检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yan, Danqi Gao, Qing Qian, Yuepeng Chen, Xinxing Fu, Chenglong Leng, Yuquan Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems the Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities China Department of Mechanical and Energy Engineering Southern University of Science and Technology Shenzhen518055 China School of Electronics and Communication Engineering Sun Yat-sen University Shenzhen518107 China

Three-dimensional (3D) human pose estimation using a monocular camera has gained increasing attention due to its ease of implementation and the abundance of data available from daily life. However, owing to the inherent depth ambiguity in images, the accuracy of existing monocular camera-based 3D pose estimation methods remains unsatisfactory, and the estimated 3D poses usually include much noise. By observing the histogram of this noise, we find each dimension of the noise follows a certain distribution, which indicates the possibility for a neural network to learn the mapping between noisy poses and ground truth poses. In this work, in order to obtain more accurate 3D poses, a Diffusion-based 3D Pose Refiner (D3PRefiner) is proposed to refine the output of any existing 3D pose estimator. We first introduce a conditional multivariate Gaussian distribution to model the distribution of noisy 3D poses, using paired 2D poses and noisy 3D poses as conditions to achieve greater accuracy. Additionally, we leverage the architecture of current diffusion models to convert the distribution of noisy 3D poses into ground truth 3D poses. To evaluate the effectiveness of the proposed method, two state-of-the-art sequence-to-sequence 3D pose estimators are used as basic 3D pose estimation models, and the proposed method is evaluated on different types of 2D poses and different lengths of the input sequence. Experimental results demonstrate the proposed architecture can significantly improve the performance of current sequence-to-sequence 3D pose estimators, with a reduction of at least 10.3% in the mean per joint position error (MPJPE) and at least 11.0% in the Procrustes MPJPE (P-MPJPE). Copyright © 2024, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

RAVE: A Framework for Radar Ego-Velocity Estimation

RAVE: A Framework for Radar Ego-Velocity Estimation

引用

International Conference on Multisensor Fusion and Integration for Intelligent systems (MFI)

作者： Vlaho-Josip Štironja Luka Petrović Juraj Peršić Ivan Marković Ivan Petrović Laboratory for Autonomous Systems and Mobile Robotics (LAMOR) University of Zagreb Faculty of Electrical Engineering and Computing Zagreb Croatia Calirad d.o.o. Zagreb Croatia

ISBN: (数字)9798350368031

ISBN: (纸本)9798350368048

State estimation is an essential component of autonomous systems, usually relying on sensor fusion that integrates data from cameras, LiDARs and IMUs. Recently, radars have shown the potential to improve the accuracy and robustness of state estimation and perception, especially in challenging environmental conditions such as adverse weather and low-light scenarios. In this paper, we present a framework for ego-velocity estimation, which we call RAVE, that relies on 3D automotive radar data and encompasses zero velocity detection, outlier rejection, and velocity estimation. In addition, we propose a simple filtering method to discard infeasible egovelocity estimates. We also conduct a systematic analysis of how different existing outlier rejection techniques and optimization loss functions impact estimation accuracy. Our evaluation on three open-source datasets demonstrates the effectiveness of the proposed filter and a significant positive impact of RAVE on the odometry accuracy. Furthermore, we release an opensource implementation of the proposed framework for radar ego-velocity estimation accompanied with a ROS interface.

关键词： Accuracy Three-dimensional displays Systematics Filtering Radar Trajectory Odometry State estimation Optimization Automotive engineering

来源：评论

学校读者我要写书评

暂无评论

A Novel Bio-Inspired Quadruped Crawling Robot with Movable Waist

A Novel Bio-Inspired Quadruped Crawling Robot with Movable W...

引用

ASME/IFToMM International Conference on Reconfigurable Mechanisms and Robots, ReMAR

作者： Ruiqin Wang Hao Wu Jian S. Dai The School of Mechanical Engineering Hebei University of Technology Tianjin China School of Mechanical Engineering Hebei University of Technology Tianjin China The Shenzhen Key Laboratory of Intelligent Robotics and Flexible Manufacturing Systems Southern University of Science and Technology Shenzhen China Mechanisms and Robotics Centre for Robotics Research King's College London UK

ISBN: (数字)9798350395969

ISBN: (纸本)9798350395976

Traditional quadruped robots usually have rigid and fixed torso, which limits their mobility and flexibility. Robots with movable waist can improve the flexibility and environmental adaptability of robots. In this paper, a novel bionic crawling robot with movable waist is proposed. The movable waist innovatively adopts an anti-parallelogram mechanism. At the same time, the waist adopts a double-layer structure design to increase the stability and bearing capacity of the robot. The kinematics model of the robot is derived based on the D-H parameter method. Bas ed on the Monte Carlo method, the toe workspace of the leg is obtained in Matlab software. The results show that due to the torsion of the movable waist, the toe workspace is significantly expanded, and the robot can achieve faster and smoother motion. A prototype was made based on 3D printing technology for experimental verification.

关键词： Legged locomotion Monte Carlo methods Robot kinematics Prototypes Three-dimensional printing Stability analysis Software

来源：评论

学校读者我要写书评

暂无评论

Bridging VLM and KMP: Enabling Fine-grained robotic manipulation via Semantic Keypoints Representation

arXiv

引用

arXiv 2025年

作者： Zhu, Junjie Liu, Huayu Wang, Jin Wen, Bangrong Huang, Kaixiang Li, Xiaofei Zhang, Haiyun Lu, Guodong The State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou310058 China Zhejiang Key Laboratory of Industrial Big Data and Robot Intelligent Systems Zhejiang University Hangzhou310058 China School of Robotics Ningbo University of Technology Ningbo315211 China Robotics Research Center of Yuyao City Ningbo315400 China

From early Movement Primitive (MP) techniques to modern Vision-Language Models (VLMs), autonomous manipulation has remained a pivotal topic in robotics. As two extremes, VLM-based methods emphasize zero-shot and adaptive manipulation but struggle with fine-grained planning. In contrast, MP-based approaches excel in precise trajectory generalization but lack decision-making ability. To leverage the strengths of the two frameworks, we propose VL-MP, which integrates VLM with Kernelized Movement Primitives (KMP) via a low-distortion decision information transfer bridge, enabling fine-grained robotic manipulation under ambiguous situations. One key of VL-MP is the accurate representation of task decision parameters through semantic keypoints constraints, leading to more precise task parameter generation. Additionally, we introduce a local trajectory feature-enhanced KMP to support VL-MP, thereby achieving shape preservation for complex trajectories. Extensive experiments conducted in complex real-world environments validate the effectiveness of VL-MP for adaptive and fine-grained manipulation. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Kidney Stone Segmentation Based on Segmentation Anything Model for Robotic-Assisted Endoscope Navigation 16th

Zero-Shot Kidney Stone Segmentation Based on Segmentation A...

引用

16th International Conference on Intelligent robotics and Applications, ICIRA 2023

作者： Meng, Hui Chen, Lingkai Zhu, Shiqiang Fei, Chentao Zhang, Yong Zheng, Miaojuan Han, Jianda Song, Wei School of Intelligent Science and Technology Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences 1 Sub-lane Xiangshan Hangzhou310024 China Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Hangzhou311100 China Hangzhou ElephantChain Network Technology Co. Ltd. Hangzhou China Faculty of Mechanical Engineering and Automation Zhejiang Sci-Tech University Hangzhou310018 China College of Artificial Intelligence and Tianjin Key Laboratory of Intelligent Robotics Institute of Robotics and Automatic Information Systems Nankai University Tianjin300350 China

ISBN: (纸本)9789819964888

Biomedical robotics has had a significant impact on flexible ureteroscopy (FURS) for the management of nephrolithiasis. The biomedical robots provide a suitable and safe platform for FURS. However, operating the robots expertly still represents a challenge for surgeons. Vision-based navigation is an effective means to simplify the operations of robots by surgeons, which has great potential to improve surgical efficiency. To achieve vision-based navigation, the localization of kidney stones in endoscopic images is the first step. In this paper, we propose a stone segmentation method (SSM) based on zero-shot learning, which consists of segmentation anything model (SAM), an image preprocessing module, and a mask postprocessing module. The SAM segments all objects in endoscopic images, which lack semantic information. The preprocessing module is designed to suppress interference of reflective area in endoscopic images, and the mask postprocessing module is used to filter noise masks. The experimental results on our collected endoscopic images indicate that our method achieves close accuracy on stone segmentation compared with supervised U-Net and VGG_U-Net, which significantly outperforms the Ostu and the SAM. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

BlueLink: A Bidirectional Optical Modem for High-Speed Underwater Communication

BlueLink: A Bidirectional Optical Modem for High-Speed Under...

引用

IEEE International Workshop on Metrology for the Sea;Learning to Measure Sea Health Parameters (MetroSea)

作者： Ivar Bjørgo Saksvik Vahid Hassani Antonio Pascoal Alex Alcocer Department of Mechanical Electronic and Chemical Engineering Oslo Metropolitan University Oslo Norway Laboratory of Robotics and Systems in Engineering and Science (LARSyS) University of Lisbon Lisbon Portugal

Free space optical communication has emerged as a highly promising solution for enabling high-speed data transmission in underwater environments. The increasing demand for telemetry in unmanned underwater vehicles requires a significant increase in bandwidth capacity, surpassing the limitations of conventional acoustic technologies that currently dominate this domain. In this paper, we introduce a compact and energy-efficient optical modem for high-speed wireless underwater communication. The proposed modem offers bidirectional data transfer capabilities through the integration of transmitting LEDs and a photodiode receiver for light pulse detection, with data processing efficiently managed by an FPGA. The modem utilizes a software-defined architecture, enabling re-configurable modulation schemes and streamlining the implementation of signal filtering and processing through software, as opposed to traditional analog circuitry. Experiments conducted in a 3-meter seawater pool demonstrate a throughput of 2 Mbit/s.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A 5G-Based Switching Method between a Local Controller and an Edge Controller 6

A 5G-Based Switching Method between a Local Controller and a...

引用

6th International Conference on Intelligent robotics and Control engineering, IRCE 2023

作者： Wang, Xiulian Lin, Jinggao Jin, Xi Xia, Changqing Xu, Chi College of Automation and Electrical Engineering Shenyang Ligong University China Chinese Academy of Sciences Key Laboratory of Networked Control Systems Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9798350326338

With the rapid development of edge computing, industrial automation has evolved a two-layer distributed computing architecture, including local controllers communicating through wired networks and edge controllers communicating wirelessly. The edge controllers in existing studies use WIFI, which has a limited working distance and requires independent network deployment, so they are unsuitable for future large-scale complex industrial production. At present, 5G technology is undergoing rapid development in the field of industrial automation, with wide coverage and excellent mobility, gradually becoming suitable for future large-scale and complex industrial production scenarios. Therefore, this paper proposed an SW5G method based on 5G, which combined the local controller with the edge controller. The controllers were switched according to the constantly changing 5G network transmission delay, thereby optimizing the overall system control performance. Finally, simulation experiments demonstrated good control performance of SW5G in various network scenarios. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Path Planning with Potential Field-Based Obstacle Avoidance in a 3D Environment by an Unmanned Aerial Vehicle

arXiv

引用

arXiv 2023年

作者： Batinovic, Ana Goricanec, Jurica Markovic, Lovro Bogdan, Stjepan University of Zagreb Faculty of Electrical Engineering and Computing LARICS Laboratory for Robotics and Intelligent Control Systems Unska 3 Zagreb10000 Croatia

In this paper we address the problem of path planning in an unknown environment with an aerial robot. The main goal is to safely follow the planned trajectory by avoiding obstacles. The proposed approach is suitable for aerial vehicles equipped with 3D sensors, such as LiDARs. It performs obstacle avoidance in real time and on an on-board computer. We present a novel algorithm based on the conventional Artificial Potential Field (APF) that corrects the planned trajectory to avoid obstacles. To this end, our modified algorithm uses a rotation-based component to avoid local minima. The smooth trajectory following, achieved with the MPC tracker, allows us to quickly change and re-plan the UAV trajectory. Comparative experiments in simulation have shown that our approach solves local minima problems in trajectory planning and generates more efficient paths to avoid potential collisions with static obstacles compared to the original APF method. © 2023, CC BY-SA.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Lower Limb Joint Torque Estimation via Bayesian Regularized Backpropagation Neural Networks

Lower Limb Joint Torque Estimation via Bayesian Regularized ...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Jyotindra Narayan Hassène Gritli Santosha K Dwivedy Department of Mechanical Engineering Mechatronics and Robotics Laboratory Indian Institute of Technology Guwahati Guwahati Assam India Laboratory of Robotics Informatics and Complex Systems (RISC Lab - LR16ES07) National Engineering School of Tunis University of Tunis El Manar Le Belvédère Tunis Tunisia

Prior gait analysis has played a crucial role in assessing overall health and well-being, particularly in individuals of different age groups. Nevertheless, acquiring gait data has necessitated the in-person presence of participants, incurring potential expenses. We introduce a deep learning technique called Bayesian regularized backpropagation neural network (BR-BPNN) to estimate joint torques in lower-limb motion based on anthropometric data and joint movements. The study collects joint movement data from 40 healthy participants (25 males and 15 females) spanning ages 7 to 65, utilizing an established motion-capture system. The input data encompassed various parameters such as age, gender, total body mass, height, thigh length, calf length, ankle-foot length, thigh mass, calf mass, ankle mass, and joint angles for the hip, knee, and ankle. The output data included joint torques calculated for a simplified leg model using the inverse dynamics method derived from the Euler-Lagrangian principle. We presented the conceptual details of the proposed BR-BPNN model and contrast model named Levenberg-Marquardt-based BPNN (LM-BPNN). Performing a comparative analysis, the results revealed that the BR-BPNN model (R train = 0.985, R test = 0.955) excelled in accurately estimating joint torques compared to the LM-BPNN model (R train = 0.973, R test = 0.924). Furthermore, the BR-BPNN model is found to be effective by 87.19%, 77.87%, and 72.73% in estimating hip, knee, and ankle joint torques for a 51-year-old male subject from the testing dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Object Graph Affordance Network: Goal-Oriented Planning through Learned Compound Object Affordances

arXiv

引用

arXiv 2023年

作者： Girgin, Tuba Ugur, Emre Department of Computer Engineering Bogazici University Istanbul Turkey Robotics and Autonomous Systems Laboratory TUBITAK BIL-GEM Kocaeli41470 Turkey

—Learning object affordances is an effective tool in the field of robot learning. While the data-driven models investigate affordances of single or paired objects, there is a gap in the exploration of affordances of compound objects composed of an arbitrary number of objects. We propose the Multi-Object Graph Affordance Network which models complex compound object affordances by learning the outcomes of robot actions that facilitate interactions between an object and a compound. Given the depth images of the objects, the object features are extracted via convolution operations and encoded in the nodes of graph neural networks. Graph convolution operations are used to encode the state of the compounds, which are used as input to decoders to predict the outcome of the object-compound interactions. After learning the compound object affordances, given different tasks, the learned outcome predictors are used to plan sequences of stack actions that involve stacking objects on top of each other, inserting smaller objects into larger containers and passing through ring-like objects through poles. We showed that our system successfully modeled the affordances of compound objects that include concave and convex objects, in both simulated and real-world environments. We benchmarked our system with a baseline model to highlight its advantages. © 2023, CC BY.

关键词： Convolution

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：