检索结果-内蒙古大学图书馆

Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lai, Song Zhao, Zhe Zhu, Fei Lin, Xi Zhang, Qingfu Meng, Gaofeng Department of Computer Science City University of Hong Kong Hong Kong Centre for Artificial Intelligence and Robotics HK Institute of Science & Innovation Chinese Academy of Sciences China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China City University of Hong Kong Shenzhen Research Institute Hong Kong University of Science and Technology of China China

Continual learning aims to learn multiple tasks sequentially. A key challenge in continual learning is balancing between two objectives: retaining knowledge from old tasks (stability) and adapting to new tasks (plasticity). Experience replay methods, which store and replay past data alongside new data, have become a widely adopted approach to mitigate catastrophic forgetting. However, these methods neglect the dynamic nature of the stability-plasticity trade-off and aim to find a fixed and unchanging balance, resulting in suboptimal adaptation during training and inference. In this paper, we propose Pareto Continual Learning (ParetoCL), a novel framework that reformulates the stability-plasticity trade-off in continual learning as a multi-objective optimization (MOO) problem. ParetoCL introduces a preference-conditioned model to efficiently learn a set of Pareto optimal solutions representing different trade-offs and enables dynamic adaptation during inference. From a generalization perspective, ParetoCL can be seen as an objective augmentation approach that learns from different objective combinations of stability and plasticity. Extensive experiments across multiple datasets and settings demonstrate that ParetoCL outperforms state-of-the-art methods and adapts to diverse continual learning scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Multi-task learning

Variable Stiffness Control with Strict Frequency Domain Constraints for Physical Human-Robot Interaction

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zou, Wulin Duan, Pu Chen, Yawen Yu, Ningbo Shi, Ling Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Hong Kong Xeno Dynamics Co. Ltd Shenzhen China Institute of Robotics and Automatic Information Systems Tianjin Key Laboratory of Intelligent Robotics Nankai University Tianjin China

Variable impedance control is advantageous for physical human-robot interaction to improve safety, adaptability and many other aspects. This paper presents a gain-scheduled variable stiffness control approach under strict frequency-domain constraints. Firstly, to reduce conservativeness, we characterize and constrain the impedance rendering, actuator saturation, disturbance/noise rejection and passivity requirements into their specific frequency bands. This relaxation makes sense because of the restricted frequency properties of the interactive robots. Secondly, a gain-scheduled method is taken to regulate the controller gains with respect to the desired stiffness. Thirdly, the scheduling function is parameterized via a nonsmooth optimization method. Finally, the proposed approach is validated by simulations, experiments and comparisons with a gain-fixed passivity-based PID method. Copyright © 2020, The Authors. All rights reserved.

关键词： Frequency domain analysis

Soft yet Effective Robots via Holistic Co-Design

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Stölzle, Maximilian Pagliarani, Niccolò Stella, Francesco Hughes, Josie Laschi, Cecilia Rus, Daniela Cianchetti, Matteo Santina, Cosimo Della Zardini, Gioele Laboratory for Information & Decision Systems Massachusetts Institute of Technology CambridgeMA02139 United States Cognitive Robotics Delft University of Technology Mekelweg 2 CD Delft2628 Netherlands The BioRobotics Institute Scuola Superiore Sant’Anna Pisa56025 Italy Embodied AI AG Lausanne1015 Switzerland CREATE Lab EPFL Lausanne1015 Switzerland Advanced Robotics Centre Department of Mechanical Engineering National University of Singapore 117575 Singapore Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology CambridgeMA02139 United States

Soft robots promise inherent safety via their material compliance for seamless interactions with humans or delicate environments. Yet, their development is challenging because it requires integrating materials, geometry, actuation, and autonomy into complex mechatronic systems. Despite progress, the field struggles to balance task-specific performance with broader factors like durability and manufacturability—a difficulty that we find is compounded by traditional sequential design processes with their lack of feedback loops. In this perspective, we review emerging co-design approaches that simultaneously optimize the body and brain, enabling the discovery of unconventional designs highly tailored to the given tasks. We then identify three key shortcomings that limit the broader adoption of such co-design methods within the soft robotics domain. First, many rely on simulation-based evaluations focusing on a single metric, while real-world designs must satisfy diverse criteria. Second, current methods emphasize computational modeling without ensuring feasible realization, risking sim-to-real performance gaps. Third, high computational demands limit the exploration of the complete design space. Finally, we propose a holistic co-design framework that addresses these challenges by incorporating a broader range of design values, integrating real-world prototyping to refine evaluations, and boosting efficiency through surrogate metrics and model-based control strategies. This holistic framework, by simultaneously optimizing functionality, durability, and manufacturability, has the potential to enhance reliability and foster broader acceptance of soft robotics, transforming human-robot interactions. © 2025, CC BY.

关键词： Intellectual property core

Regularization with multilevel non-stationary tight framelets for image restoration

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Yan-Ran Chan, Raymond H.F. Shen, Lixin Zhuang, Xiaosheng College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen518060 China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China Department of Mathematics City University of Hong Kong Tat Chee Avenue Kowloon Tong Hong Kong Department of Mathematics Syracuse University SyracuseNY13244 United States

Variational regularization models are one of the popular and efficient approaches for image restoration. The regularization functional in the model carries prior knowledge about the image to be restored. The prior knowledge, in particular for natural images, are the first-order (i.e. variance in luminance) and second-order (i.e. contrast and texture) information. In this paper, we propose a model for image restoration, using a multilevel non-stationary tight framelet system that can capture the image's first-order and second-order information. We develop an algorithm to solve the proposed model and the numerical experiments show that the model is effective and efficient as compared to other higher-order models. Copyright © 2021, The Authors. All rights reserved.

关键词： Image reconstruction

3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Video

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Guangming Zhong, Jiquan Zhao, Shijie Wu, Wenhua Liu, Zhe Wang, Hesheng Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing 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 Shanghai200240 China Department of Engineering Mechanics Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Technology University of Cambridge CambridgeCB2 1TN United Kingdom

Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video. A novel unsupervised training framework is proposed with 3D hierarchical refinement and augmentation using explicit 3D geometry. In this framework, the depth and pose estimations are hierarchically and mutually coupled to refine the estimated pose layer by layer. The intermediate view image is proposed and synthesized by warping the pixels in an image with the estimated depth and coarse pose. Then, the residual pose transformation can be estimated from the new view image and the image of the adjacent frame to refine the coarse pose. The iterative refinement is implemented in a differentiable manner in this paper, making the whole framework optimized uniformly. Meanwhile, a new image augmentation method is proposed for the pose estimation by synthesizing a new view image, which creatively augments the pose in 3D space but gets a new augmented 2D image. The experiments on KITTI demonstrate that our depth estimation achieves state-of-the-art performance and even surpasses recent approaches that utilize other auxiliary tasks. Our visual odometry outperforms all recent unsupervised monocular learning-based methods and achieves competitive performance to the geometry-based method, ORB-SLAM2 with back-end optimization. Copyright © 2021, The Authors. All rights reserved.

关键词： Robots

Domain-invariant similarity activation map contrastive learning for retrieval-based long-term visual localization

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hu, Hanjiang Wang, Hesheng Liu, Zhe Chen, Weidong Autonomous Robot Lab Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Jiao Tong University Shanghai200240 China The State Key Laboratory of Robotics and System HIT The Department of Computer Science and Technology University of Cambridge United Kingdom

Visual localization is a crucial component in the application of mobile robot and autonomous driving. Image retrieval is an efficient and effective technique in image-based localization methods. Due to the drastic variability of environmental conditions, e.g. illumination, seasonal and weather changes, retrieval-based visual localization is severely affected and becomes a challenging problem. In this work, a general architecture is first formulated probabilistically to extract domain-invariant feature through multi-domain image translation. And then a novel gradient-weighted similarity activation mapping loss (Grad-SAM) is incorporated for finer localization with high accuracy. We also propose a new adaptive triplet loss to boost the contrastive learning of the embedding in a self-supervised manner. The final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models without and with Grad-SAM loss. Extensive experiments have been conducted to validate the effectiveness of the proposed approach on the CMU-Seasons dataset. The strong generalization ability of our approach is verified on RobotCar dataset using models pre-trained on urban part of CMU-Seasons dataset. Our performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision, especially under the challenging environments with illumination variance, vegetation and night-time images. The code and pretrained models are available on https://***/HanjiangHu/DISAM. Copyright © 2020, The Authors. All rights reserved.

关键词： Image retrieval

REFUGE2 CHALLENGE: A TREASURE TROVE FOR MULTI-DIMENSION ANALYSIS AND EVALUATION IN GLAUCOMA SCREENING

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fang, Huihui Li, Fei Wu, Junde Fu, Huazhu Sun, Xu Son, Jaemin Yu, Shuang Zhang, Menglu Yuan, Chenglang Bian, Cheng Lei, Baiying Zhao, Benjian Xu, Xinxing Li, Shaohua Fumero, Francisco Sigut, José Almubarak, Haidar Bazi, Yakoub Guo, Yuanhao Zhou, Yating Baid, Ujjwal Innani, Shubham Guo, Tianjiao Yang, Jie Orlando, José Ignacio Bogunović, Hrvoje Zhang, Xiulan Xu, Yanwu The REFUGE2 Challenge Australia State Key Laboratory of Ophthalmology Zhongshan Ophthalmic Center Sun Yat-Sen University Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science Guangzhou China Intelligent Healthcare Unit Baidu Inc. Beijing China The Institute of High Performance Computing Agency for Science Technology and Research Singapore Yatiris Group PLADEMA Institute CONICET UNICEN Tandil Argentina Christian Doppler Lab for Artificial Intelligence in Retina Department of Ophthalmology and Optometry Medical University of Vienna Vienna Austria VUNO Inc Seoul Korea Republic of Tencent HealthCare Tencent Shenzhen China Computer Vision Institute College of Computer Science and Software Engineering of Shenzhen University Shenzhen China School of Biomedical Engineering Health Science Center Shenzhen University China Xiaohe Healthcare ByteDance Guangdong Guangzhou510000 China School of Biomedical Engineering Shenzhen University China College of Computer Science & Software Engineering Shenzhen University China Department of Computer Science and Systems Engineering Universidad de La Laguna Spain Saudi Electronic University Saudi Arabia King Saud University Saudi Arabia Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China SGGS Institute of Engineering and Technology India Institute of Medical Robotics Shanghai Jiao Tong University China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

With the rapid development of artificial intelligence (AI) in medical image processing, deep learning in color fundus photography (CFP) analysis is also evolving. Although there are some open-source, labeled datasets of CFPs in the ophthalmology community, large-scale datasets for screening only have labels of disease categories, and datasets with annotations of fundus structures are usually small in size. In addition, labeling standards are not uniform across datasets, and there is no clear information on the acquisition device. Here we release a multi-annotation, multi-quality, and multi-device color fundus image dataset for glaucoma analysis on an original challenge-Retinal Fundus Glaucoma Challenge 2nd Edition (REFUGE2). The REFUGE2 dataset contains 2000 color fundus images with annotations of glaucoma classification, optic disc/cup segmentation, as well as fovea localization. Meanwhile, the REFUGE2 challenge sets three sub-tasks of automatic glaucoma diagnosis and fundus structure analysis and provides an online evaluation framework. Based on the characteristics of multi-device and multi-quality data, some methods with strong generalizations are provided in the challenge to make the predictions more robust. This shows that REFUGE2 brings attention to the characteristics of real-world multi-domain data, bridging the gap between scientific research and clinical application. © 2022, CC BY-NC-ND.

关键词： Color

Using micro- and macro-level network metrics unveils top communicative gene modules in psoriasis

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Naderi, Reyhaneh Mollaei, Homa Saadati Elofsson, Arne Ashtiani, Saman Hosseini Department of Artificial Intelligence and Robotics Faculty of Computer Engineering Iran University of Science and Technology Tehran Iran Department of Advanced Sciences and Technology Islamic Azad University Medical Branch Tehran Iran Department of Biochemistry and Biophysics and Science for Life Laboratory Stockholm University Stockholm106 91 Sweden

Background: Psoriasis is a multifactorial chronic inflammatory disorder of the skin with significant morbidity, characterized by hyper proliferation of the epidermis. Even though psoriasis etiology is not fully understood, it is believed to be multifactorial with numerous key components. Methods: In order to cast light on the complex molecular interactions in psoriasis vulgaris at both protein-protein interactions and transcriptomics levels, we analyzed a set of microarray gene expression analysis consisting of 170 paired lesional and non-lesional samples. Afterwards, a network analysis was conducted on protein-protein interaction network of differentially expressed genes based on micro- and macro-level network metrics at a systemic level standpoint. Results: We found 17 top communicative genes, all of which experimentally proven to be pivotal in psoriasis were identified in two modules, namely, cell cycle and immune system. Intra- and inter-gene interaction subnetworks from the top communicative genes might provide further insight into the corresponding characteristic mechanisms. Conclusions: Potential gene combinations for therapeutic/diagnostics purposes were identified. Moreover, our proposed pipeline could be of interest to a broader range of biological network analysis *** Codes 92C42 Copyright © 2020, The Authors. All rights reserved.

关键词： Dermatology

A Tendon-Driven Robotic Dexterous Hand Design for Grasping 4th

学校读者我要写书评

暂无评论

A Tendon-Driven Robotic Dexterous Hand Design for Grasping

4th International Conference on Cognitive Systems and Information Processing, ICCSIP 2018

作者： Xia, Ziwei Yuan, Jiahui Fang, Bin Sun, Fuchun Zhu, Chang Yang, Yiyong Min, Huasong State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University Haidian District Beijing100083 China Beijing100083 China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan430081 China Beijing China

ISBN: (纸本)9789811379826

This paper focuses on the research of humanoid dexterous hand with tendon-driven. The structure of the dexterous hand is designed and its kinematics, dynamics and the relationship between the finger joints and the fingertip force are deduced. Then, based on the characteristics of the dexterous hand, a hierarchical control system is proposed and fuzzy adaptive PID is used as the motor control algorithm. The grasping experiments are implemented and the results indicate the hand has well performance. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Kinematics