相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Engineering, Electrical & Electronic
Hao Fan et al.
Summary: This paper presents a new post-processing method using a ring-light imaging device to correct bias in photometric stereo reconstruction. By incorporating a set of known 3D points, the proposed method successfully reduces systematic errors and improves the accuracy of 3D height estimation.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2022)
Article
Robotics
Shaoxiong Wang et al.
Summary: TACTO is a fast, flexible, and open-source simulator for vision-based tactile sensors, capable of simulating different vision-based tactile sensors and generating realistic touch readings at high resolution. It demonstrates learning grasp stability using touch information and showcases its application in marble manipulation control tasks.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Proceedings Paper
Automation & Control Systems
Paloma Sodhi et al.
Summary: This study addresses the problem of tracking 3D object poses from touch during in-hand manipulations. They propose a novel two-stage approach using vision-based tactile sensors, and demonstrate reliable object tracking in both simulated and real-world environments.
2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2022)
(2022)
Article
Engineering, Electrical & Electronic
Bin Fang et al.
Summary: This article proposes a fabric structure defect detection method based on a vision-based tactile sensor. The method is more robust and universal compared to conventional visual methods. It uses a robotic arm equipped with tactile sensors to automate the data collection process and a convolutional neural network with attention mechanism for fabric type detection. The proposed method can effectively reduce the influence of ambient light and improve defect detection efficiency and accuracy.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Robotics
Yipai Du et al.
Summary: Recent studies have shown promising results in vision-based tactile sensing for perceiving contact information and improving dexterous manipulations. A denser and more accurate deformation field estimation at a higher resolution is achieved by using a novel random color pattern as the sensor's tracking target and dense optical flow algorithm. This allows for better depth estimation and more complete deformation tracking of contact interfaces for vision-based tactile sensors.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Engineering, Electrical & Electronic
Yicheng Yang et al.
Summary: In this study, a vision-based tactile sensor was customized and used to verify a two-step spatial surface sensing method. The results showed that surface reconstruction and recognition were related, and that the reconstruction step helped improve recognition accuracy. Additionally, the custom sensor demonstrated excellent recognition capability, indicating practical value in surface recognition through touch.
IEEE SENSORS JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Umer Hameed Shah et al.
Summary: This paper reviews the existing designs of vision-based tactile sensors (VBTS) reported in the literature and discusses different design modalities and aspects. The paper aims to investigate current manufacturing trends and component selection criteria for developing a complete VBTS system, as well as identify challenges in VBTS development technology and recommend future research directions to overcome them.
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
(2021)
Proceedings Paper
Automation & Control Systems
Shaoxiong Wang et al.
Summary: Vision-based tactile sensors have the potential to provide important contact geometry for localizing objectives with visual occlusion. The GelSight Wedge sensor is optimized for compact robot fingers, achieving high-resolution 3D reconstruction and showing flexibility in design. The effectiveness and potential of the reconstructed 3D geometry for pose tracking in 3D space is demonstrated.
2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021)
(2021)
Proceedings Paper
Robotics
Rares Ambrus et al.
Summary: Fluid-filled soft visuotactile sensors such as Soft-bubbles utilize state-of-the-art monocular depth estimation to predict dense internal depth maps for precise surface deformation measurements, overcoming size constraints of enclosed IR/depth imaging sensors. Through supervised learning on a small set of diverse objects, these sensors demonstrate sample-efficient training, accuracy, and generalizability across unseen objects and configurations. This approach has implications for the design of soft visuotactile sensors and grippers in enabling reliable grasps and high-resolution sensory feedback.
2021 IEEE 4TH INTERNATIONAL CONFERENCE ON SOFT ROBOTICS (ROBOSOFT)
(2021)
Review
Engineering, Electrical & Electronic
Alexander C. Abad et al.
IEEE SENSORS JOURNAL
(2020)
Article
Robotics
Mike Lambeta et al.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2020)
Article
Robotics
Chen Yu et al.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2020)
Review
Chemistry, Analytical
Kazuhiro Shimonomura
Article
Robotics
Xi Lin et al.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2019)
Article
Computer Science, Information Systems
Carmelo Sferrazza et al.
Article
Chemistry, Analytical
Wenzhen Yuan et al.