检索结果-内蒙古大学图书馆

2025 IEEE/SICE International Symposium on System Integration, SII 2025

作者： Mukherjee, Sourajit Takaki, Takeshi Hiroshima University Smart Robotics Lab Graduate School of Advanced Science and Engineering Hiroshima Japan

ISBN: (纸本)9798331531614

Conductive polymer composites with piezoresistive properties have found extensive use in force sensing applications, such as strain gauges. Polylactic acid filled with carbon black nano-fillers is one such easily available and inexpensive material. The piezoresistive properties of conductive polymers have been shown to share an equivalence with the linear viscoelastic relationship between stress and strain. In this study, we examine six progressively complex resistive-viscoelastic models based on this relationship. After empirically determining the model parameters, we compared their stress prediction outputs using resistance data as input, which had been recorded while subjecting a 3D-printed conductive solid to a compressive force. We observed the model performances for two cases: when model parameters are determined from the complete test cycle and when they are determined phase-wise. Phase-wise coefficients showed a much better prediction accuracy and it was also observed that simpler models gave a better performance than more complex models. © 2025 IEEE.

关键词： Conductive materials

来源：评论

学校读者我要写书评

暂无评论

DiffUIE: Learning Latent Global Priors in Diffusion Models for Underwater Image Enhancement

引用

IEEE Transactions on Multimedia 2025年 27卷 2516-2529页

作者： Qing, Yuhao Liu, Si Wang, Hai Wang, Yueying Shanghai University School of Mechatronic Engineering and Automation Shanghai200444 China Beihang University Beijing100083 China Murdoch University School of Energy of Engineering and Energy Advanced Robotics and Autonomous Systems Lab MurdochWA6150 Australia

Underwater imagery often suffers from light attenuation and color distortion, resulting in images with low contrast and blurriness. Enhancing these images is crucial yet challenging due to the complex degradation and noise inherent in underwater environments. In this study, we introduce a novel diffusion model, termed Underwater Image Enhancement(UIE) Diffusion, which leverages a global feature prior for effective underwater image enhancement. To our knowledge, this is the inaugural application of a diffusion model to the task of underwater image enhancement, setting a new benchmark in performance. Our approach begins with the introduction of a global feature prior to augment the diffusion model, mitigating the impact of noise and distortion during training. We then incorporate an underwater image degradation model to facilitate the learning of mappings between high-quality and degraded underwater images. To address over-enhancement caused by high-frequency components, we employ scaling factors to modulate the influence of frequency features during diffusion. Additionally, we enhance the model's stability during inference by integrating a backward diffusion process into its training. Comprehensive evaluations on multiple public datasets demonstrate that UIE Diffusion surpasses existing state-of-the-art methods in both subjective outcomes and objective assessments. © 1999-2012 IEEE.

关键词： Underwater imaging

来源：评论

学校读者我要写书评

暂无评论

Learning to Model Diverse Driving Behaviors in Highly Interactive Autonomous Driving Scenarios With Multiagent Reinforcement Learning

引用

IEEE Systems Journal 2025年第1期19卷 317-326页

作者： Liu, Weiwei Hu, Wenxuan Jing, Wei Lei, Lanxin Gao, Lingping Liu, Yong Zhejiang University The Advanced Perception on Robotics and Intelligent Learning Lab College of Control Science and Engineering Hangzhou310027 China Huzhou Institute of Zhejiang University Zhejiang 310027 China Alibaba DAMO Academy Autonomous Driving Lab Zhejiang 311121 China Huzhou University College of Information Engineering Zhejiang 313000 China

Autonomous vehicles trained through multiagent reinforcement learning (MARL) have shown impressive results in many driving scenarios. However, the performance of these trained policies can be impacted when faced with diverse driving styles and personalities, particularly in highly interactive situations. This is because conventional MARL algorithms usually operate under the assumption of fully cooperative behavior among all agents and focus on maximizing team rewards during training. To address this issue, we introduce the personality modeling network (PeMN), which includes a cooperation value function and personality parameters to model the varied interactions in high-interactive scenarios. The PeMN also enables the training of a background traffic flow with diverse behaviors, thereby improving the performance and generalization of the ego vehicle. Our extensive experimental studies, which incorporate different personality parameters in high-interactive driving scenarios, demonstrate that the personality parameters effectively model diverse driving styles and that policies trained with PeMN demonstrate better generalization than traditional MARL methods. © 2007-2012 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

SigmoidGS: To Guide Depth More Effectively

SigmoidGS: To Guide Depth More Effectively

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Chow, Hongai Shen, Licheng Wang, Lingyun Zhang, Tong Wang, Mengqiu Han, Yuxing Shenzhen International Graduate School Tsinghua University Shenzhen China Zero-Zero Lab Zero-Zero Robotics Inc. Hangzhou China Advanced Technology Institue Zhejiang University Hangzhou China

ISBN: (纸本)9798350368741

The recent success of 3D Gaussian Splatting (3DGS) on the task of novel view synthesis has amazed every one with its photorealistic results with high training and rendering speed. This paper aims to increase the interpretability of the model in both geometric attribute and appearances by a simple yet effective method: lifting constraints on color features of each splat. This enables more accurate guidance from monocular depth prediction models and strengthen the ability of model to reconstruct scene geometry. Experiments shows that this effectively reduces indeterminacy of the reconstruction problem and allows better understanding of the scene structure and individual, especially in scenes with limited viewpoints, while maintaining high-fidelity rendering even in some of the uncovered views. © 2025 IEEE.

关键词： 3D reconstruction Gaussian Splatting Neural Radiance Field Neural Rendering Novel View Synthesis

来源：评论

学校读者我要写书评

暂无评论

Artificial Marker-Aided Localization for Service Robots in Visually Repetitive Environments

Artificial Marker-Aided Localization for Service Robots in V...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： DongKi Noh Jeongsik Choi Seungmin Baek Advanced Robotics Lab. CTO Division LG Electronics Seoul Republic of Korea

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

In recent years, simultaneous localization and mapping (SLAM) has emerged as a critical technique for enabling the autonomous capabilities of service robots. However, practical SLAM applications often face significant performance challenges in visually and geometrically repetitive environments, which impede accurate localization. To address these challenges and ensure reliable localization for service robots, this work utilizes artificial markers, specifically AprilTags and ArUco tags. This paper presents a method that strategically leverages these markers, using them in minimal quantities while maximizing their localization impact. By leveraging the Kimera-VIO and TagSLAM algorithms, the proposed approach offers several contributions: (a) consistent pose estimation through a lightweight pose-graph optimizer suitable for resource-constrained systems; (b) an efficient strategy for optimizing the placement of artificial markers within target environments; and (c) validation of the proposed method in real-world environments, including warehouses and offices, using a commercially available service robot. This approach provides a viable industrial solution for improving localization performance in commercial service robots.

关键词： Location awareness Performance evaluation Simultaneous localization and mapping Service robots Semantics Pose estimation Reliability Faces Consumer electronics Logistics

来源：评论

学校读者我要写书评

暂无评论

Tactile Sensing Improves Handshake between Humans and Robots 16th

Tactile Sensing Improves Handshake between Humans and Robot...

引用

16th International Conference on Social robotics, ICSR + AI 2024

作者： Pequeno-Zurro, Alejandro Chicca, Elisabetta Palinko, Oskar Lab Zernike Institute for Advanced Materials University of Groningen Groningen Netherlands University of Groningen Groningen Netherlands SDU Robotics Maersk Mc-Kinney Moller Institute University of Southern Denmark Campusvej 55 Odense Denmark

ISBN: (纸本)9789819635245

Shaking hands as a gesture of greeting is a common social practice observed in numerous cultures. This behavior is acquired during the early years of childhood. We constructed a humanoid robot with the objective of greeting children and their parents at a hospital. During the robot’s initial deployment, children frequently extended their hands to grasp the robot’s hand in order to initiate a handshake. Nevertheless, social robots, including our own, require preparation for such activities. To address this challenge, we implemented an interactive handshaking protocol for our robot, which employs tactile sensors embedded in the right hand to adapt and detect the optimal timing for each phase of the handshake. In a user study, the adaptive handshake was compared with two other protocols, one with constant timing and the second with passive, compliant control, which expected the users to lead the activity. The results of statistical tests revealed that the participants expressed a preference for the adaptive robot, perceiving its behavior as more natural, pleasant, and reactive. In conclusion, it was found that the implementation of handshaking procedures on social robots with arms can facilitate more natural interaction and deepen trust. Furthermore, insights are provided regarding prospective enhancements to the platform, including integrating neuromorphic sensing technologies for sensorimotor tactile control. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Social robots

来源：评论

学校读者我要写书评

暂无评论

A Data-driven Comparison of Resistive-Viscoelastic Models for a 3D-Printed Conductive Solid

A Data-driven Comparison of Resistive-Viscoelastic Models fo...

引用

IEEE/SICE International Symposium on System Integration

作者： Sourajit Mukherjee Takeshi Takaki Smart Robotics Lab Graduate School of Advanced Science and Engineering Hiroshima University Hiroshima Japan

ISBN: (数字)9798331531614

ISBN: (纸本)9798331531621

关键词： Solid modeling Force System integration Predictive models Solids Strain measurement Polymers Stress Piezoresistance Strain

来源：评论

学校读者我要写书评

暂无评论

Impact of nano fillers on the mechanical and rheological behaviour of polydimethylsiloxane based nanocomposite elastomer

引用

Ceramics International 2025年第14期51卷 18852-18864页

作者： Mandal, Swaroop Kumar Kumar, Rahul Pradhan, Asisha Ranjan Kumar, Deepak Kumar, Satish Department of Automation and Robotics Dr. DY Patil Institute of Technology Pimpri Pune411018 India Advanced Composite and Smart Material Laboratory Department of Mechanical Engineering National Institute of Technology Jamshedpur 831014 India Department of Mechanical Engineering Parala Maharaja Engineering College Odisha 761003 India Rheology Lab Department of Mechanical Engineering National Institute of Technology Jamshedpur 831014 India

In this work, an advanced elastomer which is reinforced with nanocomposite of reduced graphene oxide and calcium carbonate (rGO/CaCO3) is fabricated. Its mechanical and rheological properties are investigated experimentally. The effect of rGO/CaCO3 nanocomposite was experimentally investigated using Dynamical Mechanical Analysis (DMA), Tensile test and Rheological test. The results indicate improved adhesion and physical strengthening effect between rGO/CaCO3 nanocomposite and the PDMS, that leads towards the decrement of extensional loss factor and hence increment in the extensional storage modulus. Also, the ultimate tensile stress and percentage elongation of the elastomers was found to be increased with increasing wt. % of rGO in CaCO3. It has been observed that 5 % rGO/CaCO3 nanocomposite in PDMS exhibits a higher tensile stress of 0.81 ± 0.040 MPa in comparison to pure PDMS (0.48 ± 0.024 MPa). The bare PDMS material has a maximum force of 12.94 ± 0.647 N, but the 5 % rGO/CaCO3/PDMS nanocomposite can tolerate a maximum force of 22.1 ± 1.105 N. Furthermore, the rheological properties of the material were altered, resulting in an increase in the viscosity of PDMS as the percentage (%) of rGO concentration in the rGO/CaCO3 nanocomposite increased. The presence of CaCO3 increases viscosity, however when 4 % (wt. %) rGO is added to CaCO3, the viscosity decreases compared to other filler concentrations in the elastomers. © 2025 Elsevier Ltd and Techna Group S.r.l.

关键词： Polydimethylsiloxane

来源：评论

学校读者我要写书评

暂无评论

Improving overlapping quality of 316L stainless steel fabricated by multi-laser powder bed fusion through optimizing non-remelting scanning strategy

引用

Journal of Manufacturing Processes 2025年 145卷 333-345页

作者： Jiang, Renwu Yang, Yongqiang Wang, Han Bai, Yuchao Liu, Linqing Zheng, Zhijun Chen, Jie Yan, Xingchen Yang, Chao Jin, Gang Wang, Di School of Mechanical and Automotive Engineering South China University of Technology Guangzhou510640 China School of Robotics and Advanced Manufacture Harbin Institute of Technology Shenzhen518052 China Institute of Intelligent Manufacturing Guangdong Academy of Sciences Guangdong Guangzhou510070 China National Engineering Laboratory for Modern Materials Surface Engineering Technology The Key Lab of Guangdong for Modern Surface Engineering Technology Guangdong Institute of New Materials Guangzhou510651 China

Multi-laser powder bed fusion (ML-PBF) has emerged as a promising solution for achieving large-scale functional parts with high resolution based on powder bed fusion technology, particularly in high-end fields (e.g. aerospace). However, ML-PBF processes are often challenged by issues like poor surface quality, internal defects, and low mechanical properties within the multi-laser overlap region. Therefore, it is necessary to investigate a multi-laser scanning strategy to develop an effective solution for controlling overlap region quality. In this work, two non-remelting scanning strategies, sequential scanning and reverse scanning, with different scanning angles (0°, 45°, 90°) were proposed to improve the ML-PBF quality. The results show that the orthogonal sequential scanning strategy with a scanning angle of 0° resulted in a flatter surface and fewer internal defects in the overlap region. Subsequently, the influence mechanism of overlap region width (ORW) under the above-mentioned scanning strategy on surface morphology, pore defects, microstructure, and mechanical properties was systematically investigated. The sample with an ORW of 1.5 mm displayed the highest ultimate tensile strength of 625.0 MPa and elongation of 36.2 %, which is comparable to the counterparts fabricated by single-laser powder bed fusion with a negligible reduction of ~2.1 % in the tensile strength. Moreover, the fracture occurred away from the overlap region during tensile testing, which means that the suggested non-remelting scanning strategy successfully enhances the quality of the overlap region. Generally, this study provides significant insight into the quality controlling in the overlap region of ML-PBF parts and theoretical guidance for enhancing the ability to fabricate large-scale parts based on powder bed fusion technology. © 2025 The Society of Manufacturing Engineers

关键词： Tensile strength

来源：评论

学校读者我要写书评

暂无评论

NavG: Risk-Aware Navigation in Crowded Environments Based on Reinforcement Learning with Guidance Points

arXiv

引用

arXiv 2025年

作者： Zhang, Qianyi Luo, Wentao Liu, Boyi Zhang, Ziyang Wang, Yaoyuan Liu, Jingtai Institute of Robotics and Automatic Information System Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin China Advanced Computing and Storage Lab Huawei 2012 Lab China Department of Electronic and Computer Engineering The Kong Kong University of Science and Technology Hong Kong

Motion planning in navigation systems is highly susceptible to upstream perceptual errors, particularly in human detection and tracking. To mitigate this issue, the concept of guidance points—a novel directional cue within a reinforcement learning-based framework—is introduced. A structured method for identifying guidance points is developed, consisting of obstacle boundary extraction, potential guidance point detection, and redundancy elimination. To integrate guidance points into the navigation pipeline, a perception-to-planning mapping strategy is proposed, unifying guidance points with other perceptual inputs and enabling the RL agent to effectively leverage the complementary relationships among raw laser data, human detection and tracking, and guidance points. Qualitative and quantitative simulations demonstrate that the proposed approach achieves the highest success rate and near-optimal travel times, greatly improving both safety and efficiency. Furthermore, real-world experiments in dynamic corridors and lobbies validate the robot’s ability to confidently navigate around obstacles and robustly avoid pedestrians. © 2025, CC BY.

关键词： Travel time

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：