检索结果-内蒙古大学图书馆

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Wang, Zilu Zhou, Zhihao Zhang, Chenxi Wang, Tiantong Zhong, Heran Wang, Rongli Wang, Ninghua Wang, Qining Peking University College of Engineering Beijing100871 China Peking University Institute for Artificial Intelligence Beijing100871 China Beijing Engineering Research Center of Intelligent Rehabilitation Engineering Beijing100871 China Peking University First Hospital Beijing100034 China Peking University College of Engineering The Institute for Artificial Intelligence Department of Advanced Manufacturing and Robotics Beijing100871 China Peking University Third Hospital Beijing100191 China University of Health and Rehabilitation Sciences Qingdao266071 China

ISBN: (纸本)9798350371499

The rupture of the Achilles Tendon (AT) is a prevalent affliction among athletic populations. The patients who process AT repair frequently exhibit a deficit in the activation and strength of the gastrocnemius muscle. The exoskeleton can help with the patients gait training, especially perform effectively interventions during walking. However, the ankle exoskeleton is not suitable for acute-phase gait training, and the knee exoskeleton may have the possibility of downward migration. To address this issue and facilitate the early-stage rehabilitation of the gastrocnemius, this paper proposes a trans-multi-articular gait intervention strategy. Preliminary study on healthy subjects suggests that the implementation of extension resistance during the hip extension phase of the gait cycle can contribute to an increment in the strength of the ankle plantar flexion muscle. Future research will focus on the effectiveness of the proposed therapy strategy in practical application to patients. © 2024 IEEE.

关键词： Exoskeleton (robotics)

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multi-Robot Path Planning in Narrow-Lane Environments with One-Way Constraint 6

Dynamic Multi-Robot Path Planning in Narrow-Lane Environment...

引用

6th International Conference on Intelligent Autonomous Systems, ICoIAS 2023

作者： Song, Zhenyu Zheng, Ronghao Zhang, Senlin Liu, Meiqin College of Electrical Engineering Zhejiang University Hangzhou310027 China Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xian710049 China

ISBN: (纸本)9798350371253

With the rapid development of the logistics industry, the path planning problem for automated guided vehicles (AGVs) in warehousing systems has become a prominent research topic. Traditional multi-robot path planning algorithms often perform poorly in narrow-lane environments found in warehouses. This paper proposes an improved dynamic multi-robot path planning algorithm specifically tailored for narrow-lane environments. By constraining the traversal directions within narrow lanes and dynamically determining the optimal directions, this algorithm achieves efficient multi-robot path planning and enhances the quality of robot paths. The effectiveness of the algorithm is theoretically proven in this paper. Extensive simulation data demonstrates that our algorithm efficiently generates high-quality paths in high-density narrow-lane warehouse environments. © 2023 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

OTIAS: OcTree Implicit Adaptive Sampling for Multispectral and Hyperspectral Image Fusion 39

OTIAS: OcTree Implicit Adaptive Sampling for Multispectral a...

引用

39th Annual AAAI Conference on artificial intelligence, AAAI 2025

作者： Deng, Shangqi Ma, Jun Deng, Liang-Jian Wei, Ping National Key Laboratory of Human-Machine Hybrid Augmented Intelligence China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China University of Electronic Science and Technology of China China

ISBN: (纸本)157735897X

Implicit Neural Representation (INR) methods have demonstrated great potential in arbitrary-scale super-resolution tasks. This success is primarily due to their ability to continuously represent images using coordinates. In the task of remote sensing image fusion, INR methods have also shown promising applications. However, the previous INR methods neglect channel-wise modeling, while sharing a single kernel across all channels at each position, resulting in a lack of sensitivity to data specificity. To address these issues, we propose the OcTree Implicit Adaptive Sampling (OTIAS) method, which innovatively applies the octree structure to restore data from both horizontal and vertical directions, effectively incorporating spatial and spectral information from hyperspectral data. Additionally, we introduce a novel method to adaptively generate interpolation kernels based on coordinates. This approach efficiently produces customized interpolation kernel parameters for octree nodes, tailored to different spectral information. Overall, our method achieves state-of-the-art performance on the CAVE and Harvard datasets with 4× and 8× scaling factors, outperforming existing approaches. © 2025, Association for the Advancement of artificial intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance, Head-pose, and Facial Expression Features

arXiv

引用

arXiv 2024年

作者： Rochow, Andre Schwarz, Max Behnke, Sven Autonomous Intelligent Systems - Computer Science Institute VI and Center for Robotics University of Bonn Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany

The task of face reenactment is to transfer the head motion and facial expressions from a driving video to the appearance of a source image, which may be of a different person (cross-reenactment). Most existing methods are CNN-based and estimate optical flow from the source image to the current driving frame, which is then inpainted and refined to produce the output animation. We propose a transformer-based encoder for computing a set-latent representation of the source image(s). We then predict the output color of a query pixel using a transformer-based decoder, which is conditioned with keypoints and a facial expression vector extracted from the driving frame. Latent representations of the source person are learned in a self-supervised manner that factorize their appearance, head pose, and facial expressions. Thus, they are perfectly suited for cross-reenactment. In contrast to most related work, our method naturally extends to multiple source images and can thus adapt to person-specific facial dynamics. We also propose data augmentation and regularization schemes that are necessary to prevent overfitting and support generalizability of the learned representations. We evaluated our approach in a randomized user study. The results indicate superior performance compared to the state-of-the-art in terms of motion transfer quality and temporal consistency.1 Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

InteractionNet: Joint Planning and Prediction for Autonomous Driving with Transformers

InteractionNet: Joint Planning and Prediction for Autonomous...

引用

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

作者： Jiawei Fu Yanqing Shen Zhiqiang Jian Shitao Chen Jingmin Xin Nanning Zheng Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an Shaanxi P.R. China

Planning and prediction are two important modules of autonomous driving and have experienced tremendous advancement recently. Nevertheless, most existing methods regard planning and prediction as independent and ignore the correlation between them, leading to the lack of consideration for interaction and dynamic changes of traffic scenarios. To address this challenge, we propose InteractionNet, which leverages transformer to share global contextual reasoning among all traffic participants to capture interaction and interconnect planning and prediction to achieve joint. Besides, InteractionNet deploys another transformer to help the model pay extra attention to the perceived region containing critical or unseen vehicles. InteractionNet outperforms other baselines in several benchmarks, especially in terms of safety, which benefits from the joint consideration of planning and forecasting. The code will be available at https://***/fujiawei0724/InteractionNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CLASS RELEVANCE LEARNING FOR OUT-OF-DISTRIBUTION DETECTION

arXiv

引用

arXiv 2023年

作者： Xiong, Butian Zhou, Liguang Lam, Tin Lun Xu, Yangsheng Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Image classification plays a pivotal role across diverse applications, yet challenges persist when models are deployed in real-world scenarios. Notably, these models falter in detecting unfamiliar classes that were not incorporated during classifier training, a formidable hurdle for safe and effective real-world model deployment, commonly known as out-of-distribution (OOD) detection. While existing techniques, like max logits, aim to leverage logits for OOD identification, they often disregard the intricate interclass relationships that underlie effective detection. This paper presents an innovative class relevance learning method tailored for OOD detection. Our method establishes a comprehensive class relevance learning framework, strategically harnessing interclass relationships within the OOD pipeline. This framework significantly augments OOD detection capabilities. Extensive experimentation on diverse datasets, encompassing generic image classification datasets (Near OOD and Far OOD datasets), demonstrates the superiority of our method over state-of-the-art alternatives for OOD detection. © 2023, CC BY-NC-SA.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Asymmetries in Pelvis, Lumbar, and Thorax During Transfemoral Amputee Walking 16th

Asymmetries in Pelvis, Lumbar, and Thorax During Transfemo...

引用

16th International Federation of Theory of Machines and Mechanisms World Congress, IFToMM WC 2023

作者： Zhong, Heran Zhou, Zhihao Wang, Qining Department of Advanced Manufacturing and Robotics College of Engineering Peking University Beijing100871 China Institute for Artificial Intelligence Peking University Beijing100871 China Beijing Engineering Research Center of Intelligent Rehabilitation Engineering Beijing100871 China

ISBN: (纸本)9783031457043

After a transfemoral amputation (TFA), individuals’ movement patterns have numerous changes. TFA significantly induces asymmetry not only in the lower limbs but also in the upper body. The study aims to assess the extent and underlying causes of kinematic asymmetry in the pelvis, torso and spine during gait with a passive prosthesis after a TFA. In the experiments, a single participant with a passive transfemoral prosthesis walked on a treadmill at three different speeds (0.6, 0.8, and 1.2 m/s), while kinematic data were collected. The key outcomes analyzed the kinematics of the pelvis, shoulders, and spine in both the frontal and horizontal planes. Results indicate that all these segments exhibited asymmetry in both planes, with certain parameters being associated with walking speed. Specifically, the upper body asymmetry in TFA amputees was attributed to compensation by the torso and pelvis. This finding underscores the importance of incorporating pelvic and torso training in gait rehabilitation for TFA patients. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Kinematics

来源：评论

学校读者我要写书评

暂无评论

Design, Modeling and Control of A Novel USV-Manipulator System

Design, Modeling and Control of A Novel USV-Manipulator Syst...

引用

IEEE International Conference on Real-time Computing and robotics (RCAR)

作者： Yiyang Jiang Ruoyu Xu Zixing Jiang Huihuan Qian The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS)

This paper introduces a novel vehicle-manipulator system which can contribute to develp theories for automatic harbors and reduce burden on human beings. It can carry out multiple tasks like helping surface vehicle berth, transporting goods and so on flexibly. It is composed of an omni-directional unmanned surface vehicle (USV) and a manipulator, and multiple control methods including real-time nonlinear model predictive control (NMPC) are applied. Simulation and experiment are implemented to verify its ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation

arXiv

引用

arXiv 2025年

作者： Liao, Bencheng Tao, Hongyuan Zhang, Qian Cheng, Tianheng Li, Yingyue Yin, Haoran Liu, Wenyu Wang, Xinggang Institute of Artificial Intelligence Huazhong University of Science & Technology China School of EIC Huazhong University of Science & Technology China Horizon Robotics China

Recent Multimodal Large Language Models (MLLMs) have achieved remarkable performance but face deployment challenges due to their quadratic computational complexity, growing Key-Value cache requirements, and reliance on separate vision encoders. We propose mmMamba, a framework for developing linear-complexity native multimodal state space models through progressive distillation from existing MLLMs using moderate academic computational resources. Our approach enables the direct conversion of trained decoder-only MLLMs to linear-complexity architectures without requiring pre-trained RNN-based LLM or vision encoders. We propose an seeding strategy to carve Mamba from trained Transformer and a three-stage distillation recipe, which can effectively transfer the knowledge from Transformer to Mamba while preserving multimodal capabilities. Our method also supports flexible hybrid architectures that combine Transformer and Mamba layers for customizable efficiency-performance trade-offs. Distilled from the Transformer-based decoder-only HoVLE, mmMamba-linear achieves competitive performance against existing linear and quadratic-complexity VLMs, while mmMamba-hybrid further improves performance significantly, approaching HoVLE’s capabilities. At 103K tokens, mmMamba-linear demonstrates 20.6× speedup and 75.8% GPU memory reduction compared to HoVLE, while mmMamba-hybrid achieves 13.5× speedup and 60.2% memory savings. Code and models are released at https: //***/hustvl/mmMamba © 2025, CC BY-NC-SA.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Incentivizing Sequential Crowdsourcing Systems 23

Incentivizing Sequential Crowdsourcing Systems

引用

Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems

作者： Yuan Luo The Chinese University of Hong Kong (Shenzhen) & Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9781450394321

A crowdsourcing system such as Amazon's Mechanical Turk allows a crowdsource campaign initiator to recruit a large number of workers to accomplish a task. The proper design of such a crowdsourcing system becomes very challenging when the task involves multiple interdependent micro-tasks, and the initiator wants the task to be completed with the minimal cost and a high probability of success. In this paper, we address this challenge by designing an EI (Effort Incentivization) mechanism, which utilizes the peer effect to incentivize workers to act according to the initiator's best interest. We prove that EI is Bayesian incentive compatible and Bayesian individually rational. Our analysis shows that when there are multiple sequential interdependent micro-tasks, the initiator should provide higher rewards to those workers responsible for completing later stage micro-tasks. When there is a flexibility regarding the worker assignment to each micro-task, the initiator should assign fewer workers to later stage micro-tasks to minimize the initiator's overall payment. Numerical results show that our proposed EI mechanism can reduce the initiator's total payment by more than 70%, compared to a fixed reward mechanism. By optimizing the numbers of workers assigned to different interdependent micro-tasks, the initiator can reduce the total payment by up to 50% compared to a random assignment scheme.

关键词： incentive mechanism crowdsourcing systems performance guarantees

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：