检索结果-内蒙古大学图书馆

RSI/ISM International Conference on Robotics and Mechatronics (ICROM)

作者： Ali Sabzejou Mehdi Tale Masouleh Ahmad Kalhor School of Electrical and Computer Engineering Department Human and Robot Interaction Laboratory University of Tehran

Robotic grasping poses a fundamental challenge in robotics, particularly when dealing with unknown objects. This skill has always been a focal point in robotics research due to its fundamental importance and inherent complexity. Recent advances utilize state-of-the-art learning techniques, including deep learning and deep reinforcement learning, presenting their unique set of challenges. Training these models requires extensive data and computational resources, with the generalization to unknown objects presenting a significant obstacle for robots. This paper presents a comprehensive approach to unknown object robotic grasping, with a specific focus on top-down grasping actions. The process encompasses image preprocessing, the application of the Straight Skeleton (StSkel) method, and the systematic generation of grasp keypoints when applied to a selection of objects from the Dex-Net dataset. During the evaluation, the analysis incorporated crucial metrics, including the number of detected grasp keypoints for each object, the count of successfully generated grasp pairs, the overall success rate, and the success rate when considering the top 5 ranked grasp pairs. One of the notable strengths of this approach lies in its adaptability to a wide array of objects, ranging from simple shapes to complex ones. The proposed approach in this paper paves the way for automatically labeling grasping datasets, providing a valuable asset for developing auto-generating Deep-RL models. The StSkel method effectively captures essential structural information, making it suitable for real-world applications involving diverse objects. The experimental outcomes affirm the robustness and adaptability of the approach, as it most often achieved a high success rate in generating viable pairs of grasping points for most tested objects. Even complex objects yield impressive results, demonstrating the method’s potential for real-world applications in grasping unknown objects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bioderived Hygromorphic Twisted Actuator for Untethered Sustainable Systems 12th

Bioderived Hygromorphic Twisted Actuator for Untethered Sust...

引用

Proceedings of the 12th International Conference on Biomimetic and Biohybrid Systems, Living Machines 2023

作者： Whatmore, Reece Keely, Emelia Lee, Zoe Minori, Adriane Yao, Lining Department of Materials Science and Engineering Carnegie Mellon University PittsburghPA15218 United States Industrial Design Department Rhode Island School of Design ProvidenceRI02903 United States Human-Computer Interaction Institute School of Computer Science Carnegie Mellon University PittsburghPA15218 United States

ISBN: (纸本)9783031388569

Environmentally friendly and hygromorphic actuators have gained increasing attention for energy harvesting, field robotics, seeding and biodegradable active structures and sensors. While recent works have used hygromorphic seeds as sources of bio-inspiration, it is challenging to engineer synthetic hygromorphic actuators with comparable stiffness, energy density, and reaction speed, and the processing of synthetic materials or need for external power sources inevitably increases fossil fuel consumption and waste production. In this paper, we harness an alternative bioderived design approach, utilizing the natural twisted body of the seed, Hesperostipa Spartea, itself as a sustainable and biodegradable hygromorphic twisting actuator that converts atmospheric water concentration into mechanical energy. Our self-powered twisted actuator is capable of providing twisting actuation with a load over 11,000 times its body mass. We further demonstrate the potential of modular biohybrid design to create untethered self-locking and crawling systems, powered solely by environmental stimuli. The ability to create biodegradable self-actuating systems with modular bioderived design presents opportunities to create biocompatible systems, improving sustainability in the field of soft robotics and beyond. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

VRoxy: Wide-Area Collaboration From an Office Using a VR-Driven Robotic Proxy 23

VRoxy: Wide-Area Collaboration From an Office Using a VR-Dri...

引用

Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology

作者： Mose Sakashita Hyunju Kim Brandon Woodard Ruidong Zhang François Guimbretière Information Science Cornell University United States Computer Science/Brown University/Human-Computer Interaction Laboratory Brown University United States

ISBN: (纸本)9798400701320

Recent research in robotic proxies has demonstrated that one can automatically reproduce many non-verbal cues important in co-located collaboration. However, they often require a symmetrical hardware setup in each location. We present the VRoxy system, designed to enable access to remote spaces through a robotic embodiment, using a VR headset in a much smaller space, such as a personal office. VRoxy maps small movements in VR space to larger movements in the physical space of the robot, allowing the user to navigate large physical spaces easily. Using VRoxy, the VR user can quickly explore and navigate in a low-fidelity rendering of the remote space. Upon the robot’s arrival, the system uses the feed of a 360 camera to support real-time interactions. The system also facilitates various interaction modalities by rendering the micro-mobility around shared spaces, head and facial animations, and pointing gestures on the proxy. We demonstrate how our system can accommodate mapping multiple physical locations onto a unified virtual space. In a formative study, users could complete a design decision task where they navigated and collaborated in a complex 7.5m x 5m layout using a 3m x 2m VR space.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recommendations in Visual Analytics - An Analytical Approach for Elaboration in science

Recommendations in Visual Analytics - An Analytical Approach...

引用

International Conference on Information Visualisation (IV)

作者： Midhad Blazevic Lennart B. Sina Cristian A. Secco Kawa Nazemi Department of Media & Department of Computer Science Human-Computer Interaction and Visual Analytics Darmstadt University of Applied Sciences Darmstadt Germany

The huge amount of scientific content increases the workload for evaluating state-of-the-art research and the complexity of creating novel and innovative methods and approaches. Although many approaches exist using recommendations in various application domains, the full potential of recommendation systems is not yet fully utilized. Particularly, there are missing approaches that combine interactive visualizations with recommendation systems to enable an analytical investigation of the current state of technology and science. We, therefore, propose in this work a novel Visual Analytics approach that integrates recommendation methods as the model and provides a seamless integration of both interactive visualizations and recommendation systems. We utilize MAE and RMSE metrics and human validation to identify the best approach out of eight approaches that differ in vectorization and similarity algorithms to recommend scientific items. We contribute novel approaches for recommending scientific publications, venues, and projects, based on comparing traditional and deep-learning-based recommendation approaches. Furthermore, we propose a Visual Analytics approach that uses recommendation methods for analytical elaboration. This work shows the potential of integrating recommendation systems into scientific research and identifies potential future directions for improving the proposed model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Imitation of human Head Motions, Blinks and Emotions by Nao Robot: A Closed-Loop Approach 11

Real-Time Imitation of Human Head Motions, Blinks and Emotio...

引用

11th RSI International Conference on Robotics and Mechatronics, ICRoM 2023

作者： Rayati, Keyhan Feizi, Amirhossein Beigy, Alireza Shahverdi, Pourya Masouleh, Mehdi Tale Kalhor, Ahmad Louie, Wing-Yue Geoffrey University of Tehran Human and Robot Interaction Lab Electrical and Computer Engineering Tehran Iran Shahrood University of Technology Department of Electrical Engineering Shahrood Iran Oakland University Intelligent Robotics Laboratory Michigan United States

ISBN: (纸本)9798350308105

This paper introduces a novel approach for enabling real-time imitation of human head motion by a Nao robot, with a primary focus on elevating human-robot interactions. By using the robust capabilities of the MediaPipe as a computer vision library and the DeepFace as an emotion recognition library, this research endeavors to capture the subtleties of human head motion, including blink actions and emotional expressions, and seamlessly incorporate these indicators into the robot's responses. The result is a comprehensive framework which facilitates precise head imitation within human-robot interactions, utilizing a closed-loop approach that involves gathering real-time feedback from the robot's imitation performance. This feedback loop ensures a high degree of accuracy in modeling head motion, as evidenced by an impressive R2 score of 96.3 for pitch and 98.9 for yaw. Notably, the proposed approach holds promise in improving communication for children with autism, offering them a valuable tool for more effective interaction. In essence, proposed work explores the integration of real-time head imitation and real-time emotion recognition to enhance human-robot interactions, with potential benefits for individuals with unique communication needs. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

LaCo: Large Language Model Pruning via Layer Collapse

LaCo: Large Language Model Pruning via Layer Collapse

引用

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Yang, Yifei Cao, Zouying Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

ISBN: (纸本)9798891761681

Large language models (LLMs) based on transformer are witnessing a notable trend of size expansion, which brings considerable costs to both model training and inference. However, existing methods such as model quantization, knowledge distillation, and model pruning are constrained by various issues, including hardware support limitations, the need for extensive training, and alterations to the model internal structure. In this paper, we propose a concise layer-wise structured pruner called Layer Collapse (LaCo), in which rear model layers collapse into a prior layer, enabling a rapid reduction in model size while preserving the model structure. Comprehensive experiments show that our method maintains an average task performance of over 80% at pruning ratios of 25-30%, significantly outperforming existing state-of-the-art structured pruning methods. We also conduct post-training experiments to confirm that the LaCo effectively inherits the parameters of the original model. Additionally, we perform ablation studies on various settings of LaCo. Finally, we discuss our motivation from the perspective of layer-wise similarity and evaluate the performance of the pruned LLMs across various pruning ratios. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Head-wise Shareable Attention for Large Language Models

Head-wise Shareable Attention for Large Language Models

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Cao, Zouying Yang, Yifei Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

ISBN: (纸本)9798891761681

Large Language Models (LLMs) suffer from huge number of parameters, which restricts their deployment on edge devices. Weight sharing is one promising solution that encourages weight reuse, effectively reducing memory usage with less performance drop. However, current weight sharing techniques primarily focus on small-scale models like BERT and employ coarse-grained sharing rules, e.g., layer-wise. This becomes limiting given the prevalence of LLMs and sharing an entire layer or block obviously diminishes the flexibility of weight sharing. In this paper, we present a perspective on head-wise shareable attention for large language models. We further propose two memory-efficient methods that share parameters across attention heads, with a specific focus on LLMs. Both of them use the same dynamic strategy to select the shared weight matrices. The first method directly reuses the pre-trained weights without retraining, denoted as DirectShare. The second method first post-trains with constraint on weight matrix similarity and then shares, denoted as PostShare. Experimental results reveal our head-wise shared models still maintain satisfactory capabilities, demonstrating the feasibility of fine-grained weight sharing applied to LLMs. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Ennet: Enhanced Interactive Information Network with Zero-Order Optimization

SSRN

引用

SSRN 2024年

作者： Yang, Pengfei Chen, Yanxin Cheng, Fei Wang, Quan Sun, Jianguo School of Computer Science and Technology Xidian University Xi’an710071 China The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province Xi’an710071 China

Interactive image segmentation extremely accelerates the generation of high-quality annotation image datasets, which are the pillars of the applications of deep learning. However, these methods suffer from the insignificance of interaction information and excessively high optimization costs, resulting in unexpected segmentation outcomes and increased computational burden. To address these issues, this paper focuses on interactive information mining from the network architecture and optimization procedure. In terms of network architecture, the issue mentioned above arises from two perspectives: less representative feature of interactive region in each layer, and the interactive information weakened by the network hierarchy structure. Therefore, the paper proposes a network called EnNet. The network addresses the two aforementioned issues by employing attention mechanisms to integrate user interaction information across the entire image and incorporating interaction information twice in a design that progresses from coarse to fine. In terms of optimization, this paper proposes an optimization method that utilizes zero-order gradient estimation to compute the gradient during the first four iterations, concurrently enhancing the efficiency of model segmentation for challenging cases while reducing optimization costs. The experimental results on GrabCut, Berkeley, DAVIS, and SBD datasets validate the effectiveness of the proposed method, with our approach achieving an average NOC@90 that surpasses RITM by 0.35. © 2024, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Technical Feasibility, Financial Viability, and Clinician Acceptance: On the Many Challenges to AI in Clinical Practice

Technical Feasibility, Financial Viability, and Clinician Ac...

引用

AAAI 2021 Fall Symposium on human Partnership with Medical AI: Design, Operationalization, and Ethics, AAAI-human 2021

作者： Yildirim, Nur Zimmerman, John Preum, Sarah Human-Computer Interaction Institute Carnegie Mellon University United States Computer Science Department Dartmouth College

Artificial intelligence (AI) applications in healthcare offer the promise of improved decision making for clinicians, and better healthcare outcomes for patients. While technical AI advances in healthcare showcase impressive performances in lab settings, they seem to fail when moving to clinical practice. In this position paper, we reflect on our experiences of designing for AI acceptance and discuss three interrelated challenges to AI in clinical practice: technical feasibility, financial viability, and clinician acceptance. We discuss each challenge and their implications for future research in clinical AI. We encourage the research community to take on these lenses in collaboratively tackling the challenges of moving AI systems into real-world healthcare applications. Copyright © 2021, for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Authentication Protocol Suitable for Constrained RFID Systems

引用

IEEE Access 2024年 12卷 61610-61628页

作者： Hosseinzadeh, Mehdi Servati, Mohammad Reza Rahmani, Amir Masoud Safkhani, Masoumeh Lansky, Jan Janoscova, Renata Ahmed, Omed Hassan Tanveer, Jawad Lee, Sang-Woong Duy Tan University Institute of Research and Development Da Nang550000 Viet Nam Duy Tan University School of Medicine and Pharmacy Da Nang550000 Viet Nam Shahid Rajaee Teacher Training University Department of Computer Engineering Tehran16788-15811 Iran National Yunlin University of Science and Technology Future Technology Research Center Douliou Yunlin64002 Taiwan School of Computer Science Tehran19395-5746 Iran University of Finance and Administration Faculty of Economic Studies Department of Computer Science and Mathematics Prague101 00 Czech Republic University of Human Development Department of Information Technology Sulaymaniyah0778-6 Iraq Sejong University Department of Computer Science and Engineering Seoul05006 Korea Republic of Gachon University Pattern Recognition and Machine Learning Laboratory Department of Ai Software Seongnam-si13557 Korea Republic of

RFID technology offers an affordable and user-friendly solution for contactless identification of objects and individuals. However, the widespread adoption of RFID systems raises concerns regarding security and privacy. Vulnerabilities such as message tampering, interception, and eavesdropping pose significant risks to the integrity of the system. This study examines the effectiveness of two recently proposed ultra-lightweight RFID authentication protocols, URASP and KUAJB, in addressing these security challenges. Surprisingly, our findings reveal that both URASP and KUAJB protocols are susceptible to secret disclosure attacks, despite their claims of providing robust security. Consequently, the development of a truly ultra-lightweight protocol that ensures adequate security becomes a formidable task. As a potential solution, the enhancement of the URASP protocol through the integration of a simple cryptographic primitive is suggested to bolster its security measures. © 2013 IEEE.

关键词： Hash functions

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：