检索结果-内蒙古大学图书馆

IEEE International Conference on robotics and Biomimetics

作者： Jian Zhang Yeheng Chen Shiqiang Zhu Yuehua Li Tian Xie Jason Gu Zhejiang Laboratory Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Hangzhou China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada

ISBN: (纸本)9781665481106

Due to communication latency with remote ground sites, automatic recognition of Mars terrain is essential for the path-planning of rovers. Currently, most vision-based terrain classification require thousands of fine-grained training samples, while the undefined terrains on Mars are difficult to be classified or fine-grained labeled. Actually, most of the terrain categories can only be coarse-grained labeled due to several limitations, such as overlapped sub-regions, blurred borders, etc. To solve this problem, CACMT (Coarse-grained Annotation-based Classification for Mars Terrain) is proposed to generate the global fine-grained classification map from the local coarse-grained data. Specifically, the complete pipeline is decomposed into (i) annotation rules with unique design, (ii) hierarchical feature fusion network for predicting sub-features of terrain (iii) and a generator for outputting dense terrain categories of Mars. Finally, the results of actual data on Mars demonstrate that the terrain sub-features can be successfully recognized and a dense terrain classification map can be generated applying only coarse-grained labeled images.

关键词： Training Image recognition Annotations Biomimetics Pipelines Generators Robots

来源：评论

学校读者我要写书评

暂无评论

Review of Inference Time Prediction Approaches of DNN: Emphasis on Service robots with cloud-edge-device architecture

Review of Inference Time Prediction Approaches of DNN: Empha...

引用

IEEE International Conference on robotics and Biomimetics

作者： Tian Xiang Qiwei Meng Ji Zhang Beibei Zhang Wei Song Anhuan Xie Jason Gu Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Hangzhou China Department of Mechanical and Automation Engineering T Stone Robotics Institute The Chinese University of Hong Kong HKSAR China Research Center for Intelligent Computing Software Research Institute of Intelligent Computing Zhejiang Laboratory Hangzhou China Electrical and Computer Engineering Dalhousie University Halifax Canada

In recent years, the global robot market has witnessed substantial growth, particularly in the domain of service robots. Despite their expanding presence, service robots encounter limitations when operating autonomously in unstructured environments, primarily due to their constrained computational capacities. As a solution, the fusion of cloud and edge computing resources becomes imperative to expedite task inference and enhance scenario perception capabilities. The integration of cloud-edge-device models holds significant promise in bolstering the operational efficiency of robots. This entails the dynamic partitioning of intricate robotic tasks, executed collaboratively across cloud, edge, and device resources. In this landscape, deep neural network (DNN) models play a pivotal role in facilitating a wide array of robotic tasks. The inference time for each layer of a DNN model in actual deployment, emerges as a critical determinant in the model’s partitioning strategy. It also serves as an important metric influencing the model’s suitability for a specific hardware platform. This article presents an overview of recent advancements in predicting inference and training time of DNN models, summarizes the related methods, and finally discusses the challenges in this field and the research that can be studied in the future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HSMR: A Head-Shoulder Mask Aided ResNet to Guide Focus of Re-Identification Implemented on Tour-Guide Robot

HSMR: A Head-Shoulder Mask Aided ResNet to Guide Focus of Re...

引用

IEEE International Conference on robotics and Biomimetics

作者： Zheyuan Lin Min Huang Wen Wang Mengjie Qin Te Li Minhong Wan Jason Gu Shiqiang Zhu Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Hangzhou China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada

ISBN: (纸本)9781665481106

For service robots, person re-identification (ReID) and multi-pedestrian tracking (MPT) are vital to get a person's location and link identities across frames. Though their accuracy keeps improving, most work lacks consideration of the application scenario, haunted by limited space, constrained power supply, and demands of the real-time response during human-robot interaction. Some ReID models learn trivial or unrelated features, inhibiting the downstream tasks. To solve these issues, the efficient and light-weighted Head-Shoulder Mask aided ResNet (HSMR) is proposed. This model applies multi-task learning to enhance the feature extraction performance in the training stage without extra computational load during inference. The auxiliary task fully uses head-shoulder information to guide the network and focuses on the head region, which contains the identity information. In experiments on the Tour-Guide Robot Data Base (TGRDB), HSMR earned results better than ResNet-18 on the ReID task and was superior to the recent two-stream method on the MPT task. On the mobile hardware, inference reaches an average of 15.2 FPS, three times faster than the two-stream method. The code is released at https://***/ZhYLin99/HSMR.

关键词： Training Service robots Computational modeling Robot vision systems Human-robot interaction Multitasking Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Modelling the Dependence of Chlorophyll Leaf-Clip Measures on Vegetation Indices Derived from Multispectral UAS Images in Vineyards Parcels

Modelling the Dependence of Chlorophyll Leaf-Clip Measures o...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Gil Gonçalves Umberto Andriolo Lúcio Paiva Cristiano Premebida António Ferraz Department of Mathematics University of Coimbra Coimbra Portugal Department of Electrical and Computer Engineering INESC Coimbra Coimbra Portugal Research Centre for Natural Resources Environment and Society Polytechnic Institute of Coimbra Coimbra Agrarian Technical School Coimbra Portugal Department of Electrical and Computer Engineering Institute of Systems and Robotics University of Coimbra Coimbra Portugal NASA Jet Propulsion Laboratory Pasadena United States

Multispectral images and leaf-clip measurements were used for evaluating the Chlorophyll (Chl) content on grapevine leaves through the use of vegetation indices. The multispectral leaf images were taken by a sensor onboard an UAS, which was placed over a table at a height of 70 cm. Images were radiometrically and geometrically processed to obtain accurate coregistered five band image stacks. Using a Kmeans segmentation, each leaf imaged in a multispectral image was automatically detected and the mean leaf reflectance values were used to compute three vegetation indices: NDVI, NDRE, and GLI. When compared to leaf-clip measurements, the results indicated that the NDRE index was the best predictor of Chl leaf content (R2=0.81). The obtained NDRE regression model can be used in UAS-based multispectral orthomosaics to generate canopy Chl maps at vine-row scale, which can assist vine growers in monitoring the spatial and temporal variability of grapevine vigor.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simulation to Reality Semantic Segmentation for Humanoid Soccer Robots

Simulation to Reality Semantic Segmentation for Humanoid Soc...

引用

Conference on Artificial Intelligence and robotics and Asia-Pacific International Symposium

作者： Amir Gholami Fatemeh Rashnozadeh Arash Rahmani Ahmadreza Nazari Pegah Behvarmanesh Alejandro Ramirez-Serrano Department of Mechanical and Manufacturing Engineering University of Calgary Calgary Alberta Canada Mechatronics Research Laboratory Qazvin Islamic Azad University Qazvin Iran Department of Electrical and Computer Engineering University of Calgary Calgary Alberta Canada

Deep learning methods like semantic segmentation have gained popularity in computer vision, but challenges remain, particularly in the lack of relevant datasets, such as for humanoid soccer robots. Manually annotating these datasets for segmentation is time-consuming and error-prone. To overcome this, we utilized realistic simulation to quickly generate large datasets and corresponding masks. This paper focuses on applying the u-net architecture on low-end hardware, using a synthetic dataset for training. To evaluate the model, a real annotated dataset was created. Although our Sim-to-Real approach produced a dataset close to reality, the results were unsatisfactory. To address this, transfer learning was employed to fine-tune the network and achieve better accuracy in a real environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-Enhanced Active Disturbance Rejection Control for Mobile Robot Trajectory Tracking

Reinforcement Learning-Enhanced Active Disturbance Rejection...

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： H. Usama M. Nasir R. Fareh J. Ghommam S. Khadraoui M. Bettayeb Research Institute of Sciences and Engineering University of Sharjah Sharjah UAE Department of Electrical Engineering University of Sharjah Sharjah UAE Department of Electrical and Computer Engineering Sultan Qaboos University Oman Control and Energy Management Laboratory (CEM Lab) Ecole National d'Ingenieur de Sfax Tunisia

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

In recent years, the application of robotics has significantly advanced many fields, providing robust performance and efficiency in complex tasks without the need for human intervention. Robot control is a key area of robotics that has received a lot of interest and technological development. Active Disturbance Rejection Controllers (ADRCs) are widely adopted due to several features, including their ability to maintain robust performance and effectively reject disturbances. The manual tuning of controller parameters is time-consuming and highlights the need for automation. This paper presents an innovative approach to tune the parameters of ADRC using Reinforcement Learning (RL) based on Deep Deterministic Policy Gradient (DDPG) for a Differential Drive Mobile Robot (DDMR). The RL agent learns the ideal parameters of the ADRC through real-time, iterative interactions with the simulated environment, improving ADRC's performance without manual tuning. Simulation results demonstrate the effectiveness of the proposed idea in improving the trajectory tracking performance. Combining RL and ADRC provides a promising automated controller tuning solution, opening the door to more intelligent and adaptive robotic systems. 10.0pt.

关键词： Robust control Trajectory tracking Simulation Reinforcement learning Manuals Scattering parameters Mobile robots Artificial intelligence State estimation Tuning

来源：评论

学校读者我要写书评

暂无评论

Clustering-Based Resource Management for Consumer Cost Optimization in IoT Edge Computing Environments

引用

IEEE Transactions on Consumer Electronics 2024年 1-1页

作者： Denden, Mohsen Jemmali, Mahdi Boulila, Wadii Soni, Mukesh Khan, Faheem Ahmad, Jawad Department of Computer and Information Technologies College of Telecommunication and Information CTI Riyadh Saudi Arabia Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah UAE Robotics and Internet-of-Things Laboratory Prince Sultan University Riyadh Saudi Arabia Department of CSE University Centre for Research and Development Chandigarh University Mohali Punjab- India Department of Computer Engineering Gachon University Seongnam-si South Korea School of Computing Engineering and the Built Environment Edinburgh Napier University U.K

Edge computing emerges as a pivotal model in the era of next-generation consumer electronics and the emerging challenges of multimodal data-driven decision-making. Specifically, edge computing offers an open computing architecture for the vast and diverse consumer multimodal data generated by mobile computing and Internet of Things (IoT) technologies. While edge computing is instrumental in optimizing latency and bandwidth control in processing consumer multimodal data, the viability of employing edge resources is complicated by high service costs and the complexities of managing multimodal data diversity. This study introduces an innovative optimization method for distributing multimodal data on edge storage, considering both the I/O (input/output) speed and the overall distribution cost. The core part of our approach is the deployment of intelligent algorithms that ensure equitable data distribution across storage servers, thus eliminating unused space and reducing extra costs. Given the complexity of this NP-hard (non-deterministic polynomial-time) challenge, our study reveals a unique model incorporating an edge-broker component in combination with novel algorithms. The proposed algorithms aim to harmonize data distribution and reduce resource allocation expenses in a multimodal edge environment. Our proposed approach achieves excellent results, highlighting the efficacy of the proposed algorithms in several parameters such as makespan, cost, multimodal data security, and total processing time. Empirical tests reveal that the BCA (Best Clustering Algorithm) performs best, achieving a minimum load balancing rate of 92.2%, an average variance of 0.04, and an average run time of 0.56 seconds. IEEE

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Optimizing Transistor Selection Using AH-TOR for Low Noise Amplifier Design in Sensing Applications

Optimizing Transistor Selection Using AH-TOR for Low Noise A...

引用

International Conference on Sensing Technology, ICST

作者： Dayarnab Baidya Karthick Thiyagarajan Mitradip Bhattacharjee Yang An Department of Electrical Engineering and Computer Science i-Lab Indian Institute of Science Education and Research Bhopal Bhopal Madhya Pradesh India Smart Sensing and Robotics Laboratory (SensR Lab) Centre for Advanced Manufacturing Technology School of Engineering Design and Built Environment Western Sydney University Penrith Australia

ISBN: (数字)9798350374827

ISBN: (纸本)9798350374834

The design of a wireless sensor network receiver requires an efficient Low Noise Amplifier (LNA), with the transistor being a critical component that influences its performance. Selecting an optimal transistor for LNA design is a complex and time-consuming process due to the conflicting criteria involved. This study utilizes the Analytic Hierarchy Trade-off Ranking Method (AH-TOR), an integrated Multi-Criteria Decision-Making (MCDM) approach, to facilitate the selection of a suitable transistor for LNA design. Four types of transistors were evaluated as alternatives based on four criteria, with the Pseudomorphic High Electron Mobility Transistor (PHEMT) emerging as the optimal choice. The weight of PHEMT was calculated to be 1.0787, and its performance was benchmarked against other existing methods. Further analysis demonstrated the robustness of the AH-TOR method across various scenarios, consistently identifying PHEMT as the most suitable option. These findings highlight the reliability of the AH-TOR method for transistor selection in diverse applications.

关键词： Low-noise amplifiers Wireless sensor networks PHEMTs Decision making Receivers Electron mobility Robustness Sensors Transistors Integrated circuit reliability

来源：评论

学校读者我要写书评

暂无评论

Dynamic and Distributed Optimization for the Allocation of Aerial Swarm Vehicles

Dynamic and Distributed Optimization for the Allocation of A...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Jason Hughes Dominic Larkin Charles O’ Donnell Christopher Korpela Department of Electrical Engineering and Computer Science Robotics Research Center United States Military Academy West Point NY USA

ISBN: (数字)9781665405935

ISBN: (纸本)9781665405942

Optimal transport (OT) is a framework that can guide the design of efficient resource allocation strategies in a network of multiple sources and targets. This paper applies discrete OT to a swarm of UAVs in a novel way to achieve appropriate task allocation and execution. Drone swarm deployments already operate in multiple domains where sensors are used to gain knowledge of an environment [1]. Use cases such as, chemical and radiation detection, and thermal and RGB imaging create a specific need for an algorithm that considers parameters on both the UAV and waypoint side and allows for updating the matching scheme as the swarm gains information from the environment. Additionally, the need for a centralized planner can be removed by using a distributed algorithm that can dynamically update based on changes in the swarm network or parameters. To this end, we develop a dynamic and distributed OT algorithm that matches a UAV to the optimal waypoint based on one parameter at the UAV and another parameter at the waypoint. We show the convergence and allocation of the algorithm through a case study and test the algorithm’s effectiveness against a greedy assignment algorithm in simulation.

关键词： Heuristic algorithms Radiation detectors Imaging Autonomous aerial vehicles Dynamic scheduling Sensors Resource management

来源：评论

学校读者我要写书评

暂无评论

Physics Representation Learning for Dexterous Manipulation Planning

Physics Representation Learning for Dexterous Manipulation P...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Yi Wu Mengsha Hu Runxiang Jin Rui Liu Informatique et Sciences du Numérique (Computer Research Laboratory) CentraléSupelec Paris-Saclay University Gif-Sur-Yvette France Cognitive Robotics and AI Lab (CRAI) College of Aeronautics and Engineering Department of Computer Science Kent State University Kent OH USA

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

Dexterous manipulation in robotics, particularly with high degrees of freedom (DoF) devices like the 24-joint Shadow Hand, confronts complexities in search space and execution precision. Humans, however, manipulate objects effortlessly, thanks to their innate grasp of physics. Inspired by this, we introduce the Physics Representation Learning (PRL) framework for robotic hand manipulation. PRL uses physics principles for action conceptualization, such as aligning axes at specific angles (Figure 1). It is a natural language that describes the physics laws, thus bridging the gap between high-level semantics planning and joint-level execution through inverse kinematics (IK). Built on top of the physics-informed action space, PRL deploys a Reinforcement Learning (RL) network with expert demonstrations. Its effectiveness was validated in Nvidia Isaac Sim on four tasks: hammering, unscrewing, sweeping, and pinching. Results show that PRL significantly outperforms conventional joint-control algorithms and RL without demonstrations, underscoring the benefits of physics-based action representations for complex tasks.

关键词： Representation learning Semantics Natural languages Reinforcement learning Kinematics Planning Complexity theory Physics Robots

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：