检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Bi, Zhihai Chen, Kai Zheng, Chunxin Li, Yulin Li, Haoang Ma, Jun Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology Guangzhou China

Interactive navigation is crucial in scenarios where proactively interacting with objects can yield shorter paths, thus significantly improving traversal efficiency. Existing methods primarily focus on using the robot body to relocate large obstacles (which could be comparable to the size of a robot). However, they prove ineffective in narrow or constrained spaces where the robot’s dimensions restrict its manipulation capabilities. This paper introduces a novel interactive navigation framework for legged manipulators, featuring an active arm-pushing mechanism that enables the robot to reposition movable obstacles in space-constrained environments. To this end, we develop a reinforcement learning-based arm-pushing controller with a two-stage reward strategy for large-object manipulation. Specifically, this strategy first directs the manipulator to a designated pushing zone to achieve a kinematically feasible contact configuration. Then, the end effector is guided to maintain its position at appropriate contact points for stable object displacement while preventing toppling. The simulations validate the robustness of the arm-pushing controller, showing that the two-stage reward strategy improves policy convergence and long-term performance. Real-world experiments further demonstrate the effectiveness of the proposed navigation framework, which achieves shorter paths and reduced traversal time. The open-source project can be found at https://***/Zhihaibi/ Interactive-Navigation-for-legged-manipulator. git. Copyright © 2025, The Authors. All rights reserved.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

Motion Planning for an Underwater Swimming Manipulator Using BMA-RRT* and the Geometric Follow-the-Leader Method

Motion Planning for an Underwater Swimming Manipulator Using...

引用

第43届中国控制会议

作者： Yiwei Zhao Chao Ren Shugen Ma Thrust of Robotics and Autonomous Systems The Hong Kong University of Science and Technology (Guangzhou)

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The Underwater Swimming Manipulator(USM) is a novel type of underwater robot that can autonomously and flexibly execute underwater tasks by leveraging its redundant degrees of freedom. Currently, there is a lack of motion planning methods specifically designed for USMs. In this paper, a USM with 14 degrees of freedom is introduced and a motion planning framework for it is designed. The framework consists of a path planner based on Rapidly-exploring Random Tree(RRT) and an inverse kinematics(IK) solver based on the geometric Follow-the-Leader(FTL) strategy. Then, BMA-RRT* is proposed to address the limitations of the existing MDA-RRT* algorithm. Simulation results in a 3D environment show that BMA-RRT*improves overall performance compared to MDA-RRT*, and the feasibility and efficiency of proposed framework are validated.

关键词： Underwater swimming manipulator Redundant robots Motion and path planning

来源：评论

学校读者我要写书评

暂无评论

Feasibility Investigation on Sinusoidal-Reluctance Rotor Contour in Variable Reluctance Resolver

Feasibility Investigation on Sinusoidal-Reluctance Rotor Con...

引用

2023 IEEE International Magnetic Conference - Short Papers, INTERMAG Short Papers 2023

作者： Mi, Wenyuan Yu, Jincheng Cai, Zheng Zhao, Hang Zhao, Fei Luo, Yixiao School of Mechanical Engineering and Automation Shenzhen China Robotics and Autonomous Systems Thrust Guangzhou China Huazhong University of Science and Technology School of Electrical and Electronic Engineering Wuhan China

ISBN: (纸本)9798350338362

In this digest, a novel variable reluctance (VR) resolver with sinusoidal-reluctance rotor contour is proposed and its envelope feasibility is evaluated via the analytical and finite element (FE) analysis. Moreover, the third order harmonic suppression via flux leakage compensation is addressed to reveal the operation principle of the proposed VR resolver. Under 4 mm tooth width, the total harmonic distortion of the cosine envelope with the proposed rotor contour can be limited to only 0.56%. © 2023 IEEE.

关键词： Harmonic analysis

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Superposition Point Process Model with Neuronal Encoding Engagement Identification 46

An Adaptive Superposition Point Process Model with Neuronal ...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Li, Mingdong Wang, Mingyi Wang, Yiwen Robotics and Autonomous Systems Thrust Hkust Guangzhou China Hkust Hong Kong Department of Chemical and Biological Engineering Hkust Hong Kong Department of Electronic and Computer Engineering Hkust Hong Kong Hkust Guangzhou China

ISBN: (纸本)9798350371499

Neuronal encoding is realized by modulating firing rates in response to various encoding factors, including external stimuli, behaviors, and complex neural interactions. The neuronal encoding engagement of various factors are dynamic, which reflects how neurons aggregate different information. The process of uncovering the extent to which these factors contribute to neuronal encoding over time is neuronal encoding engagement identification. Brain-machine interface (BMI) establishes a closed-loop framework to investigate how neurons response to different encoding factors. Since neurons don't fully participate in encoding one specific factor, accurate encoding engagement identification contributes to leveraging encoding and decoding in more naturalistic BMI application scenarios. However, previous works focus on modeling and estimating tuning properties instead of analyzing the neuronal information aggregation. We develop a dual adaptive superposition point process filter (DASPPF), which explicitly incorporates various encoding factors. DASPPF not only enables decoding kinematics but also identifies the engagement of individual kinematics encoding and functional neural connectivity encoding. DASPPF is validated on numerical simulations of monkey circle-tracking tasks. The proposed method can effectively promote decoding performance and uncover how neurons engage themselves in different effects with point process observation, which may help enhance the development of neurotechnologies. © 2024 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Order-Reduced Nonlinear Semi-Analytical Multiphysics Model for Axial-Flux Motors

引用

IEEE Transactions on Transportation Electrification 2025年

作者： Su, Xiangdong Li, Fang Yin, Zhenxiao Liu, Xuyang Zhao, Hang Thrust of Robotics and Autonomous Systems Guangzhou510000 China Direct Drive Technology Research and Development Center Dongguan523000 China

Electromagnetic-thermal analysis is crucial to guarantee the axial flux motors' (AFMs) reliable operation as their compact size and poor heat dissipation conditions can lead to thermal limits. However, the conventional coupled analysis is extremely time-consuming, especially in 3D analysis. To this end, a fast semi-analytical electromagnetic-thermal coupling calculation framework is proposed that couples a harmonic modeling method (HMM) with a lumped parameter thermal network (LPTN), incorporating heat transfer mechanisms including conduction, convection, and radiation. In the electromagnetic field analysis part, an order-reduced electromagnetic model is constructed using the HMM considering the nonlinearity of the iron core. Based on that, a bi-directional electromagnetic-thermal coupling analysis is realized, the variation of electromagnetic properties with temperature, including copper conductivity, permanent magnet (PM) remanence, and the permeability of the iron core, are incorporated into the coupling analysis. Notably, the stator teeth are finely segmented in the electromagnetic model to accurately capture magnetic saturation effects under varying temperature conditions. Ultimately, the reliability and accuracy of the proposed method are verified through the finite element method (FEM) and prototype experiments. It is demonstrated that compared with FEM, the proposed framework has a satisfactory calculation efficiency and saves 98.4% of the computation time than FEM, making it suitable for preliminary motor design and optimization considering multiphysics influence. © 2015 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Ultra-Local Model-Free Predictive Control with Switching Strategy of PMSMs for Two-Phase Stationary Current

Ultra-Local Model-Free Predictive Control with Switching Str...

引用

International Conference on Electrical Machines and systems (ICEMS)

作者： Xueyan Wang Zhenxiao Yin Yang Shen Ming Liu Hang Zhao Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China

ISBN: (数字)9784886864406

ISBN: (纸本)9798350379105

This paper presents a high-performance switching ultra-local model-free control strategy for permanent magnet synchronous motors (PMSMs) in two-phase stationary coordination. First, an ultra-local model-free predictive control scheme that incorporates a tracking error term is proposes in this paper, allowing for enhanced control performance with reduced parameter tuning. Second, the exponential term is introduced into this strategy to enable a more accurate fitting of motor current response, thereby enhancing the system's dynamic performance. Finally, simulation results show that the proposed switching model-free predictive control (PSMFPC) achieves the shortest rise time during no-load startup. The d-axis and q-axis current oscillations of PSMFPC are significantly reduced by 26.79% and 15.64% respectively. Inductance mismatch has a significant negative impact on traditional PI and model-free predictive control (MFPC) strategies, nearly doubling the dq-axis current oscillations, while PSMFPC demonstrates higher robustness.

关键词： Robust control System dynamics Simulation Switches Predictive models Robustness Time factors Tuning Oscillators Predictive control

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Subcategory Ground Segmentation Model for LiDAR Point Cloud

Learning-Based Subcategory Ground Segmentation Model for LiD...

引用

IEEE International Conference on robotics and Biomimetics

作者： Guoyang Zhao Fulong Ma Weiqing Qi Ming Liu Jun Ma Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

Ground segmentation based on LiDAR point clouds is one of the crucial tasks in 3D perception, directly impacting the recognition of traversable areas for mobile robots. Current mainstream methods rely on manually designed features and parameter tuning, requiring adjustments for different environments. This approach is not only time-consuming but also results in unstable robustness. This paper proposes a model named GroundSeg, which uses deep learning to automatically learn and extract distinguishing ground features. It not only accurately segments the overall ground but also performs semantic segmentation of ground subcategories. In our ground segmentation model, we introduce cylindrical voxelization to match the physical characteristics of LiDAR point clouds. We then propose a Channel-Plane Extraction (CPE) Module to ex-tract both local and global distinguishing features of the ground in three-dimensional voxels. Finally, we incorporate a class-balanced loss group to achieve precise ground segmentation and subcategory classification. Experimental results show that our proposed model has significant advantages in the integrity of ground segmentation and outperforms existing traditional and learning-based methods in F-l score. This is the first work to consider refined category ground segmentation, making it more meaningful for practical robotic applications. All qualitative and quantitative evaluation experiments were conducted on the standard SemanticKITTI dataset.

关键词： Point cloud compression Learning systems Visualization Laser radar Three-dimensional displays Semantic segmentation Feature extraction Mobile robots Tuning Standards

来源：评论

学校读者我要写书评

暂无评论

Hybrid Event-triggered Control of Nonlinear System with Full State Constraints and Disturbance

Hybrid Event-triggered Control of Nonlinear System with Full...

引用

Chinese Control and Decision Conference, CCDC

作者： Ziming Wang Systems Hub Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

This article focuses on the problem of adaptive tracking control for a specific type of nonlinear system that is subject to full-state constraints via a hybrid event-triggered control (HETC) strategy. With the auxiliary system, we proposed a ’log’ function to deal with the full-state constraint. Additionally, a disturbance observer (DO) is constructed to handle the unmeasurable external disturbance. Then, by employing radial basis function neural networks (RBFNNs) and a first-order differentiator, an opportune backstepping design procedure is given to avoid the problem of "explosion of complexity". The HETC strategy, including the fixed and relative threshold, is presented to provide more flexibility in balancing the system performances and network burdens. Finally, to demonstrate the effectiveness of the aforementioned control scheme, a simulation example is presented to validate its effectiveness.

关键词： Backstepping Estimation Switches Radial basis function networks Control systems Disturbance observers Explosions

来源：评论

学校读者我要写书评

暂无评论

Design Considerations of Outer-Rotor Flux-Modulated Permanent-Magnet In-Wheel Motors 32

Design Considerations of Outer-Rotor Flux-Modulated Permanen...

引用

32nd IEEE International Symposium on Industrial Electronics, ISIE 2023

作者： Huang, Zekang Luo, Yixiao Mi, Wenyuan Cai, Zheng Zhao, Fei Zhao, Hang Yu, Jincheng School of Mechanical Engineering and Automation Shenzhen China Huazhong University of Science and Technology School of Electrical and Electronic Engineering Wuhan China Robotics and Autonomous Systems Thrust Guangzhou China

ISBN: (纸本)9798350399714

This paper presents the design considerations of outer-rotor flux-modulated permanent-magnet (OR-FMPM) in-wheel motors applied to light electric vehicles (EVs). The basic wheel model and drive system specifications are considered in the motor design, with utility of the flat-wire armature windings. The multi-step motor optimization focusing on the outer-rotor PM machines is carried out to reach the design objectives of the drive system, with auxiliary of the sensitivity analysis to lower the computing burden. Finally, the motor electromagnetic performances are specifically analyzed, verifying the feasibility of the motor design in the application of in-wheel motors. © 2023 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

CP-RCNN: Lidar Object Detection with Feature Pooling and Abstraction

CP-RCNN: Lidar Object Detection with Feature Pooling and Abs...

引用

International Conference on Control, Automation, robotics and Vision (ICARCV)

作者： Hang Zhou Yiding Ji Robotics and Autonomous Systems Thrust Systems Hub The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China

ISBN: (数字)9798331518493

ISBN: (纸本)9798331518509

LiDAR-based object detection is a challenging task for autonomous navigation systems, especially in pedestrian-rich environments. Recently, the integration of deep learning techniques with lidar-generated point cloud data has advanced object detection and segmentation in many scenarios. However, current lidar-based methods usually struggle to accurately detect small-sized objects, such as pedestrian and cyclist, causing severe safety and reliability concerns for autonomous vehicles. This study refines structural design of lidar based neural networks to enhance precision and recall metrics for the identification of small entities. Specifically, we introduce CP-RCNN, a novel lidar object detection framework that combines state of the art voxelization and feature extraction techniques. Extensive ablation experiments demonstrate that our method has improved performance in the detection of pedestrians and cyclists. Furthermore, this paper also proposes a novel neural network structure named Centerpoint-RCNN, which not only maintains high precision in vehicle classification but also achieves an impressive inference speed of 15Hz on the NVIDIA RTX 4090 graphics processing unit.

关键词： Pedestrians Laser radar Computational modeling Neural networks Object detection Feature extraction Safety Reliability Vehicle dynamics autonomous robots

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：