检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Guangming Pan, Lei Peng, Songyou Liu, Shaohui Xu, Chenfeng Miao, Yanzi Zhan, Wei Tomizuka, Masayoshi Pollefeys, Marc Wang, Hesheng The University of Cambridge ETH Zurich Switzerland The Department of Automation Shanghai Jiao Tong University Shanghai200240 China The Key Laboratory of System Control and Information Processing Ministry of Education of China China Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China ETH Zurich Zurich Switzerland Mechanical Systems Control Laboratory University of California Berkeley United States

Meticulous 3D environment representations have been a longstanding goal in computer vision and robotics fields. The recent emergence of neural implicit representations has introduced radical innovation to this field as implicit representations enable numerous capabilities. Among these, the Neural Radiance Field (NeRF) has sparked a trend because of the huge representational advantages, such as simplified mathematical models, compact environment storage, and continuous scene representations. Apart from computer vision, NeRF has also shown tremendous potential in the field of robotics. Thus, we create this survey to provide a comprehensive understanding of NeRF in the field of robotics. By exploring the advantages and limitations of NeRF, as well as its current applications and future potential, we hope to shed light on this promising area of research. Our survey is divided into two main sections: The Application of NeRF in robotics and The Advance of NeRF in robotics, from the perspective of how NeRF enters the field of robotics. In the first section, we introduce and analyze some works that have been or could be used in the field of robotics from the perception and interaction perspectives. In the second section, we show some works related to improving NeRF's own properties, which are essential for deploying NeRF in the field of robotics. In the discussion section of the review, we summarize the existing challenges and provide some valuable future research directions for reference. © 2024, CC BY-NC-ND.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

Description and fault diagnosis in autonomous underwater vehicles based on ontologies

Description and fault diagnosis in autonomous underwater veh...

引用

Ocean Studies (ICOS), International Conference on

作者： Timoshenko Alexander Zuev Alexander Mursalimov Eduard Gribova Valeria Inzartsev Alexander Department of Automation and Robotics Laboratory of intelligent systems for marine robots Far Eastern Federal UniversityInstitute of Marine Technology Problems FEB RAS Vladivostok Russia Laboratory of Intelligent Systems Institute of Automation and Control FEB RAS Vladivostok Russia Laboratory of Control Systems Institute of Marine Technology Problems FEB RAS Vladivostok Russia

ISBN: (纸本)9781665473736

The paper proposes new ontologies for describing and diagnosing malfunctions of subsystems of autonomous underwater vehicles (AUV) as a part of the development of a previously created approach to the intelligent diagnosis of these vehicles using knowledge bases. To implement this approach, it is proposed to use two knowledge bases, one of which describes malfunctions, features for their identification and actions necessary to adapt to the negative consequences caused by the appearance of these malfunctions. The other database contains information about the main subsystems of the AUV, devices and replaceable modules, as well as the states they may be in. Knowledge bases are used in the work of the intelligent control-emergency system (ICES) on board the AUV, which allows for comprehensive functional diagnostics of all subsystems of the device, including payload modules, as well as adaptation to the consequences of emerging malfunctions, taking into account the actual cause-and-effect relationships between them. To test the system’s operability, a prototype was developed. The results of the prototype simulation showed that ICES performs the tasks and can be implemented on the onboard computers of existing AUV using well-known programming technologies.

关键词： Performance evaluation Autonomous underwater vehicles Simulation Knowledge based systems Prototypes Ontologies Programming

来源：评论

学校读者我要写书评

暂无评论

A localizability estimation method for mobile robots based on 3D point cloud feature

A localizability estimation method for mobile robots based o...

引用

2021 IEEE International Conference on Real-Time Computing and robotics, RCAR 2021

作者： Liu, Ying Wang, Jingchuan Huang, Yi Institute of Medical Robotics Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Department of Automation Shanghai200240 China Nanjing Kingyoung Intelligent Technology CO. LTD.

ISBN: (纸本)9781665436786

This paper introduces the theoretical analysis and derivation of localizability estimation for mobile robots based on point cloud observation. Combined with the observation model, the pre-established point cloud map is firstly clustered and segmented with a newly proposed method considering multiple constraints on depth map. Then localizability is set to be equal to the strength of the constraints associated with 3D point cloud features. In addition, based on the method of using information matrix theory, this paper integrates the Fisher's information matrix and point cloud features to estimate localizability. © 2021 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Marker or Markerless? Mode-Switchable Optical Tactile Sensing for Diverse Robot Tasks

arXiv

引用

arXiv 2024年

作者： Ou, Ni Chen, Zhuo Luo, Shan The State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing100081 China The Robot Perception Lab. Centre for Robotics Research Department of Engineering King’s College London LondonWC2R 2LS United Kingdom

Optical tactile sensors play a pivotal role in robot perception and manipulation tasks. The membrane of these sensors can be painted with markers or remain markerless, enabling them to function in either marker or markerless mode. However, this uni-modal selection means the sensor is only suitable for either manipulation or perception tasks. While markers are vital for manipulation, they can also obstruct the camera, thereby impeding perception. The dilemma of selecting between marker and markerless modes presents a significant obstacle. To address this issue, we propose a novel mode-switchable optical tactile sensing approach that facilitates transitions between the two modes. The marker-to-markerless transition is achieved through a generative model, whereas its inverse transition is realized using a sparsely supervised regressive model. Our approach allows a single-mode optical sensor to operate effectively in both marker and markerless modes without the need for additional hardware, making it well-suited for both perception and manipulation tasks. Extensive experiments validate the effectiveness of our method. For perception tasks, our approach decreases the number of categories that include misclassified samples by 2 and improves contact area segmentation IoU by 3.53%. For manipulation tasks, our method attains a high success rate of 92.59% in slip detection. Code, dataset and demo videos are available at the project website https://***/Marker-Markerless-Transition/ Copyright © 2024, The Authors. All rights reserved.

关键词： Tactile sensors

来源：评论

学校读者我要写书评

暂无评论

An Improved Method for Small Target Recognition Based on Faster RCNN 17th

An Improved Method for Small Target Recognition Based on Fas...

引用

17th Chinese intelligent Systems Conference, CISC 2021

作者： Liu, Qun-po Wang, Qi-jing Hanajima, Naohiko Su, Bo Department of Robotics Engineering Henan Polytechnic University 2001 Century Avenue Jiaozuo Henan454003 China Henan International Joint Laboratory of Direct Drive and Control of Intelligent Equipment 2001 Century Avenue Jiaozuo Henan454003 China College of Information and Systems Muroran Institute of Technology 27-1 Mizumoto-cho Muroran-shi Hokkaido050-8585 Japan

ISBN: (纸本)9789811663239

As one of the most challenging tasks in the field of deep learning, target detection has achieved remarkable results. The existing algorithms have achieved excellent results in the detection of large and medium-sized targets, but the detection accuracy of small targets is not ideal because of their small size and weak features. A small target recognition method based on improved Faster_Rcnn that aims at the problem of low accuracy in small target detection is proposed in this paper. Since the ROI Pooling method in Faster Rcnn might cause quantization errors in the operation process, resulting in inaccurate positioning and other problems during detection, an improved ROI Align method is adopted to eliminate the quantization errors. The cell public data set is used for the experiment, the results show that the average recognition accuracy of the recognition model with improved algorithm is 92.11%, which is an increase of 7%. The method also obtains good effect on NWPU VHR-10 data set, which indicates that it has good universality. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Application of Deep Learning Method to Estimate Bottomhole Pressure Dynamics of Oil Wells

Application of Deep Learning Method to Estimate Bottomhole P...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Haibo Cheng Shichao Li Peng Zeng Valeriy Vyatkin State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Department of Computer Science Electrical and Space Engineering Luleå University of Technology Luleå Sweden Department of Electrical Engineering and Automation Aalto University Helsinki Finland

Surrogate models, which have become an effective and popular method to close loop reservoir management problems, use a data-driven approach to predict dynamic injection and production wells parameters and optimize waterflooding development. In this study, a deep learning-based surrogate model method is proposed to estimate bottomhole pressure (BHP) of production wells in waterflooding reservoirs. Bidirectional long short-term memory (BiLSTM) network, as an efficient deep learning approach, is applied to BHP estimation using fluctuation data. Extended Fourier amplitude sensitivity test (EFAST) method is employed to analyse the influence of different input factors on BHP dynamics, and a reduced dataset is rebuilt to predict BHP parameter based on BiLSTM-EFAST algorithm. The estimation results are tested on a dataset from Volve oilfield in North Sea, and compared with other deep learning methods. The test results indicate that the proposed method can achieve higher prediction accuracy. A reduced dataset-based approach provides a new attempt to reduce model complexity and improve calculation speed for big data-driven surrogate model in oil and gas industry.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Block Elevation Mapping for Large-scale Scene

Adaptive Block Elevation Mapping for Large-scale Scene

引用

IEEE International Conference on robotics and Biomimetics

作者： Yang Zhou Shiqiang Zhu Huang Huang Yuehua Li Jason Gu Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Hangzhou China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Beijing Institute of Control Engineering Beijing China Beijing Research Institute of Zhejiang Laboratory Beijing China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada

ISBN: (纸本)9781665481106

Dense map that contains the surrounding geometry and vision information of a robot is widely used for path planning, navigation, obstacle avoidance and other applications. Considering the performance of the processing unit mounted on the robot is limited, mapping algorithm has to make compromise by sacrificing speed and precision. It will be more challenging when the dense mapping scene is very large because the memory consumption will be greatly increased and the map is difficult to be extended if beyonding the initial map. To suppress the negative impact from the increased map scale, we proposed a novel block mapping approach to generate the dense map in large scale of scene. In this work, the elevation map is selected as the base dense map. The entire elevation map is segmented into numerous block maps of which size is much smaller than that of the entire map. The present moment of lidar and vision measurements are used to generate the local elevation map. The local elevation map is used to update block maps which are adaptively generated along the motion trajectory. A memory-disk interaction mechanism, which the block maps will be loaded to memory or saved to local disk when needed, is introduced. Our block mapping approach is tested on the KITTI datasets, and the results demonstrate that the mapping approach can stably operate in a large scale of scene with a much smaller consumption of memory.

关键词： Geometry Laser radar Navigation Motion segmentation Memory management Robot sensing systems Trajectory

来源：评论

学校读者我要写书评

暂无评论

Intracranial Photodynamic Therapy Strategy Based Magnetic Continuum Robots for Glioblastoma Management

SSRN

引用

SSRN 2024年

作者： Wu, Junfeng Li, Na Lin, Daojing Zhou, Junjian Song, Yingqiu Liu, Lianqing Jiao, Niandong School of Electrical and Control Engineering Shenyang Jianzhu University Shenyang110168 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Department of Radiotherapy Cancer Hospital of China Medical University Shenyang110042 China

Glioblastoma multiforme (GBM), a malignant brain tumor, poses a significant global health challenge because of its high invasiveness and resistance to treatment. Photodynamic therapy (PDT), with its high spatial-temporal selectivity, holds promise for GBM treatment, offering strong local selectivity, minimal systemic side effects, and low resistance. However, delivering photosensitizers across the blood-brain barrier and precisely targeting brain tumors through the skull with a laser present critical challenges to clinical application. Addressing these challenges, the soft, continuous structure and remote magnetic control of magnetic continuum robots (MCRs) offer new possibilities for precise delivery to GBM. Here, we propose an intracranial PDT strategy using MCRs, featuring a magnetic control model based on Gaussian Process Regression and a computer vision-based closed-loop control algorithm. This approach enables automatic delivery of nanomedicines and localized laser irradiation, characterized by simplicity, minimal data needs, and robustness. Additionally, under the combined effects of photodynamic nanoparticles (PNPs) and a laser, both U87 and GL261 cells exhibit high mortality rates, which increase with the concentration of PNPs, laser energy, and duration of exposure. In conclusion, this strategy overcomes PDT's limitations to superficial lesions, offers a novel GBM treatment approach, and constitutes a key milestone for using PDT in GBM treatment. © 2024, The Authors. All rights reserved.

关键词： Photodynamic therapy

来源：评论

学校读者我要写书评

暂无评论

Environment-Driven Online LiDAR-Camera Extrinsic Calibration

arXiv

引用

arXiv 2025年

作者： Huang, Zhiwei Li, Jiaqi Zhong, Ping Fan, Rui The Department of Control Science & Engineering The College of Electronics & Information Engineering Tongji University Shanghai201804 China The School of Computer Science and Engineering Central South University Hunan Changsha410083 China The National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology Hunan Changsha410073 China The Department of Control Science & Engineering The College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China The National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi Xi’an710049 China

LiDAR-camera extrinsic calibration (LCEC) is the core for data fusion in computer vision. Existing methods typically rely on customized calibration targets or fixed scene types, lacking the flexibility to handle variations in sensor data and environmental contexts. This paper introduces EdO-LCEC, the first environment-driven, online calibration approach that achieves human-like adaptability. Inspired by the human perceptual system, EdO-LCEC incorporates a generalizable scene discriminator to actively interpret environmental conditions, creating multiple virtual cameras that capture detailed spatial and textural information. To overcome cross-modal feature matching challenges between LiDAR and camera, we propose dual-path correspondence matching (DPCM), which leverages both structural and textural consistency to achieve reliable 3D-2D correspondences. Our approach formulates the calibration process as a spatial-temporal joint optimization problem, utilizing global constraints from multiple views and scenes to improve accuracy, particularly in sparse or partially overlapping sensor views. Extensive experiments on real-world datasets demonstrate that EdO-LCEC achieves state-of-the-art performance, providing reliable and precise calibration across diverse, challenging environments. Copyright © 2025, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion

arXiv

引用

arXiv 2022年

作者： Jiang, Chaokang Wang, Guangming Miao, Yanzi Wang, Hesheng Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China

3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space, which possesses the capacity to infer autonomously the non-rigid motion of all objects in the scene. The previous methods for estimating scene flow from images have limitations, which split the holistic nature of 3D scene flow by estimating optical flow and disparity separately. Learning 3D scene flow from point clouds also faces the difficulties of the gap between synthesized and real data and the sparsity of LiDAR point clouds. In this paper, the generated dense depth map is utilized to obtain explicit 3D coordinates, which achieves direct learning of 3D scene flow from 2D images. The stability of the predicted scene flow is improved by introducing the dense nature of 2D pixels into the 3D space. Outliers in the generated 3D point cloud are removed by statistical methods to weaken the impact of noisy points on the 3D scene flow estimation task. Disparity consistency loss is proposed to achieve more effective unsupervised learning of 3D scene flow. The proposed method of self-supervised learning of 3D scene flow on real-world images is compared with a variety of methods for learning on the synthesized dataset and learning on LiDAR point clouds. The comparisons of multiple scene flow metrics are shown to demonstrate the effectiveness and superiority of introducing pseudo-LiDAR point cloud to scene flow estimation. © 2022, CC BY.

关键词： Three dimensional computer graphics

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：