检索结果-内蒙古大学图书馆

FWAF-VID: A Flapping-Wing Aggressive Flight Benchmark Dataset for Visual-Inertial Localization

IEEE robotics and Automation Letters 2025年第6期10卷 6328-6335页

作者： Jiang, Jizhou Pan, Erzhen Xu, Wenfu Sun, Wei Ye, Jingyang Harbin Institute of Technology School of Robotics and Advanced Manufacture Shenzhen518055 China Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Shenzhen518055 China Guangdong Biomimetic Intelligent Unmanned System Engineering Technology Research Center Shenzhen518052 China

Accurate state estimation of micro aerial vehicles (MAVs) in high-speed and dynamic environments poses a significant challenge for visual-inertial odometry (VIO) algorithms. Flapping-wing aerial vehicles (FWAVs), as an emerging flight platform, have attracted significant attention for stealth capabilities and efficient flight characteristics. Despite the availability of numerous MAV visual-inertial datasets for six-degree-of-freedom (6-DoF) state estimation, these datasets are not applicable for FWAVs with pronounced vibrations and agile maneuverability. To address this gap, we propose a large-scale flapping-wing aggressive flight visual-inertial dataset FWAF-VID. It contains diverse integrations of synchronized onboard cameras and IMU sensors. A total of 28 sequences include static flapping, calibration, and real-world flights collected in outdoor and indoor environments. The 17 flight sequences feature variations in illuminations, speeds, trajectories, camera perspectives, and flight modalities. We provide precisely aligned ground truth RTK and UWB measurements for algorithm evaluation. Furthermore, a comprehensive benchmark comparison is conducted, qualitatively and quantitatively evaluating the positioning accuracy of state-of-the-art VIO algorithms. The experimental results indicate that despite the degradation in localization accuracy in high-dynamic environments, FWAF-VID can effectively support the further development of VIO algorithms for FWAVs. To the best of our knowledge, this is the first onboard benchmark dataset tailored for aggressive flight in flapping-wing airborne platforms. © 2025 IEEE.

关键词： Micro air vehicle (MAV)

来源：评论

学校读者我要写书评

暂无评论

LTM: A Fast and Error-sensitive Point Cloud Clustering Algorithm for LiDAR Panoptic Segmentation 9

LTM: A Fast and Error-sensitive Point Cloud Clustering Algor...

引用

9th International Conference on robotics and Automation Engineering, ICRAE 2024

作者： Wu, Peng Hu, Zhengxi Zhang, Qianyi Guang, Jinzheng Liu, Jingtai Nankai University Robotics and Automatic Information System Tianjin China Tianjin Key Laboratory of Intelligent Robotics China Nankai University Tbi Center China

ISBN: (纸本)9798331518301

Point cloud clustering is a crucial approach to understand and analyze geometric information for both robotic systems and autonomous driving. To meet real-time requirements, several existing point cloud clustering algorithms are based on Connected Component Labeling. It means that classification decisions are made locally based on the geometric relationships among neighboring points. However, the existing neighborhood connection criterion lack robustness. This is because the difference in resolution between point clouds in the horizontal and vertical directions and various depth affect the distance between adjacent points, thereby affecting connectivity determination. In this paper, we propose a novel clustering algorithm LTM (includes Linearization, Trunk extraction and Merge). It processes the horizontal and vertical directions separately in two steps and innovatively utilizes three points to determine neighborhood connectivity. Thus, it can reduce the impact of these constraints on the effectiveness. We cascade the proposed clustering algorithm with existing semantic segmentation models and perform a panoptic segmentation task on the SemanticKITTI. Experimental results demonstrate that LTM achieved the best results among all published methods of the same category. Furthermore, the single-frame processing time for clustering is within 10 milliseconds. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Flexible servo riveting system control strategy based on the RBF network and self-pierce riveting process

引用

Advances in Manufacturing 2023年第1期11卷 39-55页

作者： Yan Liu Qiu Tang Xin-Cheng Tian Long Cui Center for Robotics School of Control Science and EngineeringShandong UniversityJinan250061People’s Republic of China Engineering Research Center of Intelligent Unmanned System Ministry of EducationJinan250061People’s Republic of China

As more and more composite materials are used in lightweight vehicle white bodies,self-pierce riveting(SPR)technology has attracted great ***,the existing riveting tools still have the disadvantages of low efficiency and *** improve these disadvantages and the riveting qualification rate,this paper improves the control scheme of the existing riveting tools,and proposes a novel controller design approach of the flexible servo riveting system based on the RBF network and SPR ***,this paper briefly introduces the working principle and SPR procedure of the servo riveting *** a moving component force analysis is performed,which lays the foundation for the motion ***,the riveting quality inspection rules of traditional riveting tools are used for reference to plan the force-displacement curve *** control this process,the riveting force is fed back into the closed-loop control of the riveting tool and the riveting speed is computed based on the admittance control ***,this paper adopts the permanent magnet synchronous motor(PMSM)as the power of riveting tool,and proposes an integral sliding mode control approach based on the improved reaching law and the radial basis function(RBF)network friction compensation for the PMSM speed ***,the proposed control approach is simulated by Matlab,and is applied to the servo riveting system designed by our *** simulation and riveting results show the feasibility of the designed controller.

关键词： Lightweight vehicle body connection Self-pierce riveting(SPR)process Flexible servo riveting tool Riveting force planning and control

来源：评论

学校读者我要写书评

暂无评论

UAGE: A Supervised Contrastive Method for Unconstrained Adaptive Gaze Estimation 17th

UAGE: A Supervised Contrastive Method for Unconstrained Ada...

引用

17th Asian Conference on Computer Vision, ACCV 2024

作者： Lan, Enfan Hu, Zhengxi Liu, Jingtai Institute of Robotics and Automatic Information System Nankai University Tianjin China Tianjin Key Laboratory of Intelligent Robotics Tianjin China TBI Center Nankai University Tianjin China

ISBN: (纸本)9789819609628

Gaze estimation, which involves perceiving human gaze directions, is the foundation of gaze analysis. It provides crucial clues for understanding human attention and intention. However, most existing methods are designed for constrained environments, which leads to a significant performance drop in unconstrained practical applications. In this work, we propose a supervised contrastive method for Unconstrained Adaptive Gaze Estimation (UAGE), which consists of an unconstrained gaze estimation method and a Gaze-guided Contrastive Domain Adaptation (GCDA) framework. Our method leverages the entire human body states and the uncertainty of gaze behaviors to robustly estimate gazes in unconstrained environments, rather than solely relying on head states. Additionally, we employ the GCDA framework to adapt the model to new domains, thereby improving its generalization ability. Experiment results show that our UAGE method has achieved state-of-the-art within-domain performance on the unconstrained GAFA dataset and has reduced the angular error by 14% compared to the baseline in cross-domain gaze estimation, with GAFA as the source domain and Gaze360 as the target domain. The code is available at https://***/youthhfor/***. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Domain adaptation Gaze estimation Unconstrained environment

来源：评论

学校读者我要写书评

暂无评论

Safe and Robust Human Following for Mobile Robots Based on Self-Avoidance MPC in Crowded Corridor Scenarios

Safe and Robust Human Following for Mobile Robots Based on S...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Song, Yinuo Zhang, Qianyi Hu, Zhengxi Liu, Jingtai Nankai University Robotics and Automatic Information System China Tianjin Key Laboratory of Intelligent Robotics China Nankai University Tbi Center China

ISBN: (纸本)9798350325706

The robot could provide convenient service for humans by following them. But it is not easy for the robot to follow a person while avoiding various objects in real crowded corridors. In this paper, a self-avoidance model predictive controller (SA-MPC) for human following in crowded environments is proposed. An obstacle avoidance optimization item is designed to enable the generalized controller to avoid collisions. Another adaptive method of selecting waypoints is introduced to make the robot move at the specific linear and angular velocities. We verified our method on the pedestrian simulation platform. Qualitative and quantitative simulations demonstrate that the proposed SA-MPC achieves a higher scene pass rate and improves safety and robustness in dense environments. Simulations are implemented in dense corridors and complex scenarios with random obstacles. SA-MPC can serve as a generalized controller for various mobile robots. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Experimental Validation of a Worm-Like Tensegrity Robot for In-Pipe Locomotion

引用

Journal of Bionic Engineering 2023年第2期20卷 515-529页

作者： Xiaolin Dai Yixiang Liu Wei Wang Rui Song Yibin Li Jie Zhao School of Control Science and Engineering Shandong UniversityJinan250061China Engineering Research Center of Intelligent Unmanned System of Ministry of Education Jinan250061China Shandong Research Institute of Industrial Technology Jinan250061China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin150080China

Traditional rigid-body in-pipe robots usually have complex and heavy structures with limited flexibility and *** soft in-pipe robots have great improvements in flexibility,they still have manufacturing difficulties due to their reliance on high-performance soft *** structure is a kind of self-stressed spatial structure consisting discrete rigid struts connected by a continuous net of tensional flexible strings,which combines the advantages of both rigid structures and soft *** applying tensegrity structures into robotics,this paper proposes a novel worm-like tensegrity robot for moving inside ***,a robot module capable of body deformation is designed based on the concept of tensegrity and its deformation performance is ***,the optimal parameters of the module are obtained based on the tensegrity *** deformation ability of the tensegrity module is tested ***,the worm-like tensegrity robot that can crawl inside pipes is developed by connecting three modules in *** performance and load capacity are tested on the prototype of the worm-like tensegrity robot by experiments of moving in horizontal pipe,vertical pipe,and elbow *** results demonstrate the effectiveness of the proposed design and suggest that the robot has high compliance,mobility,and adaptability although with simple structure and low cost.

关键词： Bio-inspired robot Soft robot application Tensegrity structure Pipe crawling

来源：评论

学校读者我要写书评

暂无评论

Squeezing More Past Knowledge for Online Class-Incremental Continual Learning

引用

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 722-736页

作者： Da Yu Mingyi Zhang Mantian Li Fusheng Zha Junge Zhang Lining Sun Kaiqi Huang the State Key Laboratory of Robotics and System Harbin Institute of Technology(HIT)Harbin 150080China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190 School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190the School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijing 100049 the CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai 200031China IEEE

Continual learning(CL)studies the problem of learning to accumulate knowledge over time from a stream of data.A crucial challenge is that neural networks suffer from performance degradation on previously seen data,known as catastrophic forgetting,due to allowing parameter *** this work,we consider a more practical online class-incremental CL setting,where the model learns new samples in an online manner and may continuously experience new ***,prior knowledge is unavailable during training and *** works usually explore sample usages from a single dimension,which ignores a lot of valuable supervisory *** better tackle the setting,we propose a novel replay-based CL method,which leverages multi-level representations produced by the intermediate process of training samples for replay and strengthens supervision to consolidate previous ***,besides the previous raw samples,we store the corresponding logits and features in the ***,to imitate the prediction of the past model,we construct extra constraints by leveraging multi-level information stored in the *** the same number of samples for replay,our method can use more past knowledge to prevent *** conduct extensive evaluations on several popular CL datasets,and experiments show that our method consistently outperforms state-of-the-art methods with various sizes of episodic *** further provide a detailed analysis of these results and demonstrate that our method is more viable in practical scenarios.

关键词： Catastrophic forgetting class-incremental learning continual learning(CL) experience replay

来源：评论

学校读者我要写书评

暂无评论

C2FNet: Coarse-to-Fine Keypoint Localization Network for Monocular 6D Object Pose Estimation

C2FNet: Coarse-to-Fine Keypoint Localization Network for Mon...

引用

2023 China Automation Congress, CAC 2023

作者： Sun, Jiahao Ma, Xin Li, Yibin Center for Robotics School of Control Science and Engineering Shandong University China Engineering Research Center of Intelligent Unmanned System Ministry of Education Jinan China

ISBN: (纸本)9798350303759

Estimating the 6D object pose from a singular RGB image is a fundamental task in the field of computer vision. Recent studies have demonstrated that keypoint-based methods exhibit remarkable efficacy. Such methodologies initially identify keypoints and subsequently deduce the object's pose by addressing a Perspective-n-Point (PnP) problem. Nonetheless., the prevalent approach of directly regressing the 2D coordinates of keypoints renders these methods sensitive to occlusions. Instead., we inaugurate a coarse-to-fine keypoint localization network (C2FNet)., where we utilize the predicted keypoint offsets from the first stage as input to deformable convolutional networks (DCN) in the second stage., to further capture geometric features and enhance spatial relationships between keypoints., thus outputting accurate and robust keypoint coordinates. Experiments indicate that the proposed approach surpasses existing advanced methods in terms of performance on the LINEMOD and Occlusion LINEMOD datasets. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Methods for Fixed-Wing Aircraft Control 9

Reinforcement Learning Methods for Fixed-Wing Aircraft Contr...

引用

9th International Conference on systems and Informatics, ICSAI 2023

作者： Li, Lun Zhang, Xuebo Wang, Yang Qian, Chenxu Zhao, Minghui Nankai University Institute of Robotics and Automatic Information System Tianjin Key Laboratory of Intelligent Robotics College of Artificial Intelligence Tianjin China Tianjin Municipal Data Management Center Tianjin China

ISBN: (纸本)9798350383706

In recent years, reinforcement learning (RL) has been widely researched for fixed-wing aircraft control, offering transformative potential for more adaptive, efficient, and autonomous flight operations. This paper presents a comprehensive analysis of the current state, advantages, challenges, and future prospects of employing RL in fixed-wing aircraft control. The advantages of RL include model-free, adaptive decision-making, and effectively solving complex nonlinear constraints, leading to increased efficiency and maneuverability in high-dynamic environments. However, significant challenges, such as the guarantee of stability and optimization, interpretability, and sim-to-real transferring, highlight areas necessitating further attention and development. Overcoming these challenges requires collaborative efforts among aviation experts, control theory experts, and machine learning researchers to ensure safe, reliable integration of RL in flight systems. As research and advancements continue, the RL holds promise for providing a more efficient, maneuverable, and autonomous strategy for controlling fixed-wing aircraft in the future. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Vision Sensor Fusion Localization and Navigation of Robot in Unstructured Environment

Multi-Vision Sensor Fusion Localization and Navigation of Ro...

引用

2023 China Automation Congress, CAC 2023

作者： Shang, Fuhao Zhou, Lelai Li, Yibin Zhang, Chen School of Control Science and Engineering Shandong University Center for Robotics Jinan250061 China Engineering Research Center of Intelligent Unmanned System Ministry of Education Jinan250061 China

ISBN: (纸本)9798350303759

Robots that have the ability to work in complex natural environments have broad application prospects. Focusing on the lack of autonomous navigation ability of the robot in the wild environment, this paper respectively proposes the improved localization and trajectory tracking methods. The multi-vision sensor fusion localization method is based on dual-factor graph optimization, which realizes the rapid processing of asynchronous sensor information. The dual-factor graph optimization can improve the localization accuracy and fault tolerance of the system under outdoor environments. Meanwhile, the multi-fine granularity MPC-based trajectory tracking method for unstructured terrain. Under the large-scale global path, a refined map is built around the robot. And the elevation difference is introduced to impose new constraints at the omni-directional velocity. The proposed methods in this study are implemented in actual environment. Experiments and simulations in representative terrain environments have verified the effectiveness of the improved methods. © 2023 IEEE.

关键词： Navigation

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：