检索结果-内蒙古大学图书馆

Chinese Control and Decision Conference, CCDC

作者： Jingyu Ru Jiayu Liu Zhongcheng Wang Yifan Gao Hongli Xu Faculty of Robot Science and Engineering Northeastern University Shenyang China College of Information Science and Engineering Northeastern University Shenyang China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

A cooperative fixed-point detection algorithm for multiple UAVs based on conflict search is proposed, which solves the problem of continuous cooperative detection of a certain place by multiple UAVs. This method can monitor and resolve the conflict in real time by setting the conflict between UAVs with large repetition times of detection time, so that multiple UAVs can continuously detect a certain place. At the same time, some improvements are made to the algorithm, and the detection time of UAV is prolonged by adding detection time to heuristic function; In order to meet the high real-time requirements of multi-UAV system, FOCAL-list is added to improve the running speed of the algorithm. Experimental results show that the proposed algorithm can achieve multi-UAV cooperative fixed-point detection, compared with the swarm intelligence algorithm, the improved algorithm has better effect.

关键词： Heuristic algorithms Autonomous aerial vehicles Search problems Real-time systems Path planning Mathematical models Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Degradation Adaption Based Heterogeneous Face Hallucination 4

Degradation Adaption Based Heterogeneous Face Hallucination

引用

4th International Conference on Big Data, Artificial Intelligence and Internet of Things engineering, ICBAIE 2023

作者： Teng, Zi Wang, Huan Yu, Xiaosheng Wu, Chengdong Northeastern University Faculty of Robotics Science and Engineering Shenyang110167 China

ISBN: (纸本)9798350343618

In real-world long-range surveillance systems, thermal face images captured from a distance suffer from low resolution and noise, posing challenges for thermal-to-visible face image translation. Current methods assume similar resolutions and noise-free conditions between thermal and visible images, limiting their applicability. To address these issues, we propose the Degradation Adaption Network (DANet), which synthesizes high-quality visible images from low-quality thermal images. DANet combines pretrained Generative Adversarial Network (GAN) blocks with a U-shaped deep neural network (DNN) to incorporate faithful facial priors, including geometry, facial textures, and colors. Additionally, an unsupervised degradation representation learning scheme is developed to capture abstract degradation representations of degraded thermal images in a representation space. This approach allows DANet to adapt spatial features based on the degradation representation, striking a balance between fidelity and texture faithfulness using degradation-aware feature fusion (DAFF) blocks. Experimental results demonstrate that DANet outperforms state-of-the-art methods, showing its effectiveness in handling real-world low-quality thermal images across diverse practical applications. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Spatial Transformation and Attention Based Super-Resolution Reconstruction Algorithm 4

Multi-Scale Spatial Transformation and Attention Based Super...

引用

4th International Conference on Intelligent Computing and Human-Computer Interaction, ICHCI 2023

作者： Teng, Zi Li, Xiaoqiang Yu, Xiaosheng Wu, Chengdong Northeastern University Faculty of Robotics Science and Engineering Shenyang110167 China

ISBN: (纸本)9798350343113

Face super-resolution reconstruction is a critical task in various application domains. To fully leverage facial pose and texture information, we propose a novel algorithm for face super-resolution reconstruction that incorporates multi-scale spatial transformation and attention mechanisms. Firstly, the multi-scale spatial transformation is employed to learn the facial pose and perform affine transformations, enhancing the local information of the face image. Additionally, spatial attention is utilized to extract features in the image space, capturing global characteristics. Subsequently, a residual learning approach and a multi-path connected up-sampling module are employed to progressively increase the image resolution, reducing feature loss and training instability during the up-sampling process. Finally, a multi-scale convolution is utilized to reconstruct high-resolution facial images. The performance of the proposed algorithm is evaluated using peak signal-To-noise ratio (PSNR) and structural similarity index measure (SSIM) as objective evaluation metrics. Experimental evaluations, conducted on the CelebA dataset at magnifications of 4x and 8x, demonstrate that our model achieves improved reconstruction of edge and texture information, as well as significant enhancements in the objective evaluation indicators of PSNR and SSIM. © 2023 IEEE.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

A Resource Scheduling Optimization Algorithm of Self-organizing Cloud robot Platform

A Resource Scheduling Optimization Algorithm of Self-organiz...

引用

第35届中国控制与决策会议

作者： Ji Peng Gao Wei Li Ming Li Xiaoqiang Faculty of Robot Science and Engineering Northeastern University College of Information Science and Engineering Northeastern University

It is a research hotspot in the field of robotics to improve the running efficiency of robots based on the powerful storage and computing resources of the cloud ***,the traditional cloud computing technology is too centralized to adapt to the military,rescue,and other complex environments,so the self-organizing cloud robot technology that can achieve resource sharing and collaborative computing has received more and more *** self-organizing cloud robot has the characteristics of high stability,strong robustness,fast running speed,and strong computing *** meet the requirements of self-organizing cloud robots for cooperative work and shared computing,a resource optimization scheduling algorithm for a self-organizing robot platform is proposed in this *** the algorithm,a self-organizing network model is built based on the Raft algorithm to realize the interaction and sharing of computing resources between *** this basis,an optimization model for computing resource scheduling under time constraints that are based on the DQN algorithm is *** construction of the reward function and the design of the neural network model are used to achieve effective resource allocation and scheduling of self-organizing cloud robot systems for different task *** evaluate the performance of the proposed algorithm the simulation experiments are *** results show the proposed algorithm is more effective in resource scheduling compared with other current algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning-based Approach to Improve the Trajectory Generalization Performance of DMP

A Reinforcement Learning-based Approach to Improve the Traje...

引用

第42届中国控制会议

作者： Peng Yu Lijin Fang Yian Qian College of Information Science and Engineering Northeastern University Faculty of Robot Science and Engineering Northeastern University

Dynamic Motion Primitives(DMP) is a trajectory coding method based on imitation learning, which achieves a wide application owing to its robustness and generalization ability. However, the generalization of DMP in some special cases is not very satisfactory. For instance, when the target point changes, the similarity of the middle part of the trajectory is also greatly affected. Moreover, scaling the trajectory of the DMP is often followed by a reduction in endpoint accuracy. To solve the above problems, the following work is carried out in this paper: First, we reviewed the basic DMP framework and analyzed its worthy improvements. Second, the Pearson correlation coefficient is introduced to quantitatively assess the similarity of generalized trajectories. Next, a model-free, sampling-based reinforcement learning framework Path Integrals(PI2) is designed for the optimization of generalized trajectories, where the Gaussian weights of the DMP are iteratively updated ***, the feasibility of the method in this paper is verified by simulation in the case of target variation and trajectory scaling.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Subconscious robotic Imitation Learning

arXiv

引用

arXiv 2024年

作者： Xie, Jun Wang, Zhicheng Tan, Jianwei Lin, Huanxu Ma, Xiaoguang Faculty of Robot Science and Engineering Northeastern University Shenyang110819 China College of Information Science and Engineering Northeastern University Shenyang110819 China College of Information Science and Engineering Faculty of Robot Science and Engineering Northeastern University Shenyang110819 China Foshan Graduate School Northeastern University Foshan528311 China

Although robotic imitation learning (RIL) is promising for embodied intelligent robots, existing RIL approaches rely on computationally intensive multi-model trajectory predictions, resulting in slow execution and limited real-time responsiveness. Instead, human beings subconscious can constantly process and store vast amounts of information from their experiences, perceptions, and learning, allowing them to fulfill complex actions such as riding a bike, without consciously thinking about each. Inspired by this phenomenon in action neurology, we introduced subconscious robotic imitation learning (SRIL), wherein cognitive offloading was combined with historical action chunkings to reduce delays caused by model inferences, thereby accelerating task execution. This process was further enhanced by subconscious downsampling and pattern augmented learning policy wherein intent-rich information was addressed with quantized sampling techniques to improve manipulation efficiency. Experimental results demonstrated that execution speeds of the SRIL were 100% to 200% faster over SOTA policies for comprehensive dual-arm tasks, with consistently higher success rates. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

OFSLMs: Offline Fine-Tuned Small Language Models Based on Hybrid Synthetic Knowledge for robot Introspective Decision-Making

OFSLMs: Offline Fine-Tuned Small Language Models Based on Hy...

引用

IEEE International Conference on robotics and Biomimetics

作者： Jinbiao Zhu Lishan Wang Yi Guc Fei Wang Faculty of Robot Science and Engineering Northeastern University Shenyang Liaoning Province China

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

The combination of robots with large language models (LLMs) offers the potential to create more intelligent systems, a prospect that has garnered attention from researchers in recent years. Current efforts primarily focus on constructing prompt systems through online APIs and high-level natural language-based planning and decision-making offline. However, these approaches often neglect scenarios with weak network connectivity and downplay the close integration between models and the robot's lower-level control. We propose that robots should be equipped with Offline Fine-tuned Small Language Models (OFSLMs) capable of generating introspective decisions offline. To this end, we design a workflow for creating these OFSLMs and develop a hybrid synthetic fine-tuning dataset with human and GPT-4's annotation. This dataset contains 2,663 cases to train and evaluate OFSLMs to generate “plan” and lower-level control codes called “solution” based on given “instruction.” Additionally, we devise a two-stage evaluation method to select the best OFSLMs. In experiments, we analyze the distribution of the dataset, and then we select the recent 9 open-source small language models and filter out the best 3 models using proposed workflow. We further perform nonlinear fitting on these OFSLMs' numerical metrics, and explore the generalization capabilities of the OFSLMs. Experiments demonstrate that the dataset we create is semantically rich and that our proposed workflow yields high-quality OFSLMs. These models exhibit non-linear growth in metrics. Moreover, our OFSLMs demonstrate the ability to perform offline robot decision-making and generate control code, highlighting their specialization; simultaneously, OFSLMs also show comparable performance in non-decision-related text-based question-answering tasks, indicating their generalization capability.

关键词： Measurement Analytical models Codes Annotations Decision making Fitting Real-time systems Numerical models robots Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Constraint Programming for a Novel Integrated Optimization of Blocking Job Shop Scheduling and Variable-Speed Transfer robot Assignment 19

Constraint Programming for a Novel Integrated Optimization o...

引用

19th IEEE International Conference on Networking, Sensing and Control, ICNSC 2022

作者： Li, Xingyang Fu, Jun Jia, Zixi Zhao, Ziyan Li, Siyi Liu, Shixin Northeastern University Faculty of Robot Science and Engineering Shenyang110819 China College of Information Science and Engineering Northeastern University Shenyang110819 China Foshan Graduate School of Innovation Northeastern University Foshan528311 China

ISBN: (纸本)9781665472432

Blocking job shop scheduling problems are common in industrial environments. Various existing studies tackle them to enhance the production efficiency of job shops with machine blocking properties. In the environment of intelligent manufacturing, robots are commonly used to transfer the jobs to be processed among different processes. However, no previous work considers the integrated optimization of blocking job shop scheduling and transfer robot assignment. Facing the new and key demand of production scheduling, this work considers a novel blocking job shop scheduling problem with transfer robots whose speed varies with or without cargo load. It is first formulated by using constraint programming as a baseline model. By analyzing the characteristics of both the considered problem and baseline model this work proposes an improved constraint programming model. Numerous experiments on an adapted benchmark dataset show that the improved constraint programming model can well solve the concerned problem. Comparing with a baseline model, it can greatly enhance the solution efficiency and accuracy. Its great performance shows its high potential to be used in practical industrial scenarios. © 2022 IEEE.

关键词： Job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

Expansive Spatial-Temporal Kernel Convolution Network for Skeleton-Based Action Recognition

Expansive Spatial-Temporal Kernel Convolution Network for Sk...

引用

IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems

作者： Ziao Li Junyi Wang Quan Zhou Chengda Li Faculty of Robot Science and Engineering Northeastern University Shenyang China Faculty of Robot Science and Engineering Foshan Graduate School of Innovation Northeastern University China

In skeleton-based action recognition, graph convolutional networks (GCNs) have become the most common method due to their strong modeling ability on graph data and the utilization of prior knowledge on human skeleton. However, convolutional methods have been overlooked in this field despite their wide applications in visual tasks, mature libraries, and learning resources. In this paper, we propose an Expansive Spatial-Temporal Kernel Convolution Network (ESTCN) consisting of Expansive Spatial Kernel Convolution and Expansive Temporal Kernel Convolution for spatial feature extraction. Our ESTCN adopts large kernel convolution to achieve global receptive field and utilize prior knowledge on human joints. Extensive experiments on NTU-RGB+D dataset demonstrate that our method achieves comparable performance with GCN-based methods and outperforms other convolutional methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Noise-Tolerant Learning with Silhouette Coefficient for Unsupervised Person Re-Identification

Noise-Tolerant Learning with Silhouette Coefficient for Unsu...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Feng, Yu Zhao, Shuying Zhang, Yunzhou Liu, Yixiu Zhu, Shangdong Coleman, Sonya College of Information Science and Engineering Northeastern University United States Northeastern University Faculty of Robot Science and Engineering United States Intelligent Systems Research Centre University of Ulster United Kingdom

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Unsupervised person re-identification (re-ID) attracts growing attention due to its broad prospects in practical applications. State-of-the-art unsupervised re-ID approaches combine clustering-based pseudo-label prediction with feature fine-tuning. However, pseudo labels generated directly by clustering are not always reliable and inevitably contain noisy labels. To tackle these challenges, we propose a novel noise inhibition framework to estimate the confidence of each pseudo label and actively correct noisy labels. By introducing the silhouette coefficient, our method can estimate the pseudo-label confidence without any extra model or data, and calculate the correction matrix to correct clustering results directly. However, the silhouette coefficient is usually applied on the hyper-parameters selection of clustering algorithms. In order to make the silhouette coefficient more suitable for estimation and correction tasks, we calibrate the Jaccard distance matrix to alleviate the negative influence of the cluster size on the silhouette coefficient. Our proposed method brings significant improvement and achieves the state-of-the-art performance on benchmark datasets. © 2022 IEEE.

关键词： Clustering algorithms

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：