检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Feng, Yi Guo, Zizhan Chen, Qijun Fan, Rui The Department of Control Science & Engineering The College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems Shanghai Institute of Intelligent Science and Technology The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China

Unsupervised monocular depth estimation frameworks have shown promising performance in autonomous driving. However, existing solutions primarily rely on a simple convolutional neural network for ego-motion recovery, which struggles to estimate precise camera poses in dynamic, complicated real-world scenarios. These inaccurately estimated camera poses can inevitably deteriorate the photometric reconstruction and mislead the depth estimation networks with wrong supervisory signals. In this article, we introduce SCIPaD, a novel approach that incorporates spatial clues for unsupervised depth-pose joint learning. Specifically, a confidence-aware feature flow estimator is proposed to acquire 2D feature positional translations and their associated confidence levels. Meanwhile, we introduce a positional clue aggregator, which integrates pseudo 3D point clouds from DepthNet and 2D feature flows into homogeneous positional representations. Finally, a hierarchical positional embedding injector is proposed to selectively inject spatial clues into semantic features for robust camera pose decoding. Extensive experiments and analyses demonstrate the superior performance of our model compared to other state-of-the-art methods. Remarkably, SCIPaD achieves a reduction of 22.2% in average translation error and 34.8% in average angular error for camera pose estimation task on the KITTI Odometry dataset. Our source code is available at https://***/SCIPaD. Copyright © 2024, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Few Shot Object Detection Based on Graph Attention network

Few Shot Object Detection Based on Graph Attention Network

引用

Pattern Recognition and Machine Learning (PRML), IEEE International Conference on

作者： Rou Ding Yu Zhang State Key Laboratory of Industrial Control Technology Zhejiang University of Control Science and Engineering Zhejiang China Key Laboratory of Collaborative sensing and autonomous unmanned systems of Zhejiang Province Zhejiang China

Few shot object detection is a challenging task in computer vision, as it involves detecting objects from a small number of examples. This makes it difficult for traditional object detection methods to generalize well to new classes or scenes. In this paper, we propose a siamese neural network model that utilizes the power of Faster RCNN for few shot object detection. The network takes in support and query datasets and extracts both support and query features. To supplement category information between various support features, we use Pearson similarity to enhance the features and extract support prototypes. We propose a graph attention network that can perform association matching between support prototype and proposals. Through this network, we facilitate information exchange between support features and query features, which helps to supplement the information of query images. We divide the training process into two stages. In the first stage, we use a large amount of basic category data to train the basic detection ability. In the second stage, we further train our model on few shot novel class and base class mixed datasets to improve its generalization performance. Experimental results on the public Pascal VOC dataset demonstrate that our proposed method achieves state-of-the-art few shot object detection performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Trust Recognition in Human-Robot Cooperation Using EEG

Trust Recognition in Human-Robot Cooperation Using EEG

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Caiyue Xu Changming Zhang Yanmin Zhou Zhipeng Wang Ping Lu Bin He Department of Control Science and Engineering College of Electronics and Information Engineering Tongji University Shanghai China National Key Laboratory of Autonomous Intelligent Unmanned Systems Shanghai China Frontiers Science Center for Intelligent Autonomous Systems Shanghai China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Collaboration between humans and robots is becoming increasingly crucial in our daily life. In order to accomplish efficient cooperation, trust recognition is vital, empowering robots to predict human behaviors and make trust-aware decisions. Consequently, there is an urgent need for a generalized approach to recognize human-robot trust. This study addresses this need by introducing an EEG-based method for trust recognition during human-robot cooperation. A human-robot cooperation game scenario is used to stimulate various human trust levels when working with robots. To enhance recognition performance, the study proposes an EEG Vision Transformer model coupled with a 3-D spatial representation to capture the spatial information of EEG, taking into account the topological relationship among electrodes. To validate this approach, a public EEG-based human trust dataset called EEGTrust is constructed. Experimental results indicate the effectiveness of the proposed approach, achieving an accuracy of 74.99% in slice-wise cross-validation and 62.00% in trial-wise cross-validation. This outperforms baseline models in both recognition accuracy and generalization. Furthermore, an ablation study demonstrates a significant improvement in trust recognition performance of the spatial representation. The source code and EEGTrust dataset are available at https://***/CaiyueXu/EEGTrust.

关键词： Adaptation models Computer vision Solid modeling Accuracy Source coding Brain modeling Transformers

来源：评论

学校读者我要写书评

暂无评论

X-Tacformer : Spatio-tempral Attention Model for Tactile Recognition

X-Tacformer : Spatio-tempral Attention Model for Tactile Rec...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jiarui Hu Yanmin Zhou Zhipeng Wang Xin Li Yongkang Jiang Bin He Department of Control Science and Engineering College of Electronics and Information Engineering Tongji University Shanghai China National Key Laboratory of Autonomous Intelligent Unmanned Systems Shanghai China Frontiers Science Center for Intelligent Autonomous Systems Shanghai China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Recently, tactile sensing has attracted great interests in robotics, especially for exploring unstructured objects. Sensor arrays play an important role in the exploration, which generates rich spatio-temporal information. In this work, we propose an efficient tactile recognition model, X-Tacformer. This model pays attention to both spatial and temporal features of tactile sequences from sensor arrays, which is verified by four public datasets, Ev-Objects, Ev-Containers, Augment8000 and BioTac-Dos. Comparative studies show that our model has resulted in a significant improvement of the recognition accuracy by 0.0223, 0.1416, 0.2735 and 0.1592 in these datasets. In order to verify its performances on dataset with rich spatio-temporal features, a self-designed dataset, ALU-Textures, was constructed with 10 fabrics from everyday textiles, aiming to extend the data collection action modes of current datasets by simulating human rubbing movements with the thumb and index fingers of an Allegro hand. Our model also demonstrates efficient salient feature learning capabilities on ALU-Textures, which is further augmented by tactile data augmentation methods.

关键词： Image recognition Accuracy Three-dimensional displays Biological system modeling Thumb Robot sensing systems Data augmentation

来源：评论

学校读者我要写书评

暂无评论

A bi-level optimization approach for joint rack sequencing and storage assignment in robotic mobile fulfillment systems

引用

Science China(Information Sciences) 2023年第11期66卷 127-149页

作者： Xiang SHI Fang DENG Sai LU Yunfeng FAN Lin MA Jie CHEN Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing Institute of Technology Chongqing Innovation Center Zhejiang Cainiao Supply Chain Management Co. Ltd. Shanghai Research Institute for Intelligent Autonomous Systems

This paper studies a novel rack scheduling problem with multiple types of multiple storage locations(RS-MTMS), which can decide the retrieval sequence of racks and assign each rack a storage location after visiting a picking station. A major challenge in RS-MTMS is that the storage assignment problem and the retrieval sequence decision are closely coupled. If the RS-MTMS is solved directly, the storage assignment scheme and the retrieval sequence of racks are generally generated separately, thus resulting in poor performance. To overcome this difficulty, we propose a bi-level optimization approach for jointly optimizing the storage assignment and retrieval sequence(Bi JSR). In Bi JSR, the storage assignment problem is solved by variable neighborhood search(VNS) in the upper-level optimization. Effective candidate modes are incorporated into VNS to improve solution quality and computational efficiency. The sequencing optimization is obtained in the lower-level according to the given storage location set. A transformation strategy with sufficient problem-specific knowledge is developed to identify the lower-level optimization as the traveling salesman problem and its variants. Then these identified problems are solved using the loop-based *** results show that the proposed Bi JSR is more effective and efficient than the representative algorithms in solving the RS-MTMS problem.

关键词： rack scheduling sequence decision storage assignment bi-level optimization robotic mobile fulfillment system

来源：评论

学校读者我要写书评

暂无评论

A Semisupervised Soft-Sensor of Just-in-Time Learning With Structure Entropy Clustering and Applications for Industrial Processes Monitoring

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第4期4卷 722-733页

作者： Li, Dong Liu, Yiqi Huang, Daoping Xu, Chong South China University of Technology Key Laboratory of Autonomous Systems and Networked Control Ministry of Education School of Automation Science and Engineering Guangzhou510640 China Technical University of Denmark Process and Systems Engineering Center Department of Chemical and Biochemical Engineering Lyngby2800 Denmark South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Gannan Normal University School of Physics and Electronic Information Ganzhou341000 China

To monitor industrial processes properly, soft-sensors are widely used to predict significant but difficult-to-measure quality variables. However, the prediction performances of traditional data-driven soft-sensors are usually unacceptable once suffering from high-nonlinear, high-dimension, and imblance data issues. Therefore, a semisupervised soft-sensor, which is learned by a just-in-time method with structure entropy clustering (SS-JITL-SEC), is proposed aiming to improve prediction performance with a simpler way. Inspired by a divide and conquer strategy, a novel SEC method is proposed to achieve several clusters and then to translate the highly complex and nonlinear modeling problems into simple and linear ones. Moreover, the training dataset is extended through a mixed SS labeling approach. Finally, dissimilarity-based JITL works together with the resulting clustering subdatasets to formulate a local adaptive prediction model. Two datasets from different types of wastewater treatment plants are used to verify the effectiveness of the proposed soft-sensor. The results show that the SS-JITL-SEC soft-sensor can achieve better prediction performance than other standard counterparts, and even for effective process monitoring with the resulted residuals. © 2020 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

A Ducted Fan UAV for Safe Aerial Grabbing and Transfer of Multiple Loads Using Electromagnets

A Ducted Fan UAV for Safe Aerial Grabbing and Transfer of Mu...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Zhong Yin Hailong Pei Key Laboratory of Autonomous Systems and Networked Control Ministry of Education Guangdong Engineering Technology Research Center of Unmanned Aerial Vehicle Systems South China University of Technology Guangzhou China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In recent years, research on aerial grasping, manipulation, and transportation of objects has garnered significant attention. These tasks often require UAVs to operate safely close to environments or objects and to efficiently grasp payloads. However, current widely adopted flying platforms pose safety hazards: unprotected high-speed rotating propellers can cause harm to the surroundings. Additionally, the space for carrying payloads on the fuselage is limited, and the restricted position of the payload also hinders efficient grasping. To address these issues, this paper presents a coaxial ducted fan UAV which is equipped with electromagnets mounted externally on the fuselage, enabling safe grasping and transfer of multiple loads in midair without complex additional actuators. It also has the capability to achieve direct human-UAV cargo transfer in the air. The forces acting on the loads during magnetic attachment and their influencing factors were analyzed. An ADRC controller is utilized to counteract disturbances during grasping and achieve attitude control. Finally, flight tests are conducted to verify the UAV’s ability to directly grasp multiple loads from human hands in flight while maintaining attitude tracking.

关键词： Fans Propellers Transportation Grasping Electromagnets autonomous aerial vehicles Safety Magnetic analysis Intelligent robots Payloads

来源：评论

学校读者我要写书评

暂无评论

Low in Resolution, High in Precision: UAV Detection with Super-Resolution and Motion Information Extraction 48

Low in Resolution, High in Precision: UAV Detection with Sup...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wang, Hanzhuo Wang, Xingjian Zhou, Chengwei Meng, Wenchao Shi, Zhiguo Zhejiang University College of Control Science and Engineering Hangzhou310027 China Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China Zhejiang University Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province Hangzhou310027 China

ISBN: (纸本)9781728163277

The rapid development of unmanned aerial vehicle (UAV) market presents potential threats to public security and personal privacy, and the vision sensors are widely deployed to detect the invasive UAVs because of the intuitivity and accessibility of the video. However, the small pixel area and weak morphological characteristics of distant invasive UAVs pose a considerable challenge to the detection precision. Prior work on UAV detection simply focuses on the information fusion between different feature layers, but ignoring the feature information inside each layer. In addition, to detect small UAV in video streams, the motion information of the target is also a noteworthy feature. In this regard, we propose a feature super-resolution-based UAV detector with motion information extractor. The proposed network fully utilizes the motion information of UAVs between temporal frames and the spatial invariant features between different resolution frames to pursue a high-accuracy small UAV detection performance. Experiments on Drone vs Birds dataset are carried out, and it is demonstrated that a higher detection accuracy on small UAVs is achieved compared with the baseline. © 2023 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Memory-Efficient Reversible Spiking Neural networks

arXiv

引用

arXiv 2023年

作者： Zhang, Hong Zhang, Yu State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China Key Laboratory of Collaborative sensing and autonomous unmanned systems of Zhejiang Province Hangzhou China

Spiking neural networks (SNNs) are potential competitors to artificial neural networks (ANNs) due to their high energyefficiency on neuromorphic hardware. However, SNNs are unfolded over simulation time steps during the training process. Thus, SNNs require much more memory than ANNs, which impedes the training of deeper SNN models. In this paper, we propose the reversible spiking neural network to reduce the memory cost of intermediate activations and membrane potentials during training. Firstly, we extend the reversible architecture along temporal dimension and propose the reversible spiking block, which can reconstruct the computational graph and recompute all intermediate variables in forward pass with a reverse process. On this basis, we adopt the state-of-the-art SNN models to the reversible variants, namely reversible spiking ResNet (RevSResNet) and reversible spiking transformer (RevSFormer). Through experiments on static and neuromorphic datasets, we demonstrate that the memory cost per image of our reversible SNNs does not increase with the network depth. On CIFAR10 and CIFAR100 datasets, our RevSResNet37 and RevSFormer-4- 384 achieve comparable accuracies and consume 3.79× and 3.00× lower GPU memory per image than their counterparts with roughly identical model complexity and parameters. We believe that this work can unleash the memory constraints in SNN training and pave the way for training extremely large and deep SNNs. The code is available at https://***/mi804/***. Copyright © 2023, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Semi-Global Robust Practical Output Voltage Tracking for Single-Phase UPS Inverters via Sampled-Data control

Semi-Global Robust Practical Output Voltage Tracking for Sin...

引用

第42届中国控制会议

作者： Kaiji Zeng Wei Liu Weijie Sun Weidong Liu Key Laboratory of Autonomous Systems and Networked Control Ministry of EducationSchool of Automation Science and EngineeringSouth China University of Technology

This paper deals with the sampled-data semi-global robust practical output voltage tracking problem for single-phase voltage source uninterruptible power supply *** construct an aperiodic sampled-data state feedback control law in an internal model principle *** analysis shows that as long as the upper bound of the sampling time interval of the controller is less than an explicitly computable threshold,our problem can be handled by the proposed sampled-data control *** the tracking error is guaranteed to approach a given neighborhood of the origin asympotically.

关键词：

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：