检索结果-内蒙古大学图书馆

SimLiquid: A Simulation-Based Liquid Perception Pipeline for Robot Liquid Manipulation

JOURNAL OF FIELD ROBOTICS 2025年

作者： Huang, Yan Zhang, Jiawei Yu, Ran Li, Shoujie Ding, Wenbo Tsinghua Univ Shenzhen Int Grad Sch Shenzhen Ubiquitous Data Enabling Key Lab Shenzhen Peoples R China RISC V Int Open Source Lab Shenzhen Peoples R China

Transparent liquid volume estimation is crucial for robot manipulation tasks, such as pouring. However, estimating the volume of transparent liquids is a challenging problem. Most existing methods primarily focus on data collection in the real world, and the sensors are fixed to the robot body for liquid volume estimation. These approaches limit both the timeliness of the research process and the flexibility of perception. In this paper, we present SimLiquid20k, a high-fidelity synthetic data set for liquid volume estimation, and propose a YOLO-based multi-task network trained on fully synthetic data for estimating the volume of transparent liquids. Extensive experiments demonstrate that our method can effectively transfer from simulation to the real world. In scenarios involving changes in background, viewpoint, and container variations, our approach achieves an average error of 5% in real-world volume estimation. In addition, our work conducts two application experiments integrating with GPT-4, showcasing the potential of our method in service robotics. The accompanying videos and supporting Information are available at .

关键词： liquid estimation LLM Sim2Real transparent object

来源：评论

学校读者我要写书评

暂无评论

A Bio-Inspired Event-Driven Mechanoluminescent Visuotactile Sensor for intelligent interactions

引用

ADVANCED FUNCTIONAL MATERIALS 2025年第20期35卷

作者： Sou, Kit-Wa Chan, Wang-Sing Lei, Kai-Chong Wang, Zihan Li, Shoujie Peng, Dengfeng Ding, Wenbo Tsinghua Univ Shenzhen Int Grad Sch Shenzhen 518055 Peoples R China Univ Calif Berkeley Dept Mech Engn Berkeley CA 94709 USA Shenzhen Univ Coll Phys & Optoelect Engn Shenzhen Key Lab Intelligent Opt Measurement & Det Key Lab Optoelect Devices & SystMinist Educ & Gua Shenzhen 518060 Peoples R China RISC V Int Open Source Lab Shenzhen 518055 Peoples R China

Event-driven sensors are essential for real-time applications, yet the integration of current technologies faces limitations such as high cost, complex signal processing, and vulnerability to noise. This work introduces a bio-inspired mechanoluminescence visuotactile sensor that enables standard frame-based cameras to perform event-driven sensing by emitting light only under mechanical stress, effectively acting as an event trigger. Drawing inspiration from the biomechanics of canine teeth, the sensor utilizes a rod-patterned array to enhance mechanoluminescent signal sensitivity and expand the contact surface area. In addition, a machine learning-enabled algorithm is designed to accurately analyze the interaction-triggered mechanoluminescence signal in real-time. The sensor is integrated into a quadruped robot's mouth interface, demonstrating enhanced interactive capabilities. The system successfully classifies eight interactive activities with an average accuracy of 92.68%. Comprehensive tests validate the sensor's efficacy in capturing dynamic tactile signals and broadening the application scope of robots in interaction with the environment.

关键词： event-driven sensing human-machine interfaces mechanoluminescence quadruped robots visuotactile sensing

来源：评论

学校读者我要写书评

暂无评论

Flexible nanogenerators for intelligent robotics: design, manufacturing, and applications

引用

intERNATIONAL JOURNAL OF EXTREME MANUFACTURING 2025年第2期7卷 022012-022012页

作者： Zhao, Hongfa Ruan, Liguang Wang, Zihan Shu, Mingrui Lyu, Chuqiao Lakshan, Bulathsinghala Rameesh Ishara, Dharmasena Wu, Changsheng Ding, Wenbo Tsinghua Univ Tsinghua Berkeley Shenzhen Inst Shenzhen Int Grad Sch Shenzhen 518055 Peoples R China Loughborough Univ Wolfson Sch Mech Elect & Mfg Engn Loughborough LE11 3TU England Natl Univ Singapore Dept Mat Sci & Engn Singapore 117575 Singapore RISC V Int Open Source Lab Beijing 518055 Peoples R China

The embodied artificial intelligence (EAI) is driving a significant transformation in robotics, enhancing their autonomy, efficiency and evolution ability. In this rapidly evolving technological landscape, robots need numerous sensors to realize high levels of perception, precision, safety, adaptability, and intelligence. Triboelectric and piezoelectric sensors address these needs by providing high sensitivity, flexibility, and the capability of self-powered sensing, leveraging the revolutionary nature of nanogenerators to convert mechanical energy into electrical energy on basis of Maxwell's displacement current. These sensors surpass externally powered passive sensors by offering continuous operation, reduced maintenance, and the capability to function in remote or harsh environments. The integration of EAI with advanced nanogenerators sensors could position robotics to perform autonomously, efficiently, and safely, paving the way for innovative applications in various domains such as industrial automation, environmental monitoring, healthcare, and smart homes. In this paper, the fundamental theories, design, manufacturing, and applications of nanogenerators are comprehensively reviewed as a foundation of the advanced sensors for intelligent robotics in the new era, with three major application fields: sensing (including human-robot interaction, exteroceptive sensing and proprioceptive sensing), computing and actuating. Perspectives are addressed for nanogenerators systems in future development. Fundamentals of TENGs and PENGs are *** design of materials and structures for nanogenerators is *** techniques for nanogenerators are *** for robotic sensing, computing, and actuating systems are demonstrated.

关键词： triboelectric/piezoelectric nanogenerators robotics manufacturing

来源：评论

学校读者我要写书评

暂无评论

Construction of a ferroelectric material BiOIO3 photoelectrocatalytic anode by triboelectric-photo coupling effect for degradation of antibiotics

引用

NANO ENERGY 2025年 139卷

作者： Qin, Yuanchu Xu, Qinghao Gong, Junhao Huang, Jie Wang, Wen-Long Lyu, Chuqiao Ding, Wenbo Tsinghua Univ Tsinghua Shenzhen Int Grad Sch Guangdong Prov Engn Res Ctr Urban Water Recycling Key Lab Microorganism Applicat & Risk Control Shen Shenzhen 518055 Peoples R China Tsinghua Univ Inst Environm & Ecol Tsinghua Shenzhen Int Grad Sch Shenzhen Key Lab Ecol Remediat & Carbon Sequestrat Shenzhen 518055 Peoples R China Tsinghua Univ Inst Data & Informat Shenzhen Int Grad Sch Shenzhen Ubiquitous Data Enabling Key Lab Shenzhen 518055 Peoples R China Peking Univ Sch Environm & Energy Shenzhen Grad Sch Shenzhen 518055 Peoples R China RISC V Int Open Source Lab Shenzhen 518055 Peoples R China

Antibiotic, particularly from tetracycline derivatives, poses severe environmental and health challenges due to their stability, bioaccumulation, and resistance to traditional wastewater treatment methods. Advanced oxidation processes, including photocatalysis, offer potential solutions but are hindered by limitations like rapid recombination of photogenerated electron-hole pairs. This study introduces an innovative photoelectrocatalytic system combining BiOIO3 (BIO) with a triboelectric nanogenerator (TENG). BIO, with its unique ferroelectric properties and nanosheet morphology, enhances charge carrier separation and reduces recombination, achieving significantly improved degradation rates compared to conventional photocatalysts. TENG provides a sustainable power source by converting mechanical energy into electrical energy, modulating charge dynamics in BIO through band bending and alignment with its intrinsic electric field. The integration of TENG and BIO creates a synergistic effect, enhancing the generation of reactive species (RSs) and achieving degradation efficiencies 1.59 times higher than photocatalysis alone. The system demonstrates robust, scalable, and environmentally friendly performance, offering a promising solution for efficient antibiotic removal in water treatment applications.

关键词： Photoelectrocatalysis Triboelectric nanogenerator (TENG) Triboelectric-photo coupling effect Electric field modulates Antibiotics

来源：评论

学校读者我要写书评

暂无评论

Contactless Triboelectric Sensing for Real-Time 3D Motion Recognition in Human-Computer interaction

引用

ADVANCED ELECTRONIC MATERIALS 2025年第0期

作者： Xu, Qinghao Gong, Junhao Chen, Jiayi Zhang, Yimeng Zhao, Hongfa Yin, Jiaqi Zhao, Runze Lyu, Chuqiao Ding, Wenbo Wu, Changsheng Tsinghua Univ Inst Data & Informat Shenzhen Int Grad Sch Shenzhen Ubiquitous Data Enabling Key Lab Shenzhen 518055 Peoples R China Harbin Inst Technol Sch Future Technol Harbin 150001 Peoples R China RISC V Int Open Source Lab Shenzhen 518055 Peoples R China Natl Univ Singapore Dept Mat Sci & Engn Singapore 117575 Singapore Natl Univ Singapore Dept Elect & Comp Engn Singapore 117583 Singapore Natl Univ Singapore Inst Hlth Innovat & Technol Singapore 117599 Singapore Natl Univ Singapore Inst Hlth 1 Singapore 117456 Singapore

In the rapidly advancing fields of artificial intelligence and the internet of Things, there is a growing need for human-computer interaction (HCI) solutions that are not only intuitive but also efficient and easy to use. Triboelectric nanogenerators present a promising approach to developing wireless human-machine interfaces, offering advantages such as simple operating principles and flexible, adaptable designs. This study introduces an HCI system that leverages a contactless triboelectric detector (CTD) to classify complex motion patterns in 3D space. The CTD system consists of a contactless sensing panel, a silicone rubber finger sleeve, a signal acquisition circuit, and a mobile terminal, which together enable the seamless acquisition and classification of weak wireless signals. One of the key benefits of the system is its lack of active energy consumption, making it highly energy-efficient. Additionally, its simple structure and ease of deployment make it an attractive option for various applications. Experimental results illustrate that the proposed system has significant potential for interactive perception in industrial environments. With a motion recognition accuracy of 99.33%-including for intricate motions such as spiral curves-this system demonstrates its potential as a next-generation solution for wireless HCI systems.

关键词： triboelectric sensor motion recognition contactless sensing

来源：评论

学校读者我要写书评

暂无评论

Blockwise compression of transformer-based models without retraining

引用

NEURAL NETWORKS 2024年 171卷 423-428页

作者： Dong, Gaochen Chen, W. TensorChip Beijing Peoples R China Tsinghua Berkeley Shenzhen Inst RISC V Int Open Source Lab Shenzhen Peoples R China

Transformer-based models, exemplified by GPT-3, ChatGPT, and GPT-4, have recently garnered considerable attention in both academia and industry due to their promising performance in general language tasks. Nevertheless, these models typically involve computationally encoding processes, and in some cases, decoding processes as well, both of which are fundamentally large-scale matrix multiplication. These operations bring the inevitable challenges of massive computation resources and huge memory footprint, usually requiring at least 1023 FLOPs and hundreds of gigabytes, respectively. A common method to address this issue is to reduce the computational and memory requirements by applying layerwise quantization to the transformer, replacing the usual fp32 data type with a low-bit equivalent. Unfortunately, this method often leads to decreased model accuracy and necessitates time-consuming retraining. Such retraining not only requires fine-tuning skills but also substantial computational resources, posing challenges for users. To specifically tackle these issues, we propose BCT, a framework of blockwise compression for transformers without retraining, aiming to facilitate model deployment. Unlike layerwise compression methods, BCT achieves finer compression of the entire transformer by operating blockwise. This method mitigates data distribution deviation caused by quantization, eliminating the requirement for retraining. BCT effectively compresses all components of the model, including but not limited to the embedding, matrix multiplication, GELU, Softmax, layer normalization, and intermediate results. In a case study, an efficient model is compressed by BCT achieving up to 7.988x compression. Subsequently, we also evaluate it on several General Language Understanding Evaluation (GLUE) datasets. Experimental results on the majority of GLUE benchmark demonstrate the effectiveness of our method, as BCT achieves less than a 0.9% degradation in accuracy compared to the more

关键词： Transformer Compression Blockwise Noretraining

来源：评论

学校读者我要写书评

暂无评论

A Domain-Specific Supercomputer for Training Deep Neural Networks

引用

COMMUNICATIONS OF THE ACM 2020年第7期63卷 67-78页

作者： Jouppi, Norman P. Yoon, Doe Hyun Kurian, George Li, Sheng Patil, Nishant Laudon, James Young, Cliff Patterson, David Google Mountain View CA 94043 USA Google ML Accelerator Optimizat Scale Mountain View CA USA Univ Calif Berkeley Grad Sch Berkeley CA USA RISC V Int Open Source Lab Berkeley CA USA RISC V Int Open Source Lab Shenzhen Peoples R China

Google's TPU supercomputers train deep neural networks 50x faster than general-purpose supercomputers running a high-performance computing benchmark.

关键词： Supercomputers

来源：评论

学校读者我要写书评

暂无评论

Beyond Aggregation: Efficient Federated Model Consolidation with Heterogeneity-AdaptiveWeights Diffusion 24

Beyond Aggregation: Efficient Federated Model Consolidation ...

引用

33rd ACM international Conference on Information and Knowledge Management (CIKM)

作者： Li, Jiaqi Qu, Xiaoyang Ding, Wenbo Zhao, Zihao Wang, Jianzong Ping An Technol Shenzhen Co Ltd Shenzhen Peoples R China Tsinghua Univ Shenzhen Int Grad Sch Shenzhen Peoples R China Tsinghua Univ RISC V Int Open Source Lab Shenzhen Int Grad Sch Tsinghua Berkeley Shenzhen Inst Shenzhen Peoples R China RISC V Int Open Source Lab Shenzhen Peoples R China

ISBN: (纸本)9798400704369

As the internet of Things (IoT) evolves, the need for enhanced data-sharing to improve edge device performance has led to the adoption of Federated Learning (FL) for data privacy and optimized data utilization. However, communication costs in FL remain a significant challenge. Traditional methods focus on client enhancements but overlook server-side aggregation, potentially increasing client computation loads. In response, we introduce a novel method, FedDiff, which utilizes diffusion models for generating model weights on FL servers, replacing traditional aggregation methods. Our approach, tailored for heterogeneous environments, significantly improves communication efficiency, achieving faster convergence and robust performance against weight noise in rigorous tests.

关键词： Federated Learning integration and Aggregation Diffusion Models

来源：评论

学校读者我要写书评

暂无评论

TGF-Net: Sim2Real Transparent Object 6D Pose Estimation Based on Geometric Fusion

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2023年第6期8卷 3867-3874页

作者： Yu, Haixin Li, Shoujie Liu, Houde Xia, Chongkun Ding, Wenbo Liang, Bin Tsinghua Shenzhen Int Grad Sch Shenzhen 518055 Peoples R China RISC V Int Open Source Lab Shenzhen 518055 Peoples R China Tsinghua Univ Nav & Control Res Ctr Dept Automat Beijing 100084 Peoples R China

Transparent objects are a common part of daily life, but their unique optical properties make estimating their 6D pose a challenging task. In this letter, we propose TGF-Net, a monocular instance-level 6D pose estimation method for transparent objects based on geometric fusion. TGF-Net learns the edge features and surface fragments of transparent objects as intermediate features and reduces the influence of appearance changes on the 6D pose estimation of transparent objects by fusing rich geometric features in the network. Moreover, we propose an approach for generating high-fidelity large-scale synthetic datasets of transparent objects using Blender and use this approach to generate a synthetic dataset Trans6D-32 K. Trans6D-32 K contains rendered RGB images and poses information about transparent objects in a variety of different backgrounds, perspectives, and lighting conditions. To evaluate the performance of TGF-Net on 6D pose estimation of transparent objects, we compare with multiple related works on the dataset Trans6D-32 K. TGF-Net can be trained entirely on synthetic datasets without fine-tuning and applied directly to real-world scenarios. Multiple challenging real-scene experiments demonstrate the good performance of TGF-Net, while grasping experiments demonstrate the application value of TGF-Net in transparent object manipulation.

关键词： Pose estimation Feature extraction Lighting Synthetic data Grasping Task analysis Three-dimensional displays Deep learning for visual perception data sets for robotic vision perception for grasping and manipulation

来源：评论

学校读者我要写书评

暂无评论

Point-Wise Vibration Pattern Production via a Sparse Actuator Array for Surface Tactile Feedback

Point-Wise Vibration Pattern Production via a Sparse Actuato...

引用

IEEE international Conference on Robotics and Automation (ICRA)

作者： Li, Xiaosa Zhao, Runze Lu, Chengyue Xiao, Xiao Ding, Wenbo Tsinghua Univ Tsinghua Shenzhen Int Grad Sch Tsinghua Berkeley Shenzhen Inst Shenzhen Peoples R China RISC V Int Open Source Lab Shenzhen 518055 Peoples R China

ISBN: (纸本)9798350384581;9798350384574

Surface vibration tactile feedback is capable of conveying various semantic information to humans via handheld electronic devices, such as smartphones, touch panels, and game controllers. However, covering the entire contacting surface of the device with a dense arrangement of actuators can affect its normal use. Determining how to produce desired vibration patterns at any contact point with only a few sparse actuators deployed on the surface of the handheld device remains a significant challenge. In this work, we develop a tactile feedback board in the size of a smartphone with only five actuators, and achieve the precise production of vibration patterns that can focus at any desired position on the board. Specifically, we investigate the vibration characteristics of a single passive coil actuator and construct its vibration pattern model for any position on the feedback board surface. Optimal phase and amplitude modulation, determined using the simulated annealing algorithm, is employed with five actuators in a sparse array. The vibration patterns from all actuators are superimposed linearly to synthetically generate different onboard vibration energy distributions for tactile sensing. Experiments demonstrated that point-wise vibration pattern production on our tactile board achieved an average level of about 0.9 in the Structural Similarity Index Measure (SSIM) evaluation, when compared to the ideal single-point-focused target vibration pattern. Four point-wise patterns focused on the top, bottom, left, and right parts of the tactile board were applied, to guide continuous directional movements without visual assistance, which shows significant implications for machine-assisted cognition based on vibration tactile feedback.

关键词： Simulated annealing

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：