检索结果-内蒙古大学图书馆

Using Fiber Optic Bundles to Miniaturize Vision-Based Tactile Sensors

IEEE TRANSACTIONS ON robotics 2025年 41卷 62-81页

作者： Di, Julia Dugonjic, Zdravko Fu, Will Wu, Tingfan Mercado, Romeo Sawyer, Kevin Most, Victoria Rose Kammerer, Gregg Speidel, Stefanie Fan, Richard E. Sonn, Geoffrey Cutkosky, Mark R. Lambeta, Mike Calandra, Roberto Stanford Univ Stanford CA 94305 USA Meta Menlo Pk CA 92093 USA Tech Univ Dresden LASR Lab D-01307 Dresden Germany Sch Embedded & Composite AI SECAI D-01069 Dresden Germany Natl Ctr Tumor Dis NCT UCC Dresden D-01307 Dresden Germany Ctr Tactile Internet Human Inthe Loop CeTI D-01069 Dresden Germany

Vision-based tactile sensors have recently become popular due to their combination of low cost, very high spatial resolution, and ease of integration using widely available miniature cameras. The associated field of view and focal length, however, are difficult to package in a human-sized finger. In this article we employ optical fiber bundles to achieve a form factor that, at 15 mm diameter, is smaller than an average human fingertip. The electronics and camera are also located remotely, further reducing package size. The sensor achieves a spatial resolution of 0.22 mm and a minimum force resolution 5 mN for normal and shear contact forces. With these attributes, the DIGIT Pinki sensor is suitable for applications such as robotic and teleoperated digital palpation. We demonstrate its utility for palpation of the prostate gland and show that it can achieve clinically relevant discrimination of prostate stiffness for phantom and ex vivo tissue.

关键词： Robot sensing systems Optical fibers Optical fiber sensors Cameras Tactile sensors Robots Elastomers Lighting Optical imaging Spatial resolution deep learning in robotics fiber optics force and tactile sensing medical robotics object hardness perception for grasping and manipulation robotic palpation tissue palpation

来源：评论

学校读者我要写书评

暂无评论

Machine Vision-Assisted Design of End Effector Pose in Robotic Mixed Depalletizing of Heterogeneous Cargo

引用

SENSORS 2025年第4期25卷 1137-1137页

作者： Valero, Sebastian Martinez, Juan Camilo Montes, Ana Maria Marin, Cesar Bolanos, Ruben Alvarez, David Univ Andes Dept Ind Engn Bogota 111711 Colombia Integra SA Pereira 660003 Colombia

Automated depalletizing systems aim to offer continuous and efficient operation in warehouse logistics, reducing cycle times and contributing to worker safety. However, most commercially available depalletizing solutions are designed primarily for highly homogeneous cargo arranged in orthogonal configurations. This paper presents a real-time approach for depalletizing heterogeneous pallets with boxes of varying sizes and arbitrary orientations, including configurations where the topmost surfaces of boxes are not necessarily parallel to each other. To accomplish this, we propose an algorithm that leverages deep learning-based machine vision to determine the size, position, and orientation of boxes relative to the horizontal plane of a robot arm from sparse depth data. Using this information, we implement a path planning method that generates collision-free trajectories to enable precise box grasping and placement onto a production line. Validation through both simulated and real-world experiments demonstrates the feasibility and accuracy of this approach in complex industrial settings, highlighting potential improvements in the efficiency and adaptability of automated depalletizing systems.

关键词： segmentation hand-eye calibration robotic depalletizing heterogeneous cargo handling deep learning in robotics sparse stereo vision 3D object detection non-orthogonal pallet configurations pick-and-place robotics

来源：评论

学校读者我要写书评

暂无评论

A Vision-Guided deep learning Framework for Dexterous Robotic Grasping Using Gaussian Processes and Transformers

引用

APPLIED SCIENCES-BASEL 2025年第5期15卷 2615-2615页

作者： Sampath, Suhas Kadalagere Wang, Ning Yang, Chenguang Wu, Howard Liu, Cunjia Pearson, Martin Univ West England Fac Engn & Technol Bristol BS16 1QY England Sheffield Hallam Univ Sch Comp & Digital Technol Sheffield S9 2AA England Univ Liverpool Dept Comp Sci Liverpool L3 5TR England Antobot Ltd Cambridge CB1 1AH England Loughborough Univ Dept Aeronaut & Automot Engn Loughborough LE11 3TT Leics England

Robotic manipulation of objects with diverse shapes, sizes, and properties, especially deformable ones, remains a significant challenge in automation, necessitating human-like dexterity through the integration of perception, learning, and control. This study enhances a previous framework combining YOLOv8 for object detection and LSTM networks for adaptive grasping by introducing Gaussian Processes (GPs) for robust grasp predictions and Transformer models for efficient multi-modal sensory data integration. A Random Forest classifier also selects optimal grasp configurations based on object-specific features like geometry and stability. The proposed grasping framework achieved a 95.6% grasp success rate using Transformer-based force modulation, surpassing LSTM (91.3%) and GP (91.3%) models. Evaluation of a diverse dataset showed significant improvements in grasp force modulation, adaptability, and robustness for two- and three-finger grasps. However, limitations were observed in five-finger grasps for certain objects, and some classification failures occurred in the vision system. Overall, this combination of vision-based detection and advanced learning techniques offers a scalable solution for flexible robotic manipulation.

关键词： dexterous robotic grasping adaptive grasping deep learning in robotics transformer networks Gaussian processes vision-based force modulation

来源：评论

学校读者我要写书评

暂无评论

Shape estimation for a TPU-based multi-material 3D printed soft pneumatic actuator using deep learning models

引用

Science China(Technological Sciences) 2024年第5期67卷 1470-1481页

作者： HU Yu TANG Wei QU Yang XU HuXiu KRAMARENKO Yu.Elena ZOU Jun State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang UniversityHangzhou310058China School of Mechanical Engineering Zhejiang UniversityHangzhou310027China Institute of Process Equipment College of Energy EngineeringZhejiang UniversityHangzhou310027China Faculty of Physics Lomonosov Moscow State UniversityMoscow119991Russia Enikolopov Institute of Synthetic Polymeric Materials of Russian Academy of Sciences Moscow117393Russia

Real-time proprioception presents a significant challenge for soft robots due to their infinite degrees of freedom and intrinsic *** studies mostly focused on specific sensors and *** is still a lack of generalizable technologies for integrating soft sensing elements into soft actuators and mapping sensor signals to proprioception *** tackle this problem,we employed multi-material 3D printing technology to fabricate sensorized soft-bending actuators(SBAs)using plain and conductive thermoplastic polyurethane(TPU)*** designed various geometric shapes for the sensors and investigated their strain-resistive performance during *** address the nonlinear time-variant behavior of the sensors during dynamic modeling,we adopted a data-driven approach using different deep neural networks to learn the relationship between sensor signals and system states.A series of experiments in various actuation scenarios were conducted,and the results demonstrated the effectiveness of this *** sensing and shape prediction steps can run in real-time at a frequency of50 Hz on a consumer-level ***,a method is proposed to enhance the robustness of the learning models using data augmentation to handle unexpected sensor *** the methods are efficient,not only for in-plane 2D shape estimation but also for out-of-plane 3D shape *** aim of this study is to introduce a methodology for the proprioception of soft pneumatic actuators,including manufacturing and sensing modeling,that can be generalized to other soft robots.

关键词： shape estimation soft sensors and actuators 3D printing deep learning in robotics

来源：评论

学校读者我要写书评

暂无评论

Foot Vision: A Vision-Based Multi-Functional Sensorized Foot for Quadruped Robots

引用

IEEE robotics AND AUTOMATION LETTERS 2024年第7期9卷 6720-6727页

作者： Shi, Guowei Yao, Chen Liu, Xin Zhao, Yuntian Zhu, Zheng Jia, Zhenzhong Southern Univ Sci & Technol Shenzhen Key Lab Biomimet Robot & Intelligent Syst Shenzhen 518055 Peoples R China Southern Univ Sci & Technol Guangdong Prov Key Lab Human Augmentationand Rehab Dept Mech & Energy Engn Shenzhen 518055 Peoples R China Georgia Inst Technol Inst Robot & Intelligent Machines Atlanta GA 30332 USA

Quadruped robots equipped with sensorless feet can only provide limited information regarding the foot interaction with the surroundings, limiting their off-road exploration capability in unstructured environments. To tackle this problem, we present Foot Vision, an innovative vision-based sensorized foot for quadruped robots. It consists of a compliant ankle, a transparent foot sole with visual markers, and an internal camera. This foot is designed to be low-cost, lightweight, and adaptable to both deformable and rigid terrains. The camera can efficiently track marker displacements to estimate the foot pose. We extract the foot deformation features from the foot pose and develop a learning-based method to reconstruct 6D contact forces leveraging these features. Representative loading tests validate the foot's ability to accurately (R-2 >0.95) and dynamically predict contact forces and torques in real-time (100 Hz). Installed on the quadruped robot, the sensorized foot demonstrates its capabilities to perceive 6D contact forces on terrains with varying stiffness and estimate the local inclination of the contact surface. Furthermore, thanks to the transparent foot sole, the in-foot camera can directly identify the terrain types and measure the soil flow distribution. Experimental results confirm that the proposed vision-based sensorized foot can enhance the contact perception capability of legged robots in diverse environments.

关键词： Robot sensing systems Foot Robots Cameras Quadrupedal robots Legged locomotion Robot vision systems Legged robots vision-based sensorized foot terrain-adaptive sensing deep learning in robotics

来源：评论

学校读者我要写书评

暂无评论

Interactive Text2Pickup Networks for Natural Language-Based Human-Robot Collaboration

引用

IEEE robotics AND AUTOMATION LETTERS 2018年第4期3卷 3308-3315页

作者： Ahn, Hyemin Choi, Sungjoon Kim, Nuri Cha, Geonho Oh, Songhwai Seoul Natl Univ Dept Elect & Comp Engn Seoul 08826 South Korea Seoul Natl Univ ASRI Seoul 08826 South Korea Kakao Brain Seongnam 13494 South Korea

In this letter, we propose the Interactive Text2Pickup (IT2P) network for human-robot collaboration that enables an effective interaction with a human user despite the ambiguity in user's commands. We focus on the task where a robot is expected to pick up an object instructed by a human, and to interact with the human when the given instruction is vague. The proposed network understands the command from the human user and estimates the position of the desired object first. To handle the inherent ambiguity in human language commands, a suitable question which can resolve the ambiguity is generated. The user's answer to the question is combined with the initial command and given back to the network, resulting in more accurate estimation. The experiment results show that given unambiguous commands, the proposed method can estimate the position of the requested object with an accuracy of 98.49% based on the test dataset. Given ambiguous language commands, we show that the accuracy of the pick up task increases by 1.94 times after incorporating the information obtained from the interaction.

关键词： deep learning in robotics learning and adaptive systems social human-robot interaction

来源：评论

学校读者我要写书评

暂无评论

Neural-Swarm2: Planning and Control of Heterogeneous Multirotor Swarms Using Learned Interactions

引用

IEEE TRANSACTIONS ON robotics 2022年第2期38卷 1063-1079页

作者： Shi, Guanya Honig, Wolfgang Shi, Xichen Yue, Yisong Chung, Soon-Jo CALTECH Pasadena CA 91125 USA CALTECH Comp & Math Sci Pasadena CA 91125 USA

We present Neural-Swarm2, a learning-based method for motion planning and control that allows heterogeneous multirotors in a swarm to safely fly in close proximity. Such operation for drones is challenging due to complex aerodynamic interaction forces, such as downwash generated by nearby drones and ground effect. Conventional planning and control methods neglect capturing these interaction forces, resulting in sparse swarm configuration during flight. Our approach combines a physics-based nominal dynamics model with learned deep neural networks with strong Lipschitz properties. We make use of two techniques to accurately predict the aerodynamic interactions between heterogeneous multirotors: 1) Spectral normalization for stability and generalization guarantees of unseen data and 2) heterogeneous deep sets for supporting any number of heterogeneous neighbors in a permutation-invariant manner without reducing expressiveness. The learned residual dynamics benefit both the proposed interaction-aware multirobot motion planning and the nonlinear tracking control design because the learned interaction forces reduce the modelling errors. Experimental results demonstrate that Neural-Swarm2 is able to generalize to larger swarms beyond training cases and significantly outperforms a baseline nonlinear tracking controller with up to three times reduction in worst-case tracking errors.

关键词： Robots Planning Collision avoidance Aerodynamics Trajectory Tracking Vehicle dynamics Aerial systems deep learning in robotics multirobot motion planning and control multirobot systems

来源：评论

学校读者我要写书评

暂无评论

deep belief network-based probabilistic generative model for detection of robotic manipulator failure execution

引用

SOFT COMPUTING 2023年第1期27卷 363-375页

作者： Dash, Pandit Byomakesha Naik, Bighnaraj Nayak, Janmenjoy Vimal, S. Veer Surendra Sai Univ Technol Sambalpur 768018 Odisha India Aditya Inst Technol & Management AITAM Dept Comp Sci & Engn Tekkali 532201 India Natl Engn Coll Dept Informat Technol Thoothukudi 628503 Tamil Nadu India

This paper addresses an effective deep learning-based technique for detection of robotic manipulator's failure execution. The problem is based on the control strategy of robotic manipulators subjected to uncertain dynamics. The main contribution is to detect the failures at each different position and instance of robotic manipulators with a certain control strategy. An efficient deep belief neural network-based model is developed with an effective distribution of features at each layer of the network to demonstrate the accurate detection of failures at each instance. With the help of various suitable learning parameters at different stages of network and contrastive divergence operation, the proposed method is able to be an emergent solution for the failure detection. The performance of the proposed DBN is compared with other seven standard machine learning-based classifiers and the results are evident toward the significant impact on the high detection rate as well as the robustness of the proposed method.

关键词： deep belief network Robotic manipulator deep learning in robotics Uncertain dynamics

来源：评论

学校读者我要写书评

暂无评论

Partial caging: a clearance-based definition, datasets, and deep learning

引用

AUTONOMOUS ROBOTS 2021年第5期45卷 647-664页

作者： Welle, Michael C. Varava, Anastasiia Mahler, Jeffrey Goldberg, Ken Kragic, Danica Pokorny, Florian T. KTH Royal Inst Technol Stockholm Sweden Univ Calif Berkeley Berkeley CA 94720 USA

Caging grasps limit the mobility of an object to a bounded component of configuration space. We introduce a notion of partial cage quality based on maximal clearance of an escaping path. As computing this is a computationally demanding task even in a two-dimensional scenario, we propose a deep learning approach. We design two convolutional neural networks and construct a pipeline for real-time planar partial cage quality estimation directly from 2D images of object models and planar caging tools. One neural network, CageMaskNN, is used to identify caging tool locations that can support partial cages, while a second network that we call CageClearanceNN is trained to predict the quality of those configurations. A partial caging dataset of 3811 images of objects and more than 19 million caging tool configurations is used to train and evaluate these networks on previously unseen objects and caging tool configurations. Experiments show that evaluation of a given configuration on a GeForce GTX 1080 GPU takes less than 6 ms. Furthermore, an additional dataset focused on grasp-relevant configurations is curated and consists of 772 objects with 3.7 million configurations. We also use this dataset for 2D Cage acquisition on novel objects. We study how network performance depends on the datasets, as well as how to efficiently deal with unevenly distributed training data. In further analysis, we show that the evaluation pipeline can approximately identify connected regions of successful caging tool placements and we evaluate the continuity of the cage quality score evaluation along caging tool trajectories. Influence of disturbances is investigated and quantitative results are provided.

关键词： deep learning in robotics Grasping Computational geometry Topological representation and abstraction of configuration spaces

来源：评论

学校读者我要写书评

暂无评论

Joint Iterative Color Correction and Dehazing for Underwater Image Enhancement

引用

IEEE robotics AND AUTOMATION LETTERS 2021年第3期6卷 5121-5128页

作者： Wang, Kun Shen, Liquan Lin, Yufei Li, Mengyao Zhao, Qijie Shanghai Univ Shanghai Inst Adv Commun & Data Sci Shanghai 200444 Peoples R China Shanghai Univ Joint Int Res Lab Specialty Fiber Opt & Adv Commu Key Lab Specialty Fiber Opt & Opt Access Networks Shanghai 200444 Peoples R China Shanghai Univ Sch Mechatron Engn & Automat Shanghai 200444 Peoples R China

The captured underwater images suffer from color cast and haze effect caused by absorption and scattering. These interdependent phenomena jointly degrade images, resulting in failure of autonomous machines to recognize image contents. Most existing learning-based methods for underwater image enhancement (UIE) treat the degraded process as a whole and ignore the interaction between color correction and dehazing. Thus, they often obtain unnatural results. To this end, we propose a novel joint network to optimize the results of color correction and dehazing in multiple iterations. Firstly, a novel triplet-based color correction module is proposed to obtain color-balanced images with identical distribution of color channels. By means of inherent constraints of the triplet structure, the information of channel with less distortion is utilized to recover the information of other channels. Secondly, a recurrent dehazing module is designed to alleviate haze effect in images, where the Gated Recurrent Unit (GRU) as the memory module optimizes the results in multiple cycles to deal with severe underwater distortions. Finally, an iterative mechanism is proposed to jointly optimize the color correction and dehazing. By learning transform coefficients from dehazing features, color features and basic features of raw images are progressively refined, which maintains color balanced during the dehazing process and further improves clarity of images. Experimental results show that our network is superior to the existing state-of-the-art approaches for UIE and provides improved performance for underwater object detection.

关键词： Image color analysis Feature extraction Absorption Attenuation Scattering Iterative methods Image enhancement Marine robotics underwater image enhancement deep learning in robotics recurrent network computer vision for automation

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：