检索结果-内蒙古大学图书馆

Design of a Tendon-Actuated Foldable Wheeled-Legged Hybrid Mobile Robot with high load-bearing capacity

学校读者我要写书评

暂无评论

Design of a Tendon-Actuated Foldable Wheeled-Legged Hybrid M...

International Conference on Control, Automation, robotics and Vision (ICARCV)

作者： Yinan Yang Chongyang Zhang Wenfu Xu School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Shenzhen P.R. China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

ISBN: (纸本)9781665476881

Mobile robots that can carry heavy loads play an important role in transporting and exploring in unstructured environment. However, there are some problems existing in conventional motor direct-drive robots such as excessive joint torque and unfoldable legs when they are under heavy loads. This paper proposes a tendon-actuated foldable wheeled-legged robot with high load-bearing capacity. A spreader is attached to the knee joint so that the output torque of the motor can be amplified by pulling the end of the spreader with a cable. The single and double fixed pulleys are used to reduce the required cable tension and avoid the interference of different cables, which can better achieve the folding of legs. In addition, the statics and kinematics of the tendon-actuated leg and the formulas for calculating the required tension and motor torque, as well as the relationship between foot velocity, joint speed, and motor speed are given. Finally, Matlab is used for simulation analysis, and it is found that the joint torques required for the tendon actuation are lower than for the direct actuation at the same joint angles.

关键词： Legged locomotion Knee Torque Pulleys Kinematics Mechanical cables Static analysis

A Fabric-Based Soft Elbow Exosuit with Autonomous Anchoring Straps

学校读者我要写书评

暂无评论

A Fabric-Based Soft Elbow Exosuit with Autonomous Anchoring ...

IEEE International Conference on Soft robotics (RoboSoft)

作者： Yexun Wei Dezhi Yang Miao Feng Jianing Sun Guoying Gu Robotics Institute School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai China Zhiyuan College Shanghai Jiao Tong University Shanghai China Meta Robotic Institute Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798331520205

ISBN: (纸本)9798331520212

Fabric-based soft exosuits offer promising solutions for elbow rehabilitation and assistance owing to their lightweight and flexible nature. However, existing designs usually apply continuous compression on the arm to anchor, whether actuated or not, potentially causing discomfort, numbness, and impaired blood circulation. Here, we present a fabric-based soft elbow exosuit that autonomously adjusts its compressing forces on the arm, harnessing a fabric-lattice artificial muscle (FAM) combined with two X-crossing anchoring straps (XASs) (worn on the upper arm and forearm). When the FAM is deflated, two XASs fit loosely on the arm. When the FAM is inflated, it contracts axially to assist elbow flexion and elongates laterally to actuate two XASs to anchor concurrently. Experimental results show that the FAM can output a contraction force up to 110 N, the XASs can generate a compressing force of 9.7 N (approximately 3 kPa), and the exosuit can provide a considerable torque up to 3.5 N•m, capable of assisting an elbow model to flex to 95°. These results demonstrate that our elbow exosuit provides a new approach to autonomous anchoring while achieving elbow flexion assistance effectively.

关键词： Flexible printed circuits Torque Force Buildings Arms Soft robotics Elbow Motion control Contracts Load modeling

Unsupervised Learning of 3D Scene Flow from Monocular Camera

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Guangming Tian, Xiaoyu Ding, Ruiqi Wang, Hesheng Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai 200240 China

Scene flow represents the motion of points in the 3D space, which is the counterpart of the optical flow that represents the motion of pixels in the 2D image. However, it is difficult to obtain the ground truth of scene flow in the real scenes, and recent studies are based on synthetic data for training. Therefore, how to train a scene flow network with unsupervised methods based on real-world data shows crucial significance. A novel unsupervised learning method for scene flow is proposed in this paper, which utilizes the images of two consecutive frames taken by monocular camera without the ground truth of scene flow for training. Our method realizes the goal that training scene flow network with real-world data, which bridges the gap between training data and test data and broadens the scope of available data for training. Unsupervised learning of scene flow in this paper mainly consists of two parts: (i) depth estimation and camera pose estimation, and (ii) scene flow estimation based on four different loss functions. Depth estimation and camera pose estimation obtain the depth maps and camera pose between two consecutive frames, which provide further information for the next scene flow estimation. After that, we used depth consistency loss, dynamic-static consistency loss, Chamfer loss, and Laplacian regularization loss to carry out unsupervised training of the scene flow network. To our knowledge, this is the first paper that realizes the unsupervised learning of 3D scene flow from monocular camera. The experiment results on KITTI show that our method for unsupervised learning of scene flow meets great performance compared to traditional methods Iterative Closest Point (ICP) and Fast Global Registration (FGR). The source code is available at: https://***/IRMVLab/3DUnMonoFlow. Copyright © 2022, The Authors. All rights reserved.

关键词： Unsupervised learning

When Shannon Meets Nonstochastic Information: Communication and Estimation

学校读者我要写书评

暂无评论

IEEE Transactions on Automatic Control 2025年

作者： Zhang, Wentao Zuo, Zhiqiang Zhao, Rui Wang, Yijing Hu, Guoqiang Zhang, Hui Wang, Yaonan Hunan University School of Robotics Changsha410082 China Nanyang Technological University Continental-NTU Corporate Lab Singapore639798 Singapore Tianjin University Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information Engineering Tianjin300072 China Nanyang Technological University School of Electrical and Electronic Engineering Singapore639798 Singapore National Engineering Research Center for Robot Visual Perception and Control Changsha410082 China Hunan University College of Electrical and Information Engineering Changsha410082 China

This notes focuses on the issue of whether or not the state of a plant can be estimated when the inputs of communication channel involve noise and disturbance simultaneously. It turns out to calculate the maximum capacity of stationary memoryless multiple quasi-access channel under nonstochastic information theory. It is shown that the maximum information rate over such a channel is determined by a convex hull spanned by the zero-error capacities which are specified on the underlying sample spaces. Moreover, the state of a plant could be estimated provided that the maximal information rate is strictly greater than the topology entropy. © 1963-2012 IEEE.

关键词： Communication channels (information theory)

MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yaning Wang, Tianyi Yu, Zitong Gao, Zan Shen, Linlin Chen, Shengyong Jinan250353 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Jinan250014 China The Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia, highlighting the urgent need for robust and generalizable face forgery detection (FFD) techniques. Although existing approaches mainly capture face forgery patterns using image modality, other modalities like fine-grained noises and texts are not fully explored, which limits the generalization capability of the model. In addition, most FFD methods tend to identify facial images generated by GAN, but struggle to detect unseen diffusion-synthesized ones. To address the limitations, we aim to leverage the cutting-edge foundation model, contrastive language-image pre-training (CLIP), to achieve generalizable diffusion face forgery detection (DFFD). In this paper, we propose a novel multi-modal fine-grained CLIP (MFCLIP) model, which mines comprehensive and fine-grained forgery traces across image-noise modalities via language-guided face forgery representation learning, to facilitate the advancement of DFFD. Specifically, we devise a fine-grained language encoder (FLE) that extracts fine global language features from hierarchical text prompts. We design a multi-modal vision encoder (MVE) to capture global image forgery embeddings as well as fine-grained noise forgery patterns extracted from the richest patch, and integrate them to mine general visual forgery traces. Moreover, we build an innovative plug-and-play sample pair attention (SPA) method to emphasize relevant negative pairs and suppress irrelevant ones, allowing cross-modality sample pairs to conduct more flexible alignment. Extensive experiments and visualizations show that our model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

An RRT-Based Motion Planning Method for Hyper-Redundant Manipulators in Confined Spaces

学校读者我要写书评

暂无评论

An RRT-Based Motion Planning Method for Hyper-Redundant Mani...

IEEE International Conference on robotics and Biomimetics

作者： Jiangqin Deng Ziqing Li Yang Zheng Guoying Gu State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China Meta Robotics Institute Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781665481106

Hyper-redundant manipulators have redundant degrees of freedom, bringing additional difficulties to the motion planning. Generally, existing motion planning methods generate paths without considering joint angle limitation of hyper-redundant manipulators. And the generated paths are discretized, leading to discrete errors. In this paper, we present an autonomous motion planner to generate paths, which can be followed by hyper-redundant manipulators with analytical solutions. Starting from the ending pose in the workspace, the rapidly exploring random tree can expand to multiple entrances with limited curvature of arc segments, which ensures that the joint angle limitation is satisfied. Meanwhile, the generated path consists of arc segments, which makes the generated paths can be followed with analytical solutions. Several simulations are conducted to demonstrate the aforementioned advantages. For further validation of the planner's effectiveness, a hyper-redundant manipulator system is used to follow the generated path with follow-the-leader motion.

关键词： Motion segmentation Biomimetics Biological system modeling Soft robotics Aerospace electronics Manipulators Planning

Collaborative Perception Datasets for Autonomous Driving: A Review

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Naibang Shang, Deyong Gong, Yan Hu, Xiaoxi Song, Ziying Yang, Lei Huang, Yuhan Wang, Xiaoyu Lu, Jianli Beijing100083 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China State Key Laboratory of Intelligent Green Vehicle and Mobility Tsinghua University Beijing100084 China Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence School of Computer Science and Technology Beijing Jiaotong University China School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore School of Mechatronics Engineering Harbin Institute of Technology 92 West Dazhi St. Harbin China Department of Electronic & Electrical Engineering University of Bath United Kingdom

Collaborative perception has attracted growing interest from academia and industry due to its potential to enhance perception accuracy, safety, and robustness in autonomous driving through multi-agent information fusion. With the advancement of Vehicle-to-Everything (V2X) communication, numerous collaborative perception datasets have emerged, varying in cooperation paradigms, sensor configurations, data sources, and application scenarios. However, the absence of systematic summarization and comparative analysis hinders effective resource utilization and standardization of model evaluation. As the first comprehensive review focused on collaborative perception datasets, this work reviews and compares existing resources from a multi-dimensional perspective. We categorize datasets based on cooperation paradigms, examine their data sources and scenarios, and analyze sensor modalities and supported tasks. A detailed comparative analysis is conducted across multiple dimensions. We also outline key challenges and future directions, including dataset scalability, diversity, domain adaptation, standardization, privacy, and the integration of large language models. To support ongoing research, we provide a continuously updated online repository of collaborative perception datasets and related literature: https://***/frankwnb/Collaborative-Perceptio n-Datasets-for-Autonomous-Driving. © 2025, CC BY-SA.

关键词： Sensor data fusion

Active Virtual Mass Micro-Vibration Isolation Control Method based on Two-Parameter Acceleration Feedback 15

学校读者我要写书评

暂无评论

Active Virtual Mass Micro-Vibration Isolation Control Method...

15th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2021

作者： Wang, Jing Wang, Lei Li, Junzhong Yang, Yuanyuan Bian, Yujian Zhou, Bin School of instrumentation science and engineering Harbin Institute of Technology Harbin China Chinese Academy of Sciences Shenzhen Key Laboratory of Minimally Invasive Surgical Robotics and System Shenzhen China Heilongjiang Research Institute of Territory's Spatial Planning Harbin China

ISBN: (纸本)9781665444910

External interference is an important factor affecting the accuracy and stability of precision equipment. An active micro-vibration isolation control method is proposed and used in active vibration control to suppress external interference in this paper. This method is based on two-parameter acceleration feedback, which splits the acceleration feedback gain into two parameters, one on the front path and one on the feedback path. Compared with the traditional acceleration feedback, the proposed method not only increases the virtual mass of the system to reduce the natural frequency, but also suppresses the excessive motor output in the vibration isolation system simultaneously. Simulation results proved the effectiveness of the proposed two-parameter acceleration feedback control method in preventing excessive motor output, and experimental results confirm its capacity to reduce the natural frequency of the system. © 2021 IEEE.

关键词： Natural frequencies

Multi-kernel Correntropy Regression: Robustness, Optimality, and Application on Magnetometer Calibration

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Shilei Chen, Yihan Lou, Yunjiang Shi, Dawei Li, Lijing Shi, Ling The Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong The State Key Laboratory of Robotics and System School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Shenzhen518055 China The School of Automation Beijing Institute of Technology China The School of Information and Control Engineering China University of Mining and Technology China

This paper investigates the robustness and optimality of the multi-kernel correntropy (MKC) on linear regression. We first derive an upper error bound for a scalar regression problem in the presence of arbitrarily large outliers and state that the kernel bandwidth plays an important role in minimizing the lowest upper error bound. Then, we find that the proposed MKC is related to a specific heavy-tail distribution, where its head shape is consistent with the Gaussian distribution but its tail shape is heavy-tailed, and the extent of heavy-tail is controlled by the kernel bandwidth. It becomes a Gaussian distribution when the bandwidth is infinite, which allows one to tackle both Gaussian and non-Gaussian problems without explicitly investigating the noise distributions. To explore the optimal underlying distribution parameters, an expectation-maximization-like (EM) algorithm is developed to estimate the parameter vectors and the distribution parameters in an alternating manner. The results show that our algorithm can achieve equivalent performance compared with the traditional linear regression under Gaussian noise, and it significantly outperforms the conventional method under heavy-tailed noise. Both numerical simulations and experiments on a magnetometer calibration application verify the effectiveness of the proposed method. Note to Practitioners-The goal of this paper is to enhance the accuracy of conventional linear regression in handling outliers while maintaining its optimality under Gaussian assumptions. Our algorithm is formulated under the maximum likelihood estimation (MLE) framework, assuming the regression residuals follow a type of heavy-tailed noise distribution with an extreme case of Gaussian. The degree of the heavy tail is explored alternatingly using an Expectation-Maximization (EM) algorithm which converges very quickly. The robustness and optimality of the proposed approach are investigated and compared with the traditional approaches. Both th

关键词： Linear regression