检索结果-内蒙古大学图书馆

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

作者： Hu, Kaiyin Chu, Hao Xiao, Xibin Tang, Qingtao Wang, Fei Northeastern University Faculty of Robot Science and Engineering Shenyang110169 China

ISBN: (纸本)9781665481090

Learning from Demonstration (LfD) is a highly promising strategy in robotics technology, paving the way for robots to master and generalize human-like skills. Despite significant progress in the convergence and robustness of LfD trajectory planning in response to target point changes, these explorations are mostly limited to idealized simulation environments. They test algorithm performance by artificially adjusting target points, lacking the autonomy and intelligence demonstrated in real-world scenarios. Therefore, this paper proposes a visual-assisted autonomous adjustment method for demonstration trajectories. The method aims to enable robots to autonomously adjust according to the trajectory patterns demonstrated by humans and accurately reach new target points. For tasks with similar operational trajectories, humans only need to demonstrate once without the need for further intervention or secondary programming. We have conducted physical experiments on the Doosan robot platform, which demonstrates the high practical value of the robot in executing scenarios with similar task goals but variable specific conditions. © 2024 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Clinical Knowledge-Based Hybrid Swin Transformer for Brain Tumor Segmentation

引用

Computers, Materials & Continua 2023年第9期76卷 3797-3811页

作者： Xiaoliang Lei Xiaosheng Yu Hao Wu Chengdong Wu Jingsi Zhang College of Information Science and Engineering Northeastern UniversityShenyang110819China Faculty of Robot Science and Engineer Northeastern UniversityShenyang110819China Faculty of Engineering Macquarie UniversitySydneyNSW2109Australia

Accurate tumor segmentation from brain tissues in Magnetic Resonance Imaging(MRI)imaging is crucial in the pre-surgical planning of brain tumor *** images’heterogeneous intensity and fuzzy boundaries make brain tumor segmentation ***,recent studies have yet to fully employ MRI sequences’considerable and supplementary information,which offers critical a priori *** paper proposes a clinical knowledge-based hybrid Swin Transformermultimodal brain tumor segmentation algorithmbased on how experts identify malignancies from MRI *** the encoder phase,a dual backbone network with a Swin Transformer backbone to capture long dependencies from 3D MR images and a Convolutional Neural Network(CNN)-based backbone to represent local features have been *** of directly connecting all the MRI sequences,the proposed method re-organizes them and splits them into two groups based on MRI principles and characteristics:T1 and T1ce,T2 and *** aggregated images are received by the dual-stem Swin Transformer-based encoder branch,and the multimodal sequence-interacted cross-attention module(MScAM)captures the interactive information between two sets of linked modalities in each *** the CNN-based encoder branch,a triple down-sampling module(TDsM)has been proposed to balance the performance while *** the final stage of the encoder,the feature maps acquired from two branches are concatenated as input to the decoder,which is constrained by MScAM *** proposed method has been evaluated on datasets from the MICCAI BraTS2021 *** results of the experiments demonstrate that the method algorithm can precisely segment brain tumors,especially the portions within tumors.

关键词： Brain tumor segmentation swin transformer multimodal clinical knowledge

来源：评论

学校读者我要写书评

暂无评论

EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting 41

EvGGS: A Collaborative Learning Framework for Event-based Ge...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Jiaxu He, Junhao Zhang, Ziyi Sun, Mingyuan Sun, Jingkai Xu, Renjing Guangzhou China Faculty of Robot Science and Engineering Northeastern University Shenyang China

Event cameras offer promising advantages such as high dynamic range and low latency, making them well-suited for challenging lighting conditions and fast-moving scenarios. However, reconstructing 3D scenes from raw event streams is difficult because event data is sparse and does not carry absolute color information. To release its potential in 3D reconstruction, we propose the first event-based generalizable 3D reconstruction framework, called EvGGS, which reconstructs scenes as 3D Gaussians from only event input in a feedforward manner and can generalize to unseen cases without any retraining. This framework includes a depth estimation module, an intensity reconstruction module, and a Gaussian regression module. These submodules connect in a cascading manner, and we collaboratively train them with a designed joint loss to make them mutually promote. To facilitate related studies, we build a novel event-based 3D dataset with various material objects and calibrated labels of grayscale images, depth maps, camera poses, and silhouettes. Experiments show models that have jointly trained significantly outperform those trained individually. Our approach performs better than all baselines in reconstruction quality, and depth/intensity predictions with satisfactory rendering speed. Copyright 2024 by the author(s)

关键词： Gaussian distribution

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

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

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

ISBN: (纸本)9781665481090

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. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Mobility Path Planning for Underwater Autonomous robots Using an Improved A* Algorithm 24

Mobility Path Planning for Underwater Autonomous Robots Usin...

引用

9th International Conference on Cyber Security and Information engineering, ICCSIE 2024

作者： Sun, Haitao Faculty of Robot Science and Engineering Harbin Far East Institute of Technology China

ISBN: (纸本)9798400718137

This paper examines the path planning problem for underwater autonomous robots using an improved A algorithm. As underwater robots are increasingly employed in marine exploration and resource development, path planning has emerged as a key technology. While the traditional A algorithm can effectively solve path planning problems, it has limitations in complex underwater environments, such as producing overly long paths and having low computational efficiency. To address these issues, this paper introduces an improved A* algorithm that enhances adaptability and search efficiency in underwater settings through a dynamic weight adjustment mechanism and heuristic function optimization. Simulation results demonstrate that this improved algorithm significantly outperforms the traditional A* algorithm in both path length and computation time, offering a more efficient path planning solution for underwater autonomous robots. © 2024 Copyright held by the owner/author(s).

关键词： robot programming

来源：评论

学校读者我要写书评

暂无评论

Improving the Teaching Assessment System for the AI Comprehensive Practice Course Based on the K-means Algorithm within the CBA Framework 24

Improving the Teaching Assessment System for the AI Comprehe...

引用

3rd International Conference on Artificial Intelligence and Education, ICAIE 2024

作者： Xiao, Xibin Chu, Hao Wang, Fei Wen, Shiguang Faculty of Robot Science and Engineering Northeastern University Liaoning Shenyang China

ISBN: (纸本)9798400712692

Traditional assessment systems can't fully evaluate students' practical abilities in the course teaching process. To address the issue, we develop a teaching evaluation system for AI course. It is based on the Competition-Based Assessment (CBA) framework. The weights of evaluation criteria are optimized dynamically by using K-Means clustering and Spearman's rank correlation analysis. So that the system's accuracy and fairness has been enhanced. In the proposed system, the students' competencies are better reflected in the aspect of practical ability, innovation, and teamwork spirit. The experiment results show that our evaluation system provides a more objective assessment approach. Moreover, it can reflect students' practical skills effectively. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

SUGrasping: a semantic grasping framework based on multi-head 3D U-Net

引用

Multimedia Tools and Applications 2024年 1-22页

作者： Cao, He Zhang, Yunzhou Ge, Zhexue Chen, Xin Liu, Xiaozheng Zhao, Jiaqi Faculty of Robot Science and Engineering Northeastern University Shenyang China College of Information Science and Engineering Northeastern University Shenyang China College of Intelligence Science and Technology National University of Defense Technology Hunan Changsha410073 China

Object grasping is an important skill for robots to interact with the real world, especially in unstructured environments where occlusions and different shapes of target objects are present. In this work, we introduce a robot grasping pipeline called SUGrasping, which can obtain the grasping poses more precisely for target objects. The grasping pipeline treats the Truncated Signed Distance Function (TSDF) and point clouds of the grasping scene as input simultaneously. The proposed multi-head 3D U-Net accepts reconstructed TSDF representation and outputs the grasping configurations, including predicted grasp quality, orientation and width of the gripper. The point cloud is fed into PointNet to obtain the semantic segmentation results for all objects in the grasping workspace. With the help of point cloud inside the gripper, the relationship between the gripper and semantic information can be established. It makes robots know which object they are grasping, rather than just removing objects in the workspace like previous works. Experimental results show that the proposed method has an improvement in grasping success rate and percent cleared of target objects, which outperforms state-of-the-art methods compared in this paper. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Divided Block Multiscale Convolutional Network for Micro-expression Recognition 1

Divided Block Multiscale Convolutional Network for Micro-exp...

引用

1st International Conference on Cyber-Energy Systems and Intelligent Energy, ICCSIE 2022

作者： Zhou, Quan Liu, Shiyu Wang, Yiheng Wang, Junyi Northeastern University Faculty of Robot Science and Engineering Shenyang China Northeastern University Faculty of Robot Science and Engineering Foshan Graduate School of Innovation Shenyang China

ISBN: (纸本)9781665452151

Micro-expression (ME) is a subtle change in the face, which can be used to judge human subjective feelings. It has broad application prospects in medical diagnosis and business negotiation. However, due to the complexity of ME muscle movements and the lack of ME trainable data, the research of micro-expression recognition (MER) still faces a series of challenges. In this paper, we propose a new divided block multiscale convolution network (DBMNet), which could learn from four different optical flow (OF) feature images obtained between the onset and apex frames of ME samples. Through the proposed block-divided multiscale convolution module (BMCM), more detailed and useful multiscale advanced features of ME could be effectively extracted. In order to better address the problem of class imbalance on the ME dataset, this paper uses the weighted cross entropy (CE) loss function, which could obviously alleviate the impact of class imbalance. Finally, 5-class experiment is conducted on the composite dataset to show that the proposed method has superior performance and is comparable to those of the most advanced methods. © 2023 IEEE.

关键词： Convolution

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 13

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

引用

13th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2023

作者： Li, Ziao Wang, Junyi Zhou, Quan Li, Chengda Northeastern University Faculty of Robot Science and Engineering Shenyang110819 China Foshan Graduate School of Innovation Faculty of Robot Science and Engineering Northeastern University China

ISBN: (纸本)9798350315196

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. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Binary Classification is Enough: A Lightweight Strategy for Drug Screening with Small Datasets 2

Binary Classification is Enough: A Lightweight Strategy for ...

引用

2nd International Conference on Health Big Data and Intelligent Healthcare, ICHIH 2023

作者： Wu, Liang Ma, Xiaoguang Northeastern University Faculty of Robot Science and Engineering Shenyang China

ISBN: (纸本)9798350309324

Drug screening is an extremely costly and time-consuming process, wherein only small datasets are available in practice. We presented a particular method to estimate values of inhibition constant(Ki) or half-maximal inhibition concentration(IC50) of unknown compounds through a lightweight mutual information and logistic regression(MI-LR) united model that only needed to be trained on a small dataset. Biologists could then use this model to determine whether the compounds were initially eligible for screening, increasing efficiency of their work. A data augmentation strategy was used to sort independent samples of training datasets and solved the problem of sample shortage caused by the lightweight model, and transform a prediction task into a simpler binary classification task. In addition, we proposed an effective constraint mechanism to deal with the case when the classification results were contrary to the facts. By accurately predicting the interval of its inhibitory effect, we can improve the efficiency and accuracy of drug screening. Numerous evaluations on the Ki and IC50 dataset demonstrated high reliability of the MI-LR united approach to sort compounds according to a selected set of molecular descriptors. © 2023 IEEE.

关键词： Forecasting

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：