4.6 Article

Exploring Tactile Temporal Features for Object Pose Estimation during Robotic Manipulation

Related references

Note: Only part of the references are listed.
Article Computer Science, Cybernetics

Learning Haptic-Based Object Pose Estimation for In-Hand Manipulation Control With Underactuated Robotic Hands

Osher Azulay et al.

Summary: Unlike traditional robotic hands, modeling underactuated compliant hands is challenging due to uncertainties. As a result, pose estimation of a grasped object is typically based on visual perception, which is limited in occluded environments. This paper explores the use of haptics for pose estimation and in-hand manipulation with underactuated hands. The authors emphasize the feature state representation of the system that does not rely on vision, proposing a low-cost and flexible sensor for tactile sensing. The experiments validate the accuracy of pose estimation and manipulation with various objects using haptics.

IEEE TRANSACTIONS ON HAPTICS (2023)

Article Robotics

Interaction Control for Tool Manipulation on Deformable Objects Using Tactile Feedback

Hanwen Zhang et al.

Summary: A tactile-guided planning and control framework using GTac, a heterogeneous tactile sensor, is proposed for robots to perform delicate tasks on deformable objects. The framework accurately estimates the contact angle, achieves excellent tracking performance, and robust force control.

IEEE ROBOTICS AND AUTOMATION LETTERS (2023)

Article Robotics

Elongatable Gripper Fingers With Integrated Stretchable Tactile Sensors for Underactuated Grasping and Dexterous Manipulation

Sohee John Yoon et al.

Summary: The performance of robotic grippers is directly related to their ability to grasp objects of different sizes and shapes. This article proposes a length-adjustable linkage mechanism for underactuated fingers to adapt to complex object geometries. Tactile sensing is achieved using hyperelastic soft sensors.

IEEE TRANSACTIONS ON ROBOTICS (2022)

Article Robotics

Goal-Driven Robotic Pushing Using Tactile and Proprioceptive Feedback

John Lloyd et al.

Summary: This study introduces a reactive and adaptive method for robotic pushing, utilizing rich feedback from a high-resolution optical tactile sensor for control. The method is evaluated on planar and curved surfaces, showing accuracy and robustness on planar surfaces but slightly degraded performance on curved surfaces. The study highlights the importance of testing on nonplanar surfaces and complex environments to develop new methods for robotic pushing.

IEEE TRANSACTIONS ON ROBOTICS (2022)

Article Robotics

VisuoTactile 6D Pose Estimation of an In-Hand Object Using Vision and Tactile Sensor Data

Snehal Dikhale et al.

Summary: This letter presents a method that combines tactile and vision data to estimate the pose of an object in a robot's hand. The main challenges lie in the lack of standardized representation for tactile sensor data, fusion of data from different sources, and the need for large training datasets. The proposed method overcomes these challenges by using point clouds, a network architecture for fusion, and synthetic data for training. Results from simulated and real experiments demonstrate the effectiveness of the method.

IEEE ROBOTICS AND AUTOMATION LETTERS (2022)

Article Robotics

Multi-Fingered In-Hand Manipulation With Various Object Properties Using Graph Convolutional Networks and Distributed Tactile Sensors

Satoshi Funabashi et al.

Summary: Researchers have developed a control method based on graph convolutional network to process tactile information from multi-fingered hands with complex shapes, achieving stable manipulation. They collected data using distributed tri-axial tactile sensors and trained the robot hand by transferring human dexterous manipulation skills. The effectiveness of the method was confirmed through experiments.

IEEE ROBOTICS AND AUTOMATION LETTERS (2022)

Article Robotics

Tactile object recognition in early phases of grasping using underactuated robotic hands

Vinicius Prado da Fonseca et al.

Summary: Identifying objects is a crucial step in robotic manipulation, and combining tactile sensors and machine learning models can help overcome the challenges posed by flexible robotic hands and unexpected object movements. This study explores tactile object identification through single grasping and brief exploratory procedures, demonstrating that single grasping can improve object recognition.

INTELLIGENT SERVICE ROBOTICS (2022)

Article Chemistry, Analytical

Model-Based 3D Contact Geometry Perception for Visual Tactile Sensor

Jingjing Ji et al.

Summary: This research presents a new visual-tactile sensor that can perceive the shape and texture of a contacting surface by capturing the deformation image. With model-based depth perceptual scheme and tailored fast solver, it achieves high-quality geometry reconstruction and pose estimation. The experimental results validate the effectiveness and robustness of this method.

SENSORS (2022)

Proceedings Paper Automation & Control Systems

Simultaneous Contact Location and Object Pose Estimation Using Proprioception and Tactile Feedback

Andrea Sipos et al.

Summary: This paper proposes a novel algorithm for joint estimation of object pose and extrinsic contacts using proprioception and tactile feedback. The approach utilizes two complementary particle filters to estimate contact location and object poses simultaneously. Experimental results demonstrate that the robots can infer contact location and object poses by bringing two objects into contact. The proposed method has potential applications in tasks that require accurate pose estimates.

2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (2022)

Article Engineering, Mechanical

Analysis of parasitic motion with the constraint emb e dde d Jacobian for a 3-PRS parallel manipulator

Hassen Nigatu et al.

Summary: This study derived the equation of parasitic motion of a 3-DoFs parallel manipulator from the velocity-level analytic-constraint equation and compared it with a well-known position level geometric method. The research also introduced the process of detecting and identifying parasitic terms from independent terms, as well as the constraint-compatible task motion equation and the coupling relation between parasitic and independent motions.

MECHANISM AND MACHINE THEORY (2021)

Article Robotics

Cable manipulation with a tactile-reactive gripper

Yu She et al.

Summary: This paper presents a novel perception and control framework for real-time cable following using robotic grippers equipped with vision-based tactile sensors. By combining two tactile-based controllers, the system successfully achieves cable gripping and alignment, preventing the cable from slipping out of the gripper.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2021)

Article Computer Science, Artificial Intelligence

On the Design and Development of Vision-based Tactile Sensors

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

Tactile SLAM: Real-time inference of shape and pose from planar pushing

Sudharshan Suresh et al.

Summary: The research presents a method to estimate object shape and pose in real-time from tactile measurements, applied to tactile exploration of unknown objects through planar pushing. The method combines Gaussian process implicit surface regression and pose estimation on a factor graph to infer object shape and pose in real-time. The system is evaluated across different objects in simulated and real-world planar pushing tasks.

2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) (2021)

Article Robotics

Zero-Shot Sim-to-Real Transfer of Tactile Control Policies for Aggressive Swing-Up Manipulation

Thomas Bi et al.

Summary: This research demonstrates that robots equipped with a vision-based tactile sensor can perform dynamic manipulation tasks without prior knowledge of the physical attributes of the objects being manipulated. By developing a novel simulator and learning a feedback policy conditioned on sensory observations, the robotic system successfully manipulates poles of different physical attributes in a closed-loop control system.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

Review Computer Science, Artificial Intelligence

A review on object pose recovery: From 3D bounding box detectors to full 6D pose estimators

Caner Sahin et al.

IMAGE AND VISION COMPUTING (2020)

Review Robotics

A Review of Tactile Information: Perception and Action Through Touch

Qiang Li et al.

IEEE TRANSACTIONS ON ROBOTICS (2020)

Proceedings Paper Automation & Control Systems

GelTip: A Finger-shaped Optical Tactile Sensor for Robotic Manipulation

Daniel Fernandes Gomes et al.

2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (2020)

Proceedings Paper Engineering, Electrical & Electronic

Towards vision-based robotic skins: a data-driven, multi-camera tactile sensor

Camill Trueeb et al.

2020 3RD IEEE INTERNATIONAL CONFERENCE ON SOFT ROBOTICS (ROBOSOFT) (2020)

Review Computer Science, Information Systems

Tactile Sensors for Minimally Invasive Surgery: A Review of the State-of-the-Art, Applications, and Perspectives

Naghmeh Bandari et al.

IEEE ACCESS (2020)

Review Multidisciplinary Sciences

Trends and challenges in robot manipulation

Aude Billard et al.

SCIENCE (2019)

Proceedings Paper Engineering, Electrical & Electronic

Soft-bubble: A highly compliant dense geometry tactile sensor for robot manipulation

Alex Alspach et al.

2019 2ND IEEE INTERNATIONAL CONFERENCE ON SOFT ROBOTICS (ROBOSOFT 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Predicting Grasp Success with a Soft Sensing Skin and Shape-Memory Actuated Gripper

Julian Zimmer et al.

2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (2019)

Article Engineering, Electrical & Electronic

Multimodal Bio-Inspired Tactile Sensing Module

Thiago Eustaquio Alves de Oliveira et al.

IEEE SENSORS JOURNAL (2017)

Article Robotics

Biomimetic tactile sensor array

Nicholas Wettels et al.

ADVANCED ROBOTICS (2008)