检索结果-内蒙古大学图书馆

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

作者： Zhao, Guoyang Ma, Fulong Qi, Weiqing Liu, Ming Ma, Jun Robotics and Autonomous Systems Thrust Guangzhou China

ISBN: (纸本)9781665481090

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. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

CrackSegMamba: A Lightweight Mamba Model for Crack Segmentation

CrackSegMamba: A Lightweight Mamba Model for Crack Segmentat...

引用

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

作者： Qi, Weiqing Ma, Fulong Zhao, Guoyang Liu, Ming Ma, Jun Robotics and Autonomous Systems Thrust Guangzhou511453 China

ISBN: (纸本)9781665481090

Crack localization and segmentation are essential for infrastructure maintenance and safety assessments, enabling timely repairs and preventing structural failures. Despite advancements in deep learning, crack segmentation remains challenging due to the need for real-time performance and computational efficiency. Existing methods often rely on large, resource-intensive models, limiting their practical deployment. We introduce CrackSegMamba, a novel model featuring Channel-wise Parallel Mamba (CPM) Modules, which achieves state-of-the-art performance with fewer than 0.23 million parameters and just 0.7 GFLOPs. CrackSegMamba reduces computational cost by 40-fold and parameter count by nearly 100-fold compared to existing models, while maintaining comparable accuracy. These features make CrackSegMamba ideal for real-time applications. Additionally, we present Crack20000, an annotated dataset of 20,000 concrete crack images to support further research and validation. Evaluations on the Crack500 [1] and Crack20000 datasets demonstrate that CrackSegMamba delivers comparable accuracy to leading methods, with significantly reduced computational requirements. Project page is available at: https://***/view/cracksegmamba. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Characterizing Heterogeneous Car-Following Behaviors of Human Drivers in Mixed Traffic 4

Characterizing Heterogeneous Car-Following Behaviors of Huma...

引用

4th IEEE International Conference on Human-Machine systems, ICHMS 2024

作者： Sun, Meng Huang, Chunxi He, Dengbo Thrust Of Robotics And Autonomous Systems Guangzhou China Thrust Of Intelligent Transportation Guangzhou China

ISBN: (纸本)9798350315790

With an increasing number of autonomous vehicles (AVs) being tested and deployed on public roads, the sharing of the road between human-driven vehicles (HVs) and AVs will become inevitable. However, there is a lack of research on the interactions between HVs and AVs, particularly in terms of how HVs behave differently when following AVs compared to following HVs, and how this potential difference affects traffic safety and stability. To fill this gap, we utilized the Lyft dataset to investigate the variances between HV-following-AV and HV-following-HV scenarios. Hierarchical clustering was used to classify the driving styles of the following vehicles in all following events. Then, driving volatility measures and surrogate safety measures, i.e., speed volatility and reciprocal time-to-collision (reTTC) value, were used to compare the outcomes of different car-following events. The clustering results showed that human drivers exhibited four different car-following styles in the mixed traffic and when following AVs and HVs, drivers may exhibit different following styles. Compared to the leading HV, the leading AV resulted in a smaller TTC (i.e., a larger reTTC), regardless of the driving styles of the following HVs. When driving at low speeds, drivers had lower speed volatility when following AVs, indicating more stable traffic;while at high speed, when drivers were not sensitive to changes in the speed of the vehicle ahead, the leading AVs led to larger speed volatility. Future AV control algorithms should take the styles of the following HV into consideration to better optimize traffic stability and improve the safety of mixed traffic. © 2024 IEEE.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Test-Time Adaptation for Nighttime Color-Thermal Semantic Segmentation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 4893-4904页

作者： Liu, Yexin Zhang, Weiming Zhao, Guoyang Zhu, Jinjing Vasilakos, Athanasios V. Wang, Lin Robotics and Autonomous Systems Thrust Guangzhou511458 China Grimstad4879 Norway Artificial Intelligence Thrust Guangzhou511458 China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong999077 Hong Kong

The ability to scene understanding in adverse visual conditions, e.g., nighttime, has sparked active research for color-thermal semantic segmentation. However, it is essentially hampered by two critical problems: 1) the day-night gap of color images is larger than that of thermal images;and 2) the classwise performance of color images at night is not consistently higher or lower than that of thermal images. We propose the first test-time adaptation (TTA) framework, dubbed Night-TTA, to address the problems for nighttime color-thermal semantic segmentation without access to the source (daytime) data during adaptation. Our method enjoys three key technical parts. First, as one modality (e.g., color) suffers from a larger domain gap than that of the other (e.g., thermal), imaging heterogeneity refinement (IHR) employs an interaction branch on the basis of color and thermal branches to prevent cross-modal discrepancy and performance degradation. Then, class aware refinement (CAR) is introduced to obtain reliable ensemble logits based on pixel-level distribution aggregation of the three branches. In addition, we also design a specific learning scheme for our TTA framework, which enables the ensemble logits and three student logits to collaboratively learn to improve the quality of predictions during the testing phase of our Night-TTA. Extensive experiments show that our method achieves state-of-the-art (SoTA) performance with a 13.07% boost in mean intersection over union (mIoU). © 2020 IEEE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Fault-Tolerant IPM Considering Bidirectional Electromagnetic-Thermal Coupling Constraints 27

Design and Analysis of Fault-Tolerant IPM Considering Bidire...

引用

27th International Conference on Electrical Machines and systems, ICEMS 2024

作者： Ma, Yiming Su, Xiangdong Yin, Zhenxiao Zhang, Yujia Zhao, Hang Csg Pgc Energy Storage Research Institute Guangzhou511499 China Thrust of Robotics and Autonomous Systems Guangzhou510000 China

ISBN: (纸本)9784886864406

In this article, a five-phase interior permanent magnet motor (IPM) is designed and fabricated, featuring higher torque density and reduced torque ripple, making it suitable for demanding applications such as aviation electrification. The motor's performance is further evaluated through a bidirectional electromagnetic-thermal coupling analysis. Compared to separated electromagnetic and thermal analyses, the bidirectional approach provides more accurate assessments of the motor's electromagnetic behavior under temperature rise conditions. Additionally, the torque characteristics of the fault-tolerant IPM in its fault operation mode are analyzed, offering insights into the reliability of multiphase motors for aviation electrification. The research also examines the variations and disparity (19.98 % to 40 % electromagnetic torque deviation) of the electromagnetic characteristics under fault conditions. This analysis helps to depict the effects of motor faults on other subsystems in complicated aviation systems, offering further and a more comprehensive understanding of the design and operation challenges and impacts associated with multiphase motor faults in aviation electric propulsion systems (EPS). © 2024 The Institute of Electrical Engineers of Japan.

关键词： Permanent magnets

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 43

Motion Planning for an Underwater Swimming Manipulator Using...

引用

43rd Chinese Control Conference, CCC 2024

作者： Zhao, Yiwei Ma, Shugen Tianjin University School of Electrical and Information Engineering Tianjin300072 China Thrust of Robotics and Autonomous Systems Guangzhou511442 China

ISBN: (纸本)9789887581581

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. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Inverse kinematics

来源：评论

学校读者我要写书评

暂无评论

Integrated Intention Prediction and Decision-Making with Spectrum Attention Net and Proximal Policy Optimization 27

Integrated Intention Prediction and Decision-Making with Spe...

引用

27th IEEE International Conference on Intelligent Transportation systems, ITSC 2024

作者： Zhou, Xiao Meng, Chengzhen Liu, Wenru Peng, Zengqi Liu, Ming Ma, Jun Robotics and Autonomous Systems Thrust Guangzhou China The Hong Kong University of Science and Technology Division of Emerging Interdisciplinary Areas Hong Kong

ISBN: (纸本)9798331505929

For autonomous driving in highly dynamic environments, it is anticipated to predict the future behaviors of surrounding vehicles (SVs) and make safe and effective decisions. However, modeling the inherent coupling effect between the prediction and decision-making modules has been a longstanding challenge, especially when there is a need to maintain appropriate computational efficiency. To tackle these problems, we propose a novel integrated intention prediction and decision-making approach, which explicitly models the coupling relationship and achieves efficient computation. Specifically, a spectrum attention net is designed to predict the intentions of SVs by capturing the trends of each frequency component over time and their interrelations. Fast computation of the intention prediction module is attained as the predicted intentions are not decoded to trajectories in the executing process. Furthermore, the proximal policy optimization (PPO) algorithm is employed to address the non-stationary problem in the framework through a modest policy update enabled by a clipping mechanism within its objective function. On the basis of these developments, the intention prediction and decision-making modules are integrated through joint learning. Experiments are conducted in representative traffic scenarios, and the results reveal that the proposed integrated framework demonstrates superior performance over several deep reinforcement learning (DRL) baselines in terms of success rate, efficiency, and safety in driving tasks. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

CH-LSTTM: A Taxonomy of Traffic Hazards 4

CH-LSTTM: A Taxonomy of Traffic Hazards

引用

4th IEEE International Conference on Human-Machine systems, ICHMS 2024

作者： Yan, Song Huang, Chunxi He, Dengbo Thrust Of Robotics And Autonomous Systems Guangzhou China Hong Kong Thrust Of Intelligent Transportation Guangzhou China The Hong Kong University Of Science And Technology Department Of Civil And Environmental Engineering Hong Kong

ISBN: (纸本)9798350315790

During driving, drivers must interact with various objects in the highly dynamic driving environment, in which they need to perceive the traffic hazards and handle safety-critical scenarios. Previous studies have proved the importance of drivers' hazard perception skills and designed corresponding driver training programs. However, due to the lack of a suitable taxonomy for hazards, most driver training programs on hazard perception are simply a collection of various hazardous scenarios but do not guide drivers' hazard perception skills in a systematic way. The existing taxonomies of hazards were mainly based on the characteristics of hazards but did not take the hazard perception procedures into consideration, which can hardly be applied to improve drivers' hazard perception skills. Therefore, in this study, we proposed a taxonomy of traffic hazards based on an analysis of hazard perception procedures. Overall, a four-element taxonomy of traffic hazards (i.e., CH-LSTTM) was proposed, in which the Cues (single-element-based, multiple-element-based, and no-element-based), Hazards (visible vs. invisible), Link Strength (LS, which accounts for the uncertainty between the cues and the hazards during the hazard development process), and Time to Materialization (TTM, which indicates the imminence level of the hazard) were considered. We demonstrated the capability of the proposed taxonomy in depicting and categorizing realworld traffic hazards through a naturalistic driving case study. The proposed taxonomy can support the optimization of driver training programs to improve their hazard perception skills. © 2024 IEEE.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Enhance Planning with Physics-informed Safety Controller for End-to-end autonomous Driving

Enhance Planning with Physics-informed Safety Controller for...

引用

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

作者： Zhou, Hang Liu, Haichao Lu, Hongliang Ma, Jun Ji, Yiding Robotics and Autonomous Systems Thrust Systems Hub Guangzhou China School of Engineering The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering SAR Hong Kong Hong Kong Intelligent Transportation Thrust Systems Hub Guangzhou China

ISBN: (纸本)9781665481090

Recent years have seen a growing research interest in applications of Deep Neural Networks (DNN) on autonomous vehicle technology. The trend started with perception and prediction a few years ago and it is gradually being applied to motion planning tasks. Despite the performance of networks improve over time, DNN planners inherit the natural drawbacks of Deep Learning. Learning-based planners have limitations in achieving perfect accuracy on the training dataset and network performance can be affected by out-of-distribution problem. In this paper, we propose FusionAssurance, a novel trajectory-based end-to-end driving fusion framework which combines physics-informed control for safety assurance. By incorporating Potential Field into Model Predictive Control, FusionAssurance is capable of navigating through scenarios that are not included in the training dataset and scenarios where neural network fail to generalize. The effectiveness of the approach is demonstrated by extensive experiments under various scenarios on the CARLA benchmark. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis and Optimization of Unbalanced Magnetic Pull for Eccentric Doubly-Fed Induction Motor

Analysis and Optimization of Unbalanced Magnetic Pull for Ec...

引用

2024 International Conference on Electrical Machines, ICEM 2024

作者： Kang, Haoyu Wang, Jin Liu, Liyang Sun, Lu Li, Zequan Zhou, Libing Huazhong University of Science and Technology State Key Laboratory of Advanced Electromagnetic Technology Wuhan China Robotics and Autonomous Systems Thrust Guangzhou China

ISBN: (纸本)9798350370607

Due to the frequent switching of working conditions, the large doubly-fed induction motors (DFIMs) utilized in variable speed pumping units are subjected to intense hydraulic shock, thereby significantly increasing the risk of rotor eccentricity fault and posing a substantial threat to the safe operation of the motor. This paper proposes a method for suppressing the unbalanced magnetic force in DFIMs caused by eccentricity, through the injection of excitation compensation current in groups. Firstly, the air gap magnetic field of DFIMs with eccentricity is modeled using the subdomain method. Then, the optimal compensation current is efficiently calculated using the eccentric subdomain model in conjunction with the particle swarm optimization algorithm. Finally, the proposed method is implemented on a 10MW DFIM. By injecting the optimal compensation current, the unbalanced magnetic pulling force caused by eccentricity is effectively suppressed. The comparison with the finite element simulation results showed that the unbalanced magnetic pulling force is reduced by 81.6%. © 2024 IEEE.

关键词： Particle swarm optimization (PSO)

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：