems with Heterogeneous Constraint...

引用

第41届中国控制会议

作者： Qichao Ma Jiahu Qin Yu Kang Huijun Gao Department of Automation University of Science and Technology of China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Institute of Advanced Technology University of Science and Technology of China Research Institute of Intelligent Control and Systems and the State Key Laboratory of Robotics and System Harbin Institute of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this paper,we investigate multi-agent systems with heterogeneous constraints,which can represent the heuristic beliefs of the agents towards an issue or the physical constraints of the *** typical example is a group of interacting unmanned aerial vehicles in a complex environment with multiple physical *** a result of the heterogeneity of the constraints,an equilibrium point may not exist and is presumably to be a dissensus point when it *** investigate the existence of equilibrium points from the perspective of Kakutani's fixed point theory for a set-valued *** also prove the local/global stability of certain equilibrium ***,a special case that the constraints are homogeneous is taken into *** constrains are assumed to take interval forms with nonempty *** is proved that consensus can be achieved globally and asymptotically for this *** examples are designed to illustrate our theoretical findings.

关键词： Multi-agent systems heterogeneous constraints equilibrium point and its stability constrained consensus

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：