检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Chen, Zuyao Wu, Jinlin Lei, Zhen Zhang, Zhaoxiang Chen, Chang Wen The Hong Kong Polytechnic University Hong Kong Centre for Artificial Intelligence and Robotics HKISI-CAS Hong Kong 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

Scene Graph Generation (SGG) offers a structured representation critical in many computer vision applications. Traditional SGG approaches, however, are limited by a closed-set assumption, restricting their ability to recognize only predefined object and relation categories. To overcome this, we categorize SGG scenarios into four distinct settings based on the node and edge: Closed-set SGG, Open Vocabulary (object) Detection-based SGG (OvD-SGG), Open Vocabulary Relation-based SGG (OvR-SGG), and Open Vocabulary Detection + Relation-based SGG (OvD+R-SGG). While object-centric open vocabulary SGG has been studied recently, the more challenging problem of relation-involved open-vocabulary SGG remains relatively unexplored. To fill this gap, we propose a unified framework named OvSGTR towards fully open vocabulary SGG from a holistic view. The proposed framework is an end-to-end transformer architecture, which learns a visual-concept alignment for both nodes and edges, enabling the model to recognize unseen categories. For the more challenging settings of relation-involved open vocabulary SGG, the proposed approach integrates relation-aware pretraining utilizing image-caption data and retains visual-concept alignment through knowledge distillation. Comprehensive experimental results on the Visual Genome benchmark demonstrate the effectiveness and superiority of the proposed framework. Our code is available at https://***/gpt4vision/OvSGTR/. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Fractional-Order Fast Terminal Sliding Mode Control for Quadrotor UAV Under Actuator Saturation

Fractional-Order Fast Terminal Sliding Mode Control for Quad...

引用

Chinese automation Congress (CAC)

作者： Changjun Li Zhihuan Chen Zhenhua Zhu Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education Wuhan University of Science and Technology Wuhan China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan China School of Information Science and Engineering Wuhan University of Science and Technology Wuhan China

In this study, a delicate fractional-order fast terminal sliding mode controller is proposed for the position and attitude tracking of a quadrotor UAV under actuator saturation. In this controller, the fractional order calculus is incorporated to the fast terminal sliding mode surface design, which can enhance the convergence speed of the controlled UAV system. Meanwhile, to solve the problem of actual control input limitation, a RBF-based estimator is designed to evaluate the error between the virtual control input and actual control output. The stability of the controlled system is proved by using Lyapunov theorem, where the validity and effectiveness of the proposed controllers and estimator are verified by a detailed numerical simulation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hardware-in-the-Loop Simulation of Vehicle-Manipulator systems for Physical Interaction Tasks

Hardware-in-the-Loop Simulation of Vehicle-Manipulator Syste...

引用

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

作者： Hemjyoti Das Bjørn Kåre Sæbø Kristin Y. Pettersen Christian Ott Faculty of Electrical Engineering and Information Technology Automation and Control Institute (ACIN) Technical University of Vienna TU Wien Vienna Austria Department of Engineering Cybernetics Centre for Autonomous Marine Operations and Systems (NTNU AMOS) NTNU Norwegian University of Science and Technology Trondheim Norway German Aerospace Center Institute of Robotics and Mechatronics Wessling Germany

Hardware-in-the-loop simulation (HILS) allows a more realistic evaluation of control approaches than what is possible with pure software simulations, but without the actual complexity of the complete system. This is important for some complex systems such as orbital robots, where testing of the system is typically not possible after its launch, and an on-ground replica is used to validate the performance of such a system. In this article, an impedance-matching approach is presented to match the end-effector dynamics of a fixed-base robot manipulator with that of a target vehicle-manipulator system (VMS), while taking into account the redundant nullspace dynamics in a connected real-time simulation framework. This approach ensures that the forces and torques exerted by the system on the environment matches with that of the simulated system. The contact wrenches used in our approach are not obtained from numerical simulations, but rather from real physical interaction, which is one of the main advantages of our approach. The effectiveness of our method is validated by demonstrating various physical interaction tasks with the environment, using a suspended aerial manipulator as the target system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Capacitor Minimization in Analog Synapses for Efficient and Compact Binarized SNNs

IEEE Transactions on Circuits and Systems for Artificial Int...

引用

IEEE Transactions on Circuits and systems for Artificial Intelligence 2025年第2期2卷 114-125页

作者： Mikail Yayla Ming-Liang Wei Simon Thomann Albi Mema Chia-Lin Yang Jian-Jia Chen Hussam Amrouch Design Automation for Embedded Systems Group TU Dortmund University Dortmund Germany Lamarr Institute for Machine Learning and Artificial Intelligence Dortmund Germany Department of the Graduate Institute of Electronics Engineering National Taiwan University Taipei Taiwan Technical University of Munich (TUM) Munich Germany TUM School of Computation Information and Technology Chair of AI Processor Design Munich Institute of Robotics and Machine Intelligence Munich Germany Department of Computer Science and Information Engineering Graduate Institute of Electronics Engineering National Taiwan University Taipei Taiwan Department of Computer Science TU Dortmund University Dortmund Germany Lamarr Institute Dortmund Germany

Accelerating the immense workloads of Neural Networks (NNs) is a critical challenge, and analog computing-based approaches present a promising solution. Among these, the Integrate-and-Fire (IF) Spiking Neural Network (SNN) stands out for its potential in efficient neural computation. However, achieving high inference accuracy through precise multiply-accumulate (MAC) operations necessitates a large membrane capacitor—224 to 547 times larger than the synapse array at the 14nm technology node—resulting in prohibitive area costs. Additionally, the large capacitor size introduces higher energy consumption and longer access times. Thus, a key research challenge is maintaining accuracy while mitigating the costs associated with the large membrane capacitor. In this work, we propose a HW/SW Codesign method, called CapMin, for capacitor size minimization in analog computing IF-SNNs. CapMin minimizes the capacitor size by reducing the number of spike times needed for accurate operation of the HW, based on the absolute frequency of MAC level occurrences in the SW. To increase the operation of IF-SNNs to current variation, we propose the method CapMin-V, which trades capacitor size for protection based on the reduced capacitor size found in CapMin. In our experiments, CapMin achieves more than a 14 $\times$ reduction in capacitor size along with a 34% reduction in energy consumption over the state of the art, while CapMin-V achieves increased variation tolerance in the IF-SNN operation, requiring only a small increase in capacitor size.

关键词： Capacitors Circuits Accuracy Capacitance Micromechanical devices Costs Neurons Integrated circuit modeling Spiking neural networks Hardware

来源：评论

学校读者我要写书评

暂无评论

Progressive Transfer Learning for Dexterous In-Hand Manipulation with Multi-Fingered Anthropomorphic Hand

arXiv

引用

arXiv 2023年

作者： Luo, Yongkang Li, Wanyi Wang, Peng Duan, Haonan Wei, Wei Sun, Jia State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences 999077 Hong Kong

Dexterous in-hand manipulation for a multi-fingered anthropomorphic hand is extremely difficult because of the high-dimensional state and action spaces, rich contact patterns between the fingers and objects. Even though deep reinforcement learning has made moderate progress and demonstrated its strong potential for manipulation, it is still faced with certain challenges, such as large-scale data collection and high sample complexity. Especially, for some slight change scenes, it always needs to re-collect vast amounts of data and carry out numerous iterations of fine-tuning. Remarkably, humans can quickly transfer learned manipulation skills to different scenarios with little supervision. Inspired by human flexible transfer learning capability, we propose a novel dexterous in-hand manipulation progressive transfer learning framework (PTL) based on efficiently utilizing the collected trajectories and the source-trained dynamics model. This framework adopts progressive neural networks for dynamics model transfer learning on samples selected by a new samples selection method based on dynamics properties, rewards and scores of the trajectories. Experimental results on contact-rich anthropomorphic hand manipulation tasks show that our method can efficiently and effectively learn in-hand manipulation skills with a few online attempts and adjustment learning under the new scene. Compared to learning from scratch, our method can reduce training time costs by 95%. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Modeling Spoof Noise by De-spoofing Diffusion and its Application in Face Anti-spoofing

Modeling Spoof Noise by De-spoofing Diffusion and its Applic...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Bin Zhang Xiangyu Zhu Xiaoyu Zhang Zhen Lei Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security University of Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences

Face anti-spoofing is crucial for ensuring the security and reliability of face recognition systems. Several existing face anti-spoofing methods utilize GAN-like networks to detect presentation attacks by estimating the noise pattern of a spoof image and recovering the corresponding genuine image. But GAN’s limited face appearance space results in the denoised faces cannot cover the full data distribution of genuine faces, thereby undermining the generalization performance of such methods. In this work, we present a pioneering attempt to employ diffusion models to denoise a spoof image and restore the genuine image. The difference between these two images is considered as the spoof noise, which can serve as a discriminative cue for face anti-spoofing. We evaluate our proposed method on several intra-testing and inter-testing protocols, where the experimental results showcase the effectiveness of our method in achieving competitive performance in terms of both accuracy and generalization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sound Source Localization via False Negative Elimination

arXiv

引用

arXiv 2024年

作者： Song, Zengjie Zhang, Jiangshe Wang, Yuxi Fan, Junsong Zhang, Zhaoxiang School of Mathematics and Statistics Xi'an Jiaotong University Xi'An710049 China Center for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong New Laboratory of Pattern Recognition State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Sound source localization aims to localize objects emitting the sound in visual scenes. Recent works obtaining impressive results typically rely on contrastive learning. However, the common practice of randomly sampling negatives in prior arts can lead to the false negative issue, where the sounds semantically similar to visual instance are sampled as negatives and incorrectly pushed away from the visual anchor/query. As a result, this misalignment of audio and visual features could yield inferior performance. To address this issue, we propose a novel audio-visual learning framework which is instantiated with two individual learning schemes: self-supervised predictive learning (SSPL) and semantic-aware contrastive learning (SACL). SSPL explores image-audio positive pairs alone to discover semantically coherent similarities between audio and visual features, while a predictive coding module for feature alignment is introduced to facilitate the positive-only learning. In this regard SSPL acts as a negative-free method to eliminate false negatives. By contrast, SACL is designed to compact visual features and remove false negatives, providing reliable visual anchor and audio negatives for contrast. Different from SSPL, SACL releases the potential of audio-visual contrastive learning, offering an effective alternative to achieve the same goal. Comprehensive experiments demonstrate the superiority of our approach over the state-of-the-arts. Furthermore, we highlight the versatility of the learned representation by extending the approach to audio-visual event classification and object detection tasks. Code and models are available at: https://***/zjsong/SACL. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

MTPA-based Haptic Feedback Controller for Master Manipulator in Minimally Invasive Surgery

MTPA-based Haptic Feedback Controller for Master Manipulator...

引用

IEEE International Conference on robotics and Biomimetics

作者： Wenda Zhao Jian Chen Yilun Hong Hongbin Liu State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences Hong Kong China School of Biomedical Engineering and Imaging Sciences King's College London London UK

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

Haptic feedback is critical for teleoperation in surgical robots, particularly in Natural Orifice Transluminal Endoscopic Surgery (NOTES). This paper introduces a haptic controller designed to enhance force generation efficiency and resolution, surpassing traditional motor control frameworks. We propose a Maximum Torque Per Ampere (MTPA)-based Field-Oriented Control (FoC) strategy for haptic kinesthetic feedback controller, optimizing the performance of a master manipulator's joint with a brushless DC (BLDC) motor under stalled and ultra-slow conditions. This approach enables a master manipulator with three degrees of freedom (DoF) for force feedback. Its effectiveness is validated through simulator and surgical trials, demonstrating improved haptic feedback in surgical applications.

关键词： Motor drives Torque Minimally invasive surgery Medical robotics Force feedback Orifices Manipulators Motors Haptic interfaces Adaptive control

来源：评论

学校读者我要写书评

暂无评论

Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off 39

Pareto Continual Learning: Preference-Conditioned Learning a...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

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

ISBN: (纸本)157735897X

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, Association for the Advancement of Artificial Intelligence.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Development of a Fault Adaptation System for Underwater Robot Manipulators

Development of a Fault Adaptation System for Underwater Robo...

引用

Ocean Studies (ICOS), International Conference on

作者： Vladimir Filaretov Alexander Zuev Alexey Zhirabok Alexander Protsenko Institute of Automation and Control Processes Vladivostok Russia Department of Informatics and Control in Technical Systems Sevastopol State University Sevastopol Russia Institute of Marine Technology Problems Vladivostok Russia Department of Automatics and Robotics Far Eastern Federal University Vladivostok Russia

ISBN: (纸本)9781665473736

The paper describes the development and research of a system of adaptation to faults of manipulators of underwater robots. The following types of faults were considered: unknown additional load torques on the output shafts of the manipulator electric drives, changes in the electrical resistance of the armature windings of electric motors, and measurement errors of sensors of the position of the manipulator links. The proposed system makes it possible to identify these faults and compensate for their negative consequences in two stages. At the first stage, the values of faults are estimated using a bank of diagnostic observers operating in a sliding mode. At the second stage, with the help of the obtained estimates, a control signal is generated that ensures the stabilization of dynamic properties of each electric drive at the desired level. To check the operability of the proposed system, a computer simulation was carried out.

关键词： Fault diagnosis Shafts Resistance Autonomous underwater vehicles Measurement errors Computer simulation Oceans

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：