2010 IEEE International Conference on Robotics and Automation 2010
DOI: 10.1109/robot.2010.5509194
|View full text |Cite
|
Sign up to set email alerts
|

A measurement model for tracking hand-object state during dexterous manipulation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
33
0

Year Published

2012
2012
2022
2022

Publication Types

Select...
4
2
2

Relationship

0
8

Authors

Journals

citations
Cited by 38 publications
(33 citation statements)
references
References 4 publications
0
33
0
Order By: Relevance
“…Corcoran and Platt [11] use particle filtering to model objects based on contacts with a robot hand. The object state is estimated during manipulation by integrating the likelihood of contact measurements over possible contact positions.…”
Section: A Related Workmentioning
confidence: 99%
“…Corcoran and Platt [11] use particle filtering to model objects based on contacts with a robot hand. The object state is estimated during manipulation by integrating the likelihood of contact measurements over possible contact positions.…”
Section: A Related Workmentioning
confidence: 99%
“…Others use a particle filter approach to fit a model to the object pose by collecting measurements from touching the object before grasping it [8], [9]. Hebert et al use a fusion approach with vision, force/torque measurements and proprioception to estimate the position of an object with a known model, held in the end-effector [10].…”
Section: Related Workmentioning
confidence: 99%
“…by using vision and mapping a desired trajectory from the image space to robot space. In this case the feedback control is designed using the contact point position which is however based on estimates obtained by (9) i.e. p := p c .…”
Section: Force/motion Controlmentioning
confidence: 99%
“…Different combinations of tactile, force and vision information for locating the handle and opening a door were tested and it was proved that the combination of all three modalities outperformed any other possible arrangement [14]. A particle filter approach was used to estimate a tube's pose using both positive and negative contact information -the knowledge of which fingers are touching the object and which are not [15]. Another approach was to model discrete states that contain the possible combinatorial arrangements between fingers and object surfaces using an hybrid systems estimator, estimating these discrete contact modes as well as continuous state variables -i.e.…”
Section: Introductionmentioning
confidence: 99%