检索结果-内蒙古大学图书馆

8th International Conference on robotics and Automation Engineering, ICRAE 2023

作者： Tsai, Yao-Hung Hubert Goh, Hanlin Farhadi, Ali Zhang, Jian Robotics Apple SeattleWA United States Machine Learning Research Apple CupertinoCA United States Computer Science and Engineering University of Washington SeattleWA United States Robotics Apple CupertinoCA United States

ISBN: (纸本)9798350327656

The perception system in personalized mobile agents requires developing indoor scene understanding models, which can understand 3D geometries, capture objectiveness, analyze human behaviors, etc. Nonetheless, this direction has not been well-explored in comparison with models for outdoor environments (e.g., the autonomous driving system that includes pedestrian prediction, car detection, traffic sign recognition, etc.). In this paper, we first discuss the main challenge: insufficient, or even no, labeled data for real-world indoor environments, and other challenges such as fusion between heterogeneous sources of information (e.g., RGB images and Lidar point clouds), modeling relationships between a diverse set of outputs (e.g., 3D object locations, depth estimation, and human poses), and computational efficiency. Then, we describe MMISM (Multi-modality input Multi-task output Indoor Scene understanding Model) to tackle the above challenges. MMISM considers RGB images as well as sparse Lidar points as inputs and 3D object detection, depth completion, human pose estimation, and semantic segmentation as output tasks. We show that MMISM performs on par or even better than single-task models;e.g., we improve the baseline 3D object detection results by 11.7% on the benchmark ARKitScenes dataset. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Bipartite Formation Control for Linear Multi-agent Systems with External Disturbances via Observer-Based Output Feedback 7th

Bipartite Formation Control for Linear Multi-agent Systems ...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative Control, CCSICC 2023

作者： Zhang, Pengyu Mao, Li Zhang, Wei Tang, Kai Laboratory of Intelligent Control and Robotics Shanghai University of Engineering Science 333 Longteng Road Shanghai China Computer Engineering College Dalian University of Technology 1 Guangning Road Dalian China

ISBN: (纸本)9789819733392

This article investigates the problem of bipartite formation control for a class of multi-agent systems composed of two sub-formations with an inverse connection. A distributed control algorithm with observer-based output feedback is proposed under directed signed topology and unknown external disturbances. Some sufficient conditions are established to achieve a bipartite time-varying formation with bounded tracking error. Furthermore, it is shown that the suggested observer-based formation control has good robustness. Finally, a simulation example is illustrated to show the feasibility and effectiveness of the presented control scheme. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

RAMP: A Benchmark for Evaluating Robotic Assembly Manipulation and Planning

引用

IEEE robotics and Automation Letters 2024年第1期9卷 9-16页

作者： Collins, Jack Robson, Mark Yamada, Jun Sridharan, Mohan Janik, Karol Posner, Ingmar University of Oxford Applied AI Lab Oxford Robotics Institute OxfordOX1 3PJ United Kingdom University of Birmingham BirminghamB152TT United Kingdom School of Computer Science University of Birmingham Intelligent Robotics Lab BirminghamB152TT United Kingdom The Manufacturing Technology Centre CoventryCV7 9JU United Kingdom

We introduce RAMP, an open-source robotics benchmark inspired by real-world industrial assembly tasks. RAMP consists of beams that a robot must assemble into specified goal configurations using pegs as fasteners. As such, it assesses planning and execution capabilities, and poses challenges in perception, reasoning, manipulation, diagnostics, fault recovery, and goal parsing. RAMP has been designed to be accessible and extensible. Parts are either 3D printed or otherwise constructed from materials that are readily obtainable. The design of parts and detailed instructions are publicly available. In order to broaden community engagement, RAMP incorporates fixtures such as April Tags which enable researchers to focus on individual sub-tasks of the assembly challenge if desired. We provide a full digital twin as well as rudimentary baselines to enable rapid progress. Our vision is for RAMP to form the substrate for a community-driven endeavour that evolves as capability matures. © 2016 IEEE.

关键词： Robotic assembly

来源：评论

学校读者我要写书评

暂无评论

Designing Optimal Parameters for Single-Axis Solar-Tracker through Analysis of Sun-Path and Tracking Vector Dynamics 6

Designing Optimal Parameters for Single-Axis Solar-Tracker t...

引用

6th International Conference on Electrical Engineering and Information and Communication Technology, ICEEICT 2024

作者： Akhtaruzzaman, M. Islam, Md Shofiqul Shahryer, Fahim Arif, Muammer Din Mollik, Md. Sazib Rahman, Muhammad Towfiqur Rahman, Md. Mahbubur Hasan, Mohammad Kamrul Ahmed, Shugata Ashrafuzzaman, Md. Department of Computer Science and Engineering Dhaka1216 Bangladesh Department of Mechanical Engineering Dhaka1216 Bangladesh Department of Electrical and Electronic Engineering Dhaka Bangladesh Department of Computer Science and Engineering Dhaka Bangladesh Faculty of Information Science and Technology Bangi Malaysia Department of Robotics and Mechatronics Engineering Bangladesh Sdn. Bhd. Cyberjaya Malaysia

ISBN: (纸本)9798350385779

The persistent challenges faced by sun-tracking systems include inefficient power production, wastage of energy, ineffective control, and high costs. Most of the existing systems are either static or dual-axis tracking which lead to inefficient output or increasing energy wastage and cost overheads. Though, single-axis tracking system has some benefits over the static or dual-axis tracking, most of the systems do not analyze the selection of optimal sun-path which again leads to inefficient and inadequate absorption of sunlight. Addressing the issues, this article presents a design of optimal parameters for single-axis solar-tracking by analyzing the sun-path and tracking vector dynamics. The study mainly focuses on analyzing solar-tracking dynamics, variations in sunray angles, Azimuth and Elevation dynamics throughout the day for the twelve months, Sun-vector calculation for local coordinates, joint rotational-axis, and joint motion control using a Proportional-Derivative controller. Additionally, the article outlines a conceptual architecture for automated control, monitoring, and power distribution for the potential development of a sustainable smart city. The proposed strategy addresses the issues of the optimal design of a single-axis solar-tracker, thus ensuring the reduction of cost overhead and energy wastage. © 2024 IEEE.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning 38

DiffTORI: Differentiable Trajectory Optimization for Deep Re...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wan, Weikang Wang, Ziyu Wang, Yufei Erickson, Zackory Held, David Computer Science and Engineering Department University of California San Diego United States Institute for Interdisciplinary Information Sciences Tsinghua University China Robotics Institute Carnegie Mellon University United States

This paper introduces DiffTORI, which utilizes Differentiable Trajectory Optimization as the policy representation to generate actions for deep Reinforcement and Imitation learning. Trajectory optimization is a powerful and widely used algorithm in control, parameterized by a cost and a dynamics function. The key to our approach is to leverage the recent progress in differentiable trajectory optimization, which enables computing the gradients of the loss with respect to the parameters of trajectory optimization. As a result, the cost and dynamics functions of trajectory optimization can be learned end-to-end. DiffTORI addresses the "objective mismatch" issue of prior model-based RL algorithms, as the dynamics model in DiffTORI is learned to directly maximize task performance by differentiating the policy gradient loss through the trajectory optimization process. We further benchmark DiffTORI for imitation learning on standard robotic manipulation task suites with high-dimensional sensory observations and compare our method to feed-forward policy classes as well as Energy-Based Models (EBM) and Diffusion. Across 15 model-based RL tasks and 35 imitation learning tasks with high-dimensional image and point cloud inputs, DiffTORI outperforms prior state-of-the-art methods in both domains. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review of Multi-Robot Collaborative Simultaneous Localization and Mapping

A Review of Multi-Robot Collaborative Simultaneous Localizat...

引用

2023 IEEE International Conference on Unmanned Systems, ICUS 2023

作者： Zhao, Xianzhe Shao, Shiliang Wang, Ting Fang, Chuxi Zhang, Jin Zhao, Hai School of Computer Science and Engineering Northeastern University Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9798350316308

Collaborative Simultaneous Localization and Mapping (C-SLAM), commonly known as multi-robot SLAM, is a prefatory technology that allows multiple robots to efficiently traverse large and intricate areas. This is possible due to the merging of maps and the recognition of shared spaces. Despite its many benefits, multi-robot systems encounter various challenges, such as communication barriers, co-localization issues, and joint optimization problems. This paper reviews the sensors and back-end optimization methods used for SLAM. Then, it summarizes existing collaborative SLAM frameworks and some novel solutions. Finally, it discusses trends and promising research directions for collaborative SLAM. © 2023 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Observer-Based Positive Edge Consensus of Multi-agent Systems on Directed Graphs 7th

Observer-Based Positive Edge Consensus of Multi-agent Syste...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative Control, CCSICC 2023

作者： Zhang, Pengyu Zhang, Wei Mao, Li Chen, Jiayi Hu, Zhi Shanghai University of Engineering Science Laboratory of Intelligent Control and Robotics 333 Longteng Road Shanghai China Computer Engineering College Dalian University of Technology 1 Guangning Road Dalian China

ISBN: (纸本)9789819733231

This paper explores positive edge-consensus in directed networks with spanning trees using output feedback protocols. First, a novel positive system observer is proposed, which introduces a parameter to enhance the design freedom of the observer. Furthermore, using positive system theory and graph theory, sufficient conditions are proposed and the sufficient conditions based solely on the network’s edge count. Specifically, an optimized bound is given for the eigenvalue of the Laplacian matrix, and an improved consensus and non-negative condition is obtained. Finally, the effectiveness of the proposed control protocol is verified utilizing numerical simulations. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

An Attention-Based Approach for Enhanced Robot Grasp Detection in Unstructured Environments 14

An Attention-Based Approach for Enhanced Robot Grasp Detecti...

引用

14th IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems, CYBER 2024

作者： Li, Han Fan, Xinggang Zheng, Dejun Chen, Heping Li, Yaonan Yu, Diqing Jin, Yuao College of Computer Science and Technology Zhejiang University of Technology Hangzhou310023 China Zhijiang College of Zhejiang University of Technology Shaoxing310023 China Shenzhen Academy of Robotics Shenzhen518000 China

ISBN: (纸本)9798331506056

Accurate grasp detection in unstructured environments remains a challenging problem in robot manipulation tasks due to irregular layouts, occlusion, complex backgrounds, and different object shapes. In order to better understand the feature relationship between different positions in the image, a new grasp detection network is proposed in this paper. The attention part of this network combines the advantages of Softmax and linear attention and is named SoLiNet. SoLiNet introduces an additional set of agent labels in the traditional attention module and computes them for each window in each agent. By adjusting the attention weight and position bias of input features, the model can better capture global context information and thus obtain better performance when grasping unknown objects. SoLiNet's accuracy was 98.9% on the Cornell dataset and 96.2% on the Jacquard dataset. It has been successfully used in the actual robot arm grasping system. © 2024 IEEE.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Non-rigid Relative Placement through 3D Dense Diffusion

arXiv

引用

arXiv 2024年

作者： Cai, Eric Donca, Octavian Eisner, Ben Held, David Robotics Institute School of Computer Science Carnegie Mellon University United States

The task of "relative placement" is to predict the placement of one object in relation to another, e.g. placing a mug onto a mug rack. Through explicit object-centric geometric reasoning, recent methods for relative placement have made tremendous progress towards data-efficient learning for robot manipulation while generalizing to unseen task variations. However, they have yet to represent deformable transformations, despite the ubiquity of non-rigid bodies in real world settings. As a first step towards bridging this gap, we propose "cross-displacement" - an extension of the principles of relative placement to geometric relationships between deformable objects - and present a novel vision-based method to learn cross-displacement through dense diffusion. To this end, we demonstrate our method’s ability to generalize to unseen object instances, out-of-distribution scene configurations, and multimodal goals on multiple highly deformable tasks (both in simulation and in the real world) beyond the scope of prior works. Supplementary information and videos can be found at our website. Copyright © 2024, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Enhanced Local Pattern Transformation Based Feature Extraction for Identification of Parkinson’s Disease Using Gait Signals

引用

SN computer science 2023年第2期4卷 1-12页

作者： Klinton Amaladass, P. Subathra, M.S.P. Jeba Priya, S. Sivakumar, Mahima Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Tamil Nadu Coimbatore India Department of Robotics Engineering Karunya Institute of Technology and Sciences Tamil Nadu Coimbatore India

One of the most common ailments, especially among the elderly, is Parkinson's disease (PD). Although previous research has demonstrated that heuristics can diagnose Parkinson's disease using decisive signs like tremor, muscular rigidity, movement disorders, and voice disorders, it has also been reported that current approaches, which rely on simple motor tasks, are limited and lack stability and accessibility. The purpose of this study is to identify a novel cost-effective and time-efficient early detection technique for the prediction of this disease using a signal processing feature extraction approach namely, Shifted Extended Local Binary Pattern (S-ELBP) using gait signals. The features extracted using the proposed methods are given as the input to an artificial neural network (ANN) to classify them as Healthy or Parkinson’s. The proposed method has quite promising results when evaluated using different performance metrics. The method has yielded accuracy: 97.6%, specificity: 95.71%, sensitivity: 99, positive predictive value (PPV): 97.2%, negative predictive value (NPV): 98.8%, Matthews correlation coefficient (MCC): 95.4%, F1-score: 97.9%, and geometric mean: 97.19%. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Feature extraction Parkinson’s disease Parkinson’s gait Shifted extended local binary pattern

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：