检索结果-内蒙古大学图书馆

Constrained Behavior Cloning for robotic Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liang, Wensheng Xie, Jun Wang, Zhicheng Tan, Jianwei Ma, Xiaoguang School of Mechanical Engineering and Automation Northeastern University Wenhua Road Heping District Liaoning Shenyang110819 China Faculty of Robot Science and Engineering Northeastern University Chuangxin Road Hunnan District Liaoning Shenyang110169 China Foshan Graduate School of Innovation Northeastern University Shunde District Guangdong Foshan528311 China

Behavior cloning (BC) is a popular supervised imitation learning method in the societies of robotics, autonomous driving, etc., wherein complex skills can be learned by direct imitation from expert demonstrations. Despite its rapid development, it is still affected by limited field of view where accumulation of sensors and joint noise bring compounding errors. In this paper, we introduced geometrically and historically constrained behavior cloning (GHCBC) to dominantly consider high-level state information inspired by neuroscientists, wherein the geometrically constrained behavior cloning were used to geometrically constrain predicting poses, and the historically constrained behavior cloning were utilized to temporally constrain action sequences. The synergy between these two types of constrains enhanced the BC performance in terms of robustness and stability. Comprehensive experimental results showed that success rates were improved by 29.73% in simulation and 39.4% in real robot experiments in average, respectively, compared to state-of-the-art BC method, especially in long-term operational scenes, indicating great potential of using the GHCBC for robotic learning. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

RL-Based Guidance in Outpatient Hysteroscopy Training: A Feasibility Study

学校读者我要写书评

暂无评论

RL-Based Guidance in Outpatient Hysteroscopy Training: A Fea...

IEEE International Conference on robotics and Biomimetics

作者： Vladimir Poliakov Kenan Niu Emmanuel Vander Poorten Dzmitry Tsetserukou Intelligent Space Robotics Lab Skolkovo Institute of Science and Technology Moscow Russia Faculty of Mechanical Engineering KU Leuven Robot Assisted Surgery group Leuven Belgium

ISBN: (纸本)9781665481106

This work presents an RL-based agent for out-patient hysteroscopy training. Hysteroscopy is a gynecological procedure for examination of the uterine cavity. Recent ad-vancements enabled performing this type of intervention in the outpatient setup without anaesthesia. While being beneficial to the patient, this approach introduces new challenges for clinicians, who should take additional measures to maintain the level of patient comfort and prevent tissue damage. Our prior work has presented a platform for hysteroscopic training with the focus on the passage of the cervical canal. With this work, we aim to extend the functionality of the platform by designing a subsystem that autonomously performs the task of the passage of the cervical canal. This feature can later be used as a virtual instructor to provide educational cues for trainees and assess their performance. The developed algorithm is based on the soft actor critic approach to smooth the learning curve of the agent and ensure uniform exploration of the workspace. The designed algorithm was tested against the performance of five clinicians. Overall, the algorithm demonstrated high efficiency and reliability, succeeding in 98 % of trials and outperforming the expert group in three out of four measured metrics.

关键词： Training Measurement Irrigation Tissue damage Instruments Force feedback Force

Lexicographic Multi-objective Order Picking Optimization for robotic Mobile Fulfillment Systems

学校读者我要写书评

暂无评论

Lexicographic Multi-objective Order Picking Optimization for...

IEEE International Conference on Systems, Man and Cybernetics

作者： Hanying Wang Ziyan Zhao Jiaqi Liang Xingyang Li Shixin Liu College of Information Science and Engineering Northeastern University Shenyang China Foshan Graduate School of Innovation Northeastern University Foshan China Département de mathématiques et génie industriel Polytechnique Montréal Montréal Qc Canada Faculty of Robot Science and Engineering Northeastern University Shenyang China State Key Laboratory of Synthetical Automation for Process Industries and the College of Information Science and Engineering Northeastern University Shenyang China School of Control Engineering Northeastern University at Qinhuangdao Qinhuangdao Hebei China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

In light of advancements in artificial intelligence, the Internet of Things, and mechatronics, robots are increasingly integrated into e-commerce warehouses to enable smart order picking solutions and foster intelligent automation. A robot-assisted order picking process revolutionizes the traditional labor-intensive person-to-goods order picking technology, leading to a goods-to-person (G2P) smart warehouse. Within it, robots transport pods to predefined picking stations, where human pickers retrieve the requested goods from these pods to fulfill customer orders. The allocation of pods to robots and the scheduling of picking operations are key optimization issues in G2P order picking systems. Although they play a key role in improving operational efficiency, existing research has paid limited attention to their joint optimization. This study considers a lexicographic multi-objective optimization problem to shorten the order picking cycles under the premise of optimizing the picking efficiency evaluated by makespan. We build a mixed integer program for the newly proposed problem and develop a matheuristic algorithm by integrating a commodity-order model into a metaheuristic algorithm to solve it. Experimental results show that the proposed method can significantly shorten the total order picking cycles while keeping the minimum makespan. It outperforms a recent state-of-the-art algorithm. This work emphasizes the importance of joint optimization within G2P smart warehouses and reveals the high potential of the proposed method to be used in practice.

关键词： Intelligent automation Adaptation models Mechatronics Metaheuristics Search problems Scheduling Resource management Internet of Things Electronic commerce robots

Overview of Dialogue robot Competition 2023

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Minato, Takashi Higashinaka, Ryuichiro Sakai, Kurima Funayama, Tomo Nishizaki, Hiromitsu Nagai, Takayuki Hiroshi Ishiguro Laboratories ATR Kyoto Japan Guardian Robot Project RIKEN Kyoto Japan Graduate School of Informatics Nagoya University Nagoya Japan Graduate Faculty of Interdisciplinary Research University of Yamanashi Yamanashi Japan Graduate School of Engineering Science Osaka University Osaka Japan

We have held dialogue robot competitions in 2020 and 2022 to compare the performances of interactive robots using an android that closely resembles a human. In 2023, the third competition DRC2023 was held. The task of DRC2023 was designed to be more challenging than the previous travel agent dialogue tasks. Since anyone can now develop a dialogue system using LLMs, the participating teams are required to develop a system that effectively uses information about the situation on the spot (real-time information), which is not handled by ChatGPT and other systems. DRC2023 has two rounds, a preliminary round and the final round as well as the previous competitions. The preliminary round has held on Oct.27 – Nov.20, 2023 at real travel agency stores. The final round will be held on December 23, 2023. This paper provides an overview of the task settings and evaluation method of DRC2023 and the results of the preliminary round. Copyright © 2024, The Authors. All rights reserved.

关键词： Real time systems

Dynamic Perturbation-Adaptive Adversarial Training on Medical Image Classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Shuai Ma, Xiaoguang Jiang, Shancheng Meng, Lu The College of Information Science and Engineering Northeastern University Shenyang110819 China The Foshan Graduate School Northeastern University Foshan528311 China The Faculty of Robot Science and Engineering Northeastern University Shenyang110819 China The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China The School of Intelligent Systems Engineering Sun Yat-Sen University No. 135 Xingang Xi Road Guangzhou China Guangdong Provincial Key Laboratory of Fire Science and Technology Guangzhou510006 China

Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data, raising serious concerns on network robustness. Although adversarial training (AT), in responding to malevolent AEs, was recognized as an effective approach to improve robustness, it was challenging to overcome generalization decline of networks caused by the AT. In this paper, in order to reserve high generalization while improving robustness, we proposed a dynamic perturbation-adaptive adversarial training (DPAAT) method, which placed AT in a dynamic learning environment to generate adaptive data-level perturbations and provided a dynamically updated criterion by loss information collections to handle the disadvantage of fixed perturbation sizes in conventional AT methods and the dependence on external transference. Comprehensive testing on dermatology HAM10000 dataset showed that the DPAAT not only achieved better robustness improvement and generalization preservation but also significantly enhanced mean average precision and interpretability on various CNNs, indicating its great potential as a generic adversarial training method on the MIC. Copyright © 2024, The Authors. All rights reserved.

关键词： Statistical tests

Motion-to-Matching: A Mixed Paradigm for 3D Single Object Tracking

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Zhiheng Lin, Yu Cui, Yubo Li, Shuo Fang, Zheng Faculty of Robot Science and Engineering Northeastern University Shenyang110819 China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang110819 China Key Laboratory of Data Analytics and Optimization for Smart Industry Ministry of Education Northeastern University Shenyang110819 China

3D single object tracking with LiDAR points is an important task in the computer vision field. Previous methods usually adopt the matching-based or motion-centric paradigms to estimate the current target status. However, the former is sensitive to the similar distractors and the sparseness of point clouds due to relying on appearance matching, while the latter usually focuses on short-term motion clues (eg. two frames) and ignores the long-term motion pattern of target. To address these issues, we propose a mixed paradigm with two stages, named MTM-Tracker, which combines motion modeling with feature matching into a single network. Specifically, in the first stage, we exploit the continuous historical boxes as motion prior and propose an encoder-decoder structure to locate target coarsely. Then, in the second stage, we introduce a feature interaction module to extract motion-aware features from consecutive point clouds and match them to refine target movement as well as regress other target states. Extensive experiments validate that our paradigm achieves competitive performance on large-scale datasets (70.9% in KITTI and 51.70% in NuScenes). The code will be open soon at https://***/LeoZhiheng/ ***. Copyright © 2023, The Authors. All rights reserved.

关键词： Large dataset

Clustering Multimodal Ensemble Learning for Predicting Gastric Cancer Neoadjuvant Chemotherapy Efficacy

学校读者我要写书评

暂无评论

Clustering Multimodal Ensemble Learning for Predicting Gastr...

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Chi, Jianning Wu, Huixuan Shi, Yujin Li, Zelan Sun, Xiaohu Wang, Lu Zhang, Zitian Gong, Yuehua Northeastern University Faculty of Robot Science and Engineering Shenyang110167 China The First Hospital of China Medical University Key Laboratory of Gi Cancer Etiology and Prevention in Liaoning Province Tumor Etiology and Screening Department Cancer Institute and General Surgery Key Laboratory of Cancer Etiology and Prevention in Liaoning Education Department Shenyang China Cancer Hospital of China Medical University Liaoning Cancer Hospital & Institute Cancer Hospital of Dalian University of Technology Department of Radiotherapy No.44 Xiaoheyan Road Dadong District Liaoning Province Shenyang110042 China

ISBN: (纸本)9798350386226

Accurately predicting the response to neoadjuvant chemotherapy (NCT) is crucial for gastric cancer treatment planning. Multimodal diagnostic methods enhance prediction accuracy by integrating images and clinical features, but they often overlook intra-class differences, causing feature entanglement, and single models struggle to capture dataset diversity. To address these issues, we propose Clustering Multimodal Ensemble Learning (CMEL) framework, which aligns and fuses image features from different domains with clinical features and performs decision fusion using an ensemble model. Specifically, we design the clustering process using Siamese network and memory bank to partition images in feature space and introduce contrastive clustering loss to enhance clustering properties and reduce feature entanglement across domains. We design Hierarchical Feature Alignment Fusion (HFAF) module to generate multi-level image features at different depths and then separately align and fuse them with clinical features, providing diverse features to cover variations in the dataset. We design Dynamic Multi-Classifier Decision Fusion (DMDF) module to predict on fused features using a gating mechanism supervised by pseudo-labels for dynamic weights, enhancing prediction across different domains. On our collected the Gastric Cancer Chemotherapy Response (GCCR) dataset, CMEL achieves an AUC of 76.09%, accuracy of 72.00%, PPV of 86.02%. These results demonstrate the feasibility of joint image and clinical data in predicting NCT response and provide valuable insights for gastric cancer treatment. The code is available at https://***/WHX0259/CMEL. © 2024 IEEE.

关键词： Diseases

Long-Term LiDAR Place Recognition Based on Phase Congruency in Changing Environments

学校读者我要写书评

暂无评论

Long-Term LiDAR Place Recognition Based on Phase Congruency ...

Chinese Control Conference (CCC)

作者： Fengkui Cao Chi Li Ting Wang State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China Faculty of Robot Science and Engineering Northeastern University Shenyang China College of Information Engineering Dalian University Dalian China

Robust Place recognition is an open challenging problem under various perceptual conditions, e.g., all weather, times-of-day and seasons shifts. Although LiDAR sensors do not suffer from illumination problem of visual appearance, they are dramatically affected by structural changes across seasons. In this paper, a simple yet effective place recognition method is proposed based on phase congruency to achieve long-term robust localization under severe seasonal changes. To improve the efficiency while retaining geometric information of scene layouts in 3D space, a compact cylindrical description is designed to convert 3D point clouds to 2D images, in which the pixel values are computed based on geometric information rather than heights or numbers of points. Then the histogram of orientated phase congruency are encoded as global descriptor for place retrieval. Extensive real experiments on across-season Oxford robotCar dataset show that the proposed system outperforms baseline methods, verifying its robust performance in challenging scenarios.

关键词：

Machine Learning-based Energy Consumption Model for Data Center

学校读者我要写书评

暂无评论

Machine Learning-based Energy Consumption Model for Data Cen...

第35届中国控制与决策会议

作者： Lin Qiao Yuanqi Yu Qun Wang Yu Zhang Yueming Song Xiaosheng Yu Department Information Communication Branch of State Grid Liaoning Electric Power Co. Ltd. Department Information Communication Branch of State Grid Liaoning Electric Power Co. Ltd Faculty of Robot Science and Engineering Northeastern University

The accurate prediction of time series data in the industrial production process can provide important guidance for the scheduling and decision-making of industrial systems,and is also an important part of predictive control *** this paper,a time series prediction model which introduces the graph neural network(GCN) is *** model mainly consists of a time series feature extraction module and a relational modeling *** the time series feature extraction module,the Att-LSTM model is proposed to extract the feature information of time series *** the relational modeling module,a novel M-GCN network is proposed to model the relevance among different time series *** addition,based on the time series prediction model,a time series multiclassification model is also *** proposed model can predict the energy consumption conditions of the data center *** experimental results demonstrate that the propose model can provide a desirable performance superior to some traditional models in accuracy and robustness.

关键词：