检索结果-内蒙古大学图书馆

A novel underwater image synthesis method based on a pixel-level self-supervised training strategy

学校读者我要写书评

暂无评论

A novel underwater image synthesis method based on a pixel-l...

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

作者： Wu, Zhiheng Wu, Zhengxing Lu, Yue Wang, Jian Yu, Junzhi Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics BIC-ESAT College of Engineering Peking University Beijing100871 China

ISBN: (纸本)9781665436786

With the rapid development of deep neural networks, underwater vision plays an increasingly important role in the underwater robotic operation. However, the scarce underwater datasets greatly limit the performance of deep learning on underwater visual tasks, further hindering the applications of underwater operation. To solve this problem, we propose an underwater image synthesis method, which can directly convert the natural light image into the synthetic underwater image end-to-end. Particularly, a pixel-level self-supervised training strategy is designed to maximize the structural similarity between the synthesized and real images, through training the real underwater images. Finally, extensive experiments are carried out, and the obtained results demonstrate the effectiveness and superiority of our methods by quantitative and qualitative comparisons. The proposed underwater image synthesis method offers a valuable sight for underwater vision and manipulating control. © 2021 IEEE.

关键词： Deep neural networks

Distilling Tiny and Ultra-fast Deep Neural Networks for Autonomous Navigation on Nano-UAVs

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lamberti, Lorenzo Bellone, Lorenzo Macan, Luka Natalizio, Enrico Conti, Francesco Palossi, Daniele Benini, Luca The Department of Electrical Electronic and Information Engineering University of Bologna Italy The Autonomous Robotics Research Center Technology Innovation Institute United Arab Emirates CNRS LORIA University of Lorraine France The Dalle Molle Institute for Artificial Intelligence USI-SUPSI Switzerland The Integrated Systems Laboratory ETH Zürich Switzerland

Nano-sized unmanned aerial vehicles (UAVs) are ideal candidates for flying Internet-of-Things smart sensors to collect information in narrow spaces. This requires ultra-fast navigation under very tight memory/computation constraints. The PULP-Dronet convolutional neural network (CNN) enables autonomous navigation running aboard a nano-UAV at 19 frame/s, at the cost of a large memory footprint of 320 kB - and with drone control in complex scenarios hindered by the disjoint training of collision avoidance and steering capabilities. In this work, we distill a novel family of CNNs with better capabilities than PULP-Dronet, but memory footprint reduced by up to 168× (down to 2.9 kB), achieving an inference rate of up to 139 frame/s;we collect a new open-source unified collision/steering 66 k images dataset for more robust navigation;and we perform a thorough in-field analysis of both PULP-Dronet and our tiny CNNs running on a commercially available nano-UAV. Our tiniest CNN, called Tiny-PULP-Dronet v3, navigates with a 100% success rate a challenging and never-seen-before path, composed of a narrow obstacle-populated corridor and a 180° turn, at a maximum target speed of 0.5 m/s. In the same scenario, the SoA PULP-Dronet consistently fails despite having 168× more parameters. Copyright © 2024, The Authors. All rights reserved.

关键词： Drones

Probabilistic Multimodal Depth Estimation Based on Camera-LiDAR Sensor Fusion

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Obando-Ceron, Johan S. Romero-Cano, Victor Monteiro, Sildomar Robotics and Autonomous Systems Laboratory Faculty of Engineering Universidad Autónoma de Occidente Valle del Cauca Cali Colombia Autonomy Research Division Aurora Flight Sciences CambridgeMA United States University of Montreal MontréalQC Canada

Multi-modal depth estimation is one of the key challenges for endowing autonomous machines with robust robotic perception capabilities. There have been outstanding advances in the development of uni-modal depth estimation techniques based on either monocular cameras, because of their rich resolution, or LiDAR sensors, due to the precise geometric data they provide. However, each of these suffers from some inherent drawbacks, such as high sensitivity to changes in illumination conditions in the case of cameras and limited resolution for the LiDARs. Sensor fusion can be used to combine the merits and compensate for the downsides of these two kinds of sensors. Nevertheless, current fusion methods work at a high level. They process the sensor data streams independently and combine the high-level estimates obtained for each sensor. In this paper, we tackle the problem at a low level, fusing the raw sensor streams, thus obtaining depth estimates which are both dense and precise, and can be used as a unified multi-modal data source for higher level estimation problems. This work proposes a Conditional Random Field model with multiple geometry and appearance potentials. It seamlessly represents the problem of estimating dense depth maps from camera and LiDAR data. The model can be optimized efficiently using the Conjugate Gradient Squared algorithm. The proposed method was evaluated and compared with the state-of-the-art using the commonly used KITTI benchmark dataset. © 2023, CC BY.

关键词： Cameras

Exoskeleton-Based Lower Limb Rehabilitation Robot Design and Simulation for Children with Cerebral Palsy

学校读者我要写书评

暂无评论

Exoskeleton-Based Lower Limb Rehabilitation Robot Design and...

World Rehabilitation Robot Convention (WRRC)

作者： Wujing Cao Shuo Zhang Yupeng Zou Xinqiang Guo Changyu Li Jingxin Wang Worawarit Kobsiriphat Xinyu Wu Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China and SIAT-CUHK Joint Laboratory of Robotics and Intelligent Systems. SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society School of Mechanical Engineering China University of Petroleum East China Jining Zhongke Intelligent Technology Co. Ltd. Department of Rehabilitation Medicine Zhengzhou Central Hospital Affiliated Zhengzhou University Zhengzhou China National Metal and Materials Technology Center Thailand

ISBN: (数字)9798350355123

ISBN: (纸本)9798350355130

Squat gait is the most common abnormal gait in children with cerebral palsy. Gait training with lower limb rehabilitation robots can improve rehabilitation efficiency and reduce manual labor for them. A novel exoskeleton-based lower limb rehabilitation robot for children with cerebral palsy is proposed, considering the squat gait characteristics of children with cerebral palsy. The structure of the lower limb rehabilitation robot, which combines hip and knee with 4 active degrees of freedom exoskeleton and mobile walker, is designed and optimized. Static analysis of the key mechanical structure of the exoskeleton is conducted using ANSYS Workbench, and local structures are optimized to ensure the safety factor of the mechanical structure is greater than 1, guaranteeing reasonable structural strength and stiffness design. Dynamic simulation analysis based on the ADAMS model validates the reliability and dynamic walking effect of the lower limb exoskeleton rehabilitation robot, obtaining the curve relationship between joint angles and motion cycles, thus verifying the effectiveness of the mechanical system motion.

关键词： Knee Training Cerebral palsy Exoskeletons Dynamics Static analysis Assistive robots Safety Finite element analysis Hip

Distributed Banach-Picard Iteration for Locally Contractive Maps

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Andrade, Francisco Figueiredo, Mário A.T. Xavier, João Instituto Superior Técnico Universidade de Lisboa Lisbon Portugal Instituto de Telecomunicações Lisbon Portugal Laboratory for Robotics and Engineering Systems Institute for Systems and Robotics Lisbon Portugal

The Banach-Picard iteration is widely used to find fixed points of locally contractive (LC) maps. This paper extends the Banach-Picard iteration to distributed settings;specifically, we assume the map of which the fixed point is sought to be the average of individual (not necessarily LC) maps held by a set of agents linked by a communication network. An additional difficulty is that the LC map is not assumed to come from an underlying optimization problem, which prevents exploiting strong global properties such as convexity or Lipschitzianity. Yet, we propose a distributed algorithm and prove its convergence, in fact showing that it maintains the linear rate of the standard Banach-Picard iteration for the average LC map. As another contribution, our proof imports tools from perturbation theory of linear operators, which, to the best of our knowledge, had not been used before in the theory of distributed *** Codes 37C25 © 2021, CC BY-NC-ND.

关键词： Mathematical operators

学校读者我要写书评

暂无评论

IEEE International Conference on Image Processing

作者： Chaowei Han Gaofeng Meng Chunlei Huo State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics HK Institute of Science & Innovation Chinese Academy of Sciences School of Information Engineering Capital Normal University Beijing China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Content-based video retrieval aims to retrieve near-duplicate entries from a database of a given query video. It plays an important role in combating video piracy. Robustness to video temporal dynamics is crucial for a representation model in video retrieval, as frames extracted from two copied videos are hardly temporally aligned in actual situations. However, current image retrieval datasets have difficulty in evaluating this robustness. To address this issue, we collect Similar Frame Dataset (SFD), which consists of 32,923 query-target pairs with 128,240 distraction images. The task of SFD is to retrieve the target frame from all items given a query frame. SFD is constructed by sampling frames from Kinetics-700 action classification dataset. An object detection model (Faster R-CNN) and a Multimodal Large Language Model (BLIP2) are used during sampling to select those valid frames. Besides, we propose Adjacent Frames Contrastive Learning (AFCL) framework. In AFCL, adjacent frames are sampled from unlabeled videos as positive pairs. An image representation model with robustness to changing frames can be trained under AFCL framework and achieve the state-of-the-art performance on SFD. The code will be released at https://***/Chuan-shanjia/Similar-Frame-Dataset.

关键词： Codes Databases Scalability Large language models Image retrieval Contrastive learning Object detection

Sample Efficient Dynamics Learning for Symmetrical Legged Robots: Leveraging Physics Invariance and Geometric Symmetries

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lee, Jee-Eun Lee, Jaemin Bandyopadhyay, Tirthankar Sentis, Luis Human Centered Robotics Laboratory Department of Aerospace Engineering and Engineering Mechanics The University of Texas Austin United States The Department of Mechanical and Civil Engineering California Institute of Technology PasadenaCA United States Faculty of Department of Aerospace Engineering and Engineering Mechanics The University of Texas Austin United States Robotics and Autonomous Systems Group Data61 Csiro QLD 4069 Australia

Model generalization of the underlying dynamics is critical for achieving data efficiency when learning for robot control. This paper proposes a novel approach for learning dynamics leveraging the symmetry in the underlying robotic system, which allows for robust extrapolation from fewer samples. Existing frameworks that represent all data in vector space fail to consider the structured information of the robot, such as leg symmetry, rotational symmetry, and physics invariance. As a result, these schemes require vast amounts of training data to learn the system's redundant elements because they are learned independently. Instead, we propose considering the geometric prior by representing the system in symmetrical object groups and designing neural network architecture to assess invariance and equivariance between the objects. Finally, we demonstrate the effectiveness of our approach by comparing the generalization to unseen data of the proposed model and the existing models. We also implement a controller of a climbing robot based on learned inverse dynamics models. The results show that our method generates accurate control inputs that help the robot reach the desired state while requiring less training data than existing methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Vector spaces

Fault Diagnostic Opportunities for Electromagnetic Coils of Active Magnetic Bearings using Physics-of-Failure Analysis

学校读者我要写书评

暂无评论

Fault Diagnostic Opportunities for Electromagnetic Coils of ...

System Reliability and Safety engineering (SRSE), International Conference on

作者： Ruiqi Li Kai Wang Peng Zeng Jiwei Cao 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 University of Chinese Academy of Sciences Beijing China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Department of Electrical Engineering Harbin Institute of Technology China

Active magnetic bearings (AMBs) have many advantages over traditional oil bearings due to their non-contact characteristics. They are environmentally friendly solution and have been proven to be highly reliable and available. Electromagnetic coils are vital components of AMB and they are failure prone. In this paper, the failure mode of magnetic bearing coil and its corresponding failure mechanism are reviewed by FMMEA method, and the existing coil fault diagnosis methods are introduced. Future directions for coil insulation health monitoring aiming at the application characteristics of AMBs are also discussed.

关键词：

Towards Autonomous Navigation of a Mobile Robot in a Steep Slope Vineyard

学校读者我要写书评

暂无评论

Towards Autonomous Navigation of a Mobile Robot in a Steep S...

Proceedings of the International Convention MIPRO

作者： I. Hrabar J. Goričanec Z. Kovačić University of Zagreb Faculty of Electrical Engineering and Computing Laboratory for Robotics and Intelligent Control Systems (LARICS) Zagreb Croatia

This paper explores potential applications of an autonomous all-terrain mobile manipulator (AMM) in the agricultural vineyard environment. A robotic arm mounted on a mobile base performs a spraying task while moving past vines and a bud rubbing task while stopping next to vines. We discuss the challenges of AMM navigation when performing tasks in steep vineyard terrain. The presented navigation approach is based on the use of a heterogeneous robotic system consisting of an unmanned aerial vehicle (UAV) and AMM. The navigation information provided by the UAV gives the waypoints for the AMM. We also present preliminary results from navigation simulation, based on digital elevation model (DEM). The model uses real-world data, acquired by UAV photogrammetric measurement campaign. We conclude by highlighting some open problems and related future research directions.

关键词：