检索结果-内蒙古大学图书馆

IEEE International Conference on robotics and Automation (ICRA)

作者： Dehao Huang Chao Tang Hong Zhang Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

The prospect of assistive robots aiding in object organization has always been compelling. In an image-goal setting, the robot rearranges the current scene to match the single image captured from the goal scene. The key to an image-goal rearrangement system is estimating the desired placement pose of each object based on the single goal image and observations from the current scene. In order to establish sufficient associations for accurate estimation, the system should observe an object from a viewpoint similar to that in the goal image. Existing image-goal rearrangement systems, due to their reliance on a fixed viewpoint for perception, often require redundant manipulations to randomly adjust an object’s pose for a better perspective. Addressing this inefficiency, we introduce a novel object rearrangement system that employs multi-view fusion. By observing the current scene from multiple viewpoints before manipulating objects, our approach can estimate a more accurate pose without redundant manipulation times. A standard visual localization pipeline at the object level is developed to capitalize on the advantages of multi-view observations. Simulation results demonstrate that the efficiency of our system outperforms existing single-view systems. The effectiveness of our system is further validated in a physical experiment. For videos, please visit https: //***/view/multi-view-rearr.

关键词： Visualization Accuracy Databases Simulation Standards organizations Pose estimation Pipelines

来源：评论

学校读者我要写书评

暂无评论

FEIF: Feature Excitation and Interactive Fusion for 6D Object Pose Estimation

FEIF: Feature Excitation and Interactive Fusion for 6D Objec...

引用

IEEE International Conference on robotics and Biomimetics

作者： Qiwei Meng Shiqiang Zhu Jianjun Gu Zheyuan Lin Ling Zhong Wei Song 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

In this paper, we present FEIF, a novel framework for 6D object pose estimation from a single RGBD image. Compared with previous approaches, this model fully leverages the complementary RGB and depth information through lay-erwise feature excitation and interactive fusion, thus improving the effectiveness and robustness of extracted features. The representative RGBD features can be subsequently applied for object keypoints prediction and pose computation. In addition, our FEIF includes a self-evaluation module to make robots aware of the confidence of pose estimation, so they are flexible to take the corresponding strategy for following tasks. Experiment results prove the SOTA performance of our model on LineMOD, Occlusion-LineMOD and YCB-Video datasets, and we also demonstrate its applicability and robustness in real-world robotic manipulation.

关键词： Technological innovation Computational modeling Biomimetics Pose estimation Feature extraction Robustness Data mining

来源：评论

学校读者我要写书评

暂无评论

Low-cost Mars Terrain Classification System Based on Coarse-grained Annotation

Low-cost Mars Terrain Classification System Based on Coarse-...

引用

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

GraspGPT: Leveraging Semantic Knowledge from a Large Language Model for Task-Oriented Grasping

arXiv

引用

arXiv 2023年

作者： Tang, Chao Huang, Dehao Ge, Wenqi Liu, Weiyu Zhang, Hong Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Institute for Robotics and Intelligent Machines Georgia Institute of Technology Atlanta United States

Task-oriented grasping (TOG) refers to the problem of predicting grasps on an object that enable subsequent manipulation tasks. To model the complex relationships between objects, tasks, and grasps, existing methods incorporate semantic knowledge as priors into TOG pipelines. However, the existing semantic knowledge is typically constructed based on closed-world concept sets, restraining the generalization to novel concepts out of the pre-defined sets. To address this issue, we propose GraspGPT, a large language model (LLM) based TOG framework that leverages the open-end semantic knowledge from an LLM to achieve zero-shot generalization to novel concepts. We conduct experiments on Language Augmented TaskGrasp (LA-TaskGrasp) dataset and demonstrate that GraspGPT outperforms existing TOG methods on different held-out settings when generalizing to novel concepts out of the training set. The effectiveness of GraspGPT is further validated in real-robot experiments. Our code, data, appendix, and video are publicly available at https://***/view/graspgpt. Copyright © 2023, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Optimization of Residential Net Load using Demand Response and Battery Storage

Optimization of Residential Net Load using Demand Response a...

引用

International Conference on Energy Transition in the Mediterranean Area (SyNERGY MED)

作者： Jorge Bracho Neofytos Ilia George Makrides Alex R. Tseng Panagiotis Herodotou George E. Georgiou Department of Electrical and Computer Engineering PV Technology Laboratory University of Cyprus (UCY) PHAETHON Centre of Excellence (CoE) for Intelligent Efficient and Sustainable Energy Solutions Nicosia Cyprus Electrical and Computer Engineering Princeton University New Jersey U.S

ISBN: (数字)9798350375923

ISBN: (纸本)9798350375930

Demand side management (DSM) and solar-plus-storage systems are enabling technologies that facilitate consumers to increase self-consumption (SC), while reducing electricity costs through efficient and intelligent electricity usage. Even though many demand response (DR) strategies have been presented for the residential sector, a major challenge remains the joint optimal utilization and synergies of DR and the battery systems flexibility scheduling. This paper explores how the optimization of DR and battery energy storage systems (BESS) scheduling can notably improve the net load profile of residential users. The obtained results indicate that the optimized DR model and battery storage effectively support load shifting and peak energy utilization. Specifically, the analysis suggests that the combination of DR and an 8kWh battery storage system increased the SC from 55.04% to 95.84% and the SS from 37.50% to 66.88%, compared to a baseline scenario (without battery storage and DR actions). Ultimately, the proposed optimization achieved a higher degree of energy autonomy for the yearly profile of a median household by minimizing the sum of absolute values of the net load with load shifting and BESS charging/discharging. Finally, the optimization model can be used by aggregators and system operators for scheduling and optimizing flexibility actions.

关键词： Renewable energy sources Costs Electricity Optimization models Solar energy Power system stability Demand response Stability analysis Batteries Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Graph Construction of Power Flow Graphs for Electric Power Transmission Networks

Data-Driven Graph Construction of Power Flow Graphs for Elec...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Benjamin Poole Rajan Ratnakumar Dulip Tharaka Madurasinghe Christian Kümmerle Ganesh Kumar Venayagamoorthy Minwoo Lee Department of Computer Science University of North Carolina Charlotte USA Real-Time Power and Intelligent Systems Laboratory Clemson University USA Department of Electrical Electronic and Computer Engineering University of Pretoria South Africa

ISBN: (数字)9798350374889

ISBN: (纸本)9798350374896

A comprehensive understanding of the topology of the electric power transmission network (EPTN) is essential for reliable and robust control of power systems. While existing research primarily relies on domain-specific methods, it lacks data-driven approaches that have proven effective in modeling the topology of complex systems. To address this gap, this paper explores the potential of data-driven methods for more accurate and adaptive solutions to uncover the true underlying topology of EPTNs. First, this paper examines Gaussian Graphical Models (GGM) to create an EPTN network graph (i.e., undirected simple graph). Second, to further refine and validate this estimated network graph, a physics-based, domain-specific refinement algorithm is proposed to prune false edges and construct the corresponding electric power flow network graph (i.e., directed multi-graph). The proposed method is tested using a synchrophasor dataset collected from a two-area, four-machine power system simulated on the real-time digital simulator (RTDS) platform. Experimental results show both the network and flow graphs can be reconstructed using various operating conditions and topologies with limited failure cases.

关键词： Robust control Network topology Data models Real-time systems Phasor measurement units Power systems Topology Power system reliability Reliability Load flow

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

Efficient Arm Motion Planning with Reduced Viapoints for Mars Rover Operations

Efficient Arm Motion Planning with Reduced Viapoints for Mar...

引用

Space robotics (iSpaRo), International Conference on

作者： Justin Huang Valen Yamamoto Ana Warner Jet Propulsion Laboratory California Institute of Technology Pasadena CA Department of Electrical Engineering and Computer Science UC Irvine Irvine CA Department of Robotics University of Michigan Ann Arbor MI

ISBN: (数字)9798350367232

ISBN: (纸本)9798350367249

This paper describes additions and enhancements we made to the standard RRT-Connect motion planning algorithm to suit the unique needs of operating the robotic arm on the Perseverance Mars Rover. One constraint we have is to maintain a minimum distance between the terrain and any part of the arm hardware. Another goal specific to rover planning is to minimize the number of viapoints in our motion plans. These algorithms should also run efficiently so that rover planners can generate arm motion sequences in time for uplink windows. We applied the RRT-Connect algorithm to the rover’s robotic arm and tested its performance, and we found that it could be used successfully for rover planning with a few changes. First, we implemented the terrain clearance requirement using a software tool called Proximeter. Second, we simplify the paths computed by RRT-Connect to minimize the number of viapoints in a motion plan. Third, we leverage Proximeter to reduce the number of expensive terrain collision checks done by the algorithm, speeding up motion planning.

关键词： Space vehicles Mars Costs Software algorithms Manipulators Hardware Planning

来源：评论

学校读者我要写书评

暂无评论

NavG: Risk-Aware Navigation in Crowded Environments Based on Reinforcement Learning with Guidance Points

arXiv

引用

arXiv 2025年

作者： Zhang, Qianyi Luo, Wentao Liu, Boyi Zhang, Ziyang Wang, Yaoyuan Liu, Jingtai Institute of Robotics and Automatic Information System Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin China Advanced Computing and Storage Lab Huawei 2012 Lab China Department of Electronic and Computer Engineering The Kong Kong University of Science and Technology Hong Kong

Motion planning in navigation systems is highly susceptible to upstream perceptual errors, particularly in human detection and tracking. To mitigate this issue, the concept of guidance points—a novel directional cue within a reinforcement learning-based framework—is introduced. A structured method for identifying guidance points is developed, consisting of obstacle boundary extraction, potential guidance point detection, and redundancy elimination. To integrate guidance points into the navigation pipeline, a perception-to-planning mapping strategy is proposed, unifying guidance points with other perceptual inputs and enabling the RL agent to effectively leverage the complementary relationships among raw laser data, human detection and tracking, and guidance points. Qualitative and quantitative simulations demonstrate that the proposed approach achieves the highest success rate and near-optimal travel times, greatly improving both safety and efficiency. Furthermore, real-world experiments in dynamic corridors and lobbies validate the robot’s ability to confidently navigate around obstacles and robustly avoid pedestrians. © 2025, CC BY.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

An Actor-Critic Reinforcement Learning Scheme for Reactive 3D Optimal Motion Planning Based on Fluid Dynamics

An Actor-Critic Reinforcement Learning Scheme for Reactive 3...

引用

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

作者： Marios Malliaropoulos Panagiotis Rousseas Charalampos P. Bechlioulis Kostas J. Kyriakopoulos School of Mechanical Engineering Control Systems Laboratory National Technical University of Athens Department of Electrical and Computer Engineering University of Patras Center of AI & Robotics (CAIR) New York University Abu Dhabi

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This work proposes a novel and provably correct method for three-dimensional optimal motion planning in complex environments. Our approach models the 3D motion planning problem by solving streamlines of the potential fluid flow, filling a gap in traditional motion planning techniques by guaranteeing a closed-loop, smooth and natural-looking navigation solution. Special emphasis is given to an inherent challenge of artificial potential field (APF) methods, namely establishing proofs of safety and stability over the entire optimization process. A model-based actor-critic reinforcement learning algorithm is introduced to approximate the optimal solution to the Hamilton-Jacobi-Bellman equation and update the controller parameters in a deterministic manner. Through a series of ROS-Gazebo software-in-the-loop simulations the proposed methodology demonstrates robustness and outperforms widely used methods such as the RRT ∗ , highlighting its contribution to the field of 3D optimal motion planning.

关键词： Solid modeling Three-dimensional displays Navigation Reinforcement learning Mathematical models Stability analysis Robustness Planning Safety Optimization

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：