Assessing Grasp Stability Based on Learning and Haptic Data

Bekiroglu, Yasemin; Laaksonen, Janne; Jørgensen, Jimmy Alison; Kyrki, Ville; Kragić, Danica

doi:10.1109/tro.2011.2132870

Cited by 177 publications

(119 citation statements)

References 23 publications

Supporting

Mentioning

116

Contrasting

Unclassified

Order By: Relevance

“…Grasp stability was studied in terms of physical interaction with objects allowing corrective action to be taken in the case of an unsuccessful grasp [11], see Fig. 3.…”

Section: Main Findings and Resultsmentioning

confidence: 99%

Grasping Grasping in GRASP

Kragić

2013

JRSJ

Self Cite

View full text Add to dashboard Cite

Grasping and manipulation of objects is an important research problem in the area of robotics and has been addressed both from an analytical and an empirical perspective. In Europe, there have been several large-scale projects that studied different aspects of this problem: HANDLE, GRASP, DEXMART, PACO-PLUS, TOMSY, THE, to name a few. We summarize some of the main ideas and results from the GRASP project (www.grasp-project.eu).

show abstract

“…Grasp stability was studied in terms of physical interaction with objects allowing corrective action to be taken in the case of an unsuccessful grasp [11], see Fig. 3.…”

Section: Main Findings and Resultsmentioning

confidence: 99%

Grasping Grasping in GRASP

Kragić

2013

JRSJ

Self Cite

View full text Add to dashboard Cite

show abstract

“…In contrast to the works that use tactile data for controlling a robot, Bekiroglu et al [14] use it for assessing the stability of a grasp. The authors take into account uncertainty and study learning from single measurements and time series of measurements.…”

Section: A Related Workmentioning

confidence: 99%

Learning robot tactile sensing for object manipulation

Chebotar

Kroemer

Peters

2014

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-Tactile sensing is a fundamental component of object manipulation and tool handling skills. With robots entering unstructured environments, tactile feedback also becomes an important ability for robot manipulation.In this work, we explore how a robot can learn to use tactile sensing in object manipulation tasks. We first address the problem of in-hand object localization and adapt three pose estimation algorithms from computer vision. Second, we employ dynamic motor primitives to learn robot movements from human demonstrations and record desired tactile signal trajectories. Then, we add tactile feedback to the control loop and apply relative entropy policy search to learn the parameters of the tactile coupling. Additionally, we show how the learning of tactile feedback can be performed more efficiently by reducing the dimensionality of the tactile information through spectral clustering and principal component analysis. Our approach is implemented on a real robot, which learns to perform a scraping task with a spatula in an altered environment.

show abstract

“…Example works of [7], [8], [14] consider learning of grasp stability and grasp affordances. Our previous work on grasp stability assessment performs learning mainly through tactile (cutaneous), proprioceptive and visual feedback in order to predict the stability of the grasp prior to lifting and manipulating the object [8], [14]. In [7] the proposed system learns grasp affordances which are defined as hand-object relative poses that lead to successful grasps on a particular object.…”

Section: Related Workmentioning

confidence: 99%

“…In this sense, our work follows more closely approaches in which the robot first interacts with objects and assesses their contact and friction properties prior to executing tasks [13]. Our method also follows the motivation behind learning based approaches in order to deal with the issue of modeling errors and uncertainties in grasping [7], [8], [14].…”

Section: Figmentioning

confidence: 99%

See 1 more Smart Citation

Predicting slippage and learning manipulation affordances through Gaussian Process regression

Viña

Bekiroglu

Smith

et al. 2013

2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids)

Self Cite

View full text Add to dashboard Cite

Abstract-Object grasping is commonly followed by some form of object manipulation -either when using the grasped object as a tool or actively changing its position in the hand through in-hand manipulation to afford further interaction. In this process, slippage may occur due to inappropriate contact forces, various types of noise and/or due to the unexpected interaction or collision with the environment.In this paper, we study the problem of identifying continuous bounds on the forces and torques that can be applied on a grasped object before slippage occurs. We model the problem as kinesthetic rather than cutaneous learning given that the measurements originate from a wrist mounted force-torque sensor. Given the continuous output, this regression problem is solved using a Gaussian Process approach.We demonstrate a dual armed humanoid robot that can autonomously learn force and torque bounds and use these to execute actions on objects such as sliding and pushing. We show that the model can be used not only for the detection of maximum allowable forces and torques but also for potentially identifying what types of tasks, denoted as manipulation affordances, a specific grasp configuration allows. The latter can then be used to either avoid specific motions or as a simple step of achieving in-hand manipulation of objects through interaction with the environment.

show abstract

Assessing Grasp Stability Based on Learning and Haptic Data

Cited by 177 publications

References 23 publications

Grasping Grasping in GRASP

Grasping Grasping in GRASP

Learning robot tactile sensing for object manipulation

Predicting slippage and learning manipulation affordances through Gaussian Process regression

Contact Info

Product

Resources

About