Grasping and tracking using constant curvature dynamic contours

Douglas P. Perrin, Esra Kadioglu, Sascha A. Stoeter, Nikolaos P Papanikolopoulos

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In this paper we present our constant curvature dynamic contours (snakes) and three applications of these: visual servoing and grasping, occluding contour depth extraction, and localization of miniature mobile robots. For the first application, a novel deformable contour model is implemented for the automatic determination of plausible grasp axes of unknown objects using an eye-in-hand robotic system. The system finds potential grasp point pairs, ranks them based upon measurements taken from the contour, and executes a vision-guided grasp using the highest ranked grasp point pair to determine the gripper alignment. Our method is based upon statistical active deformable models. We have developed a new snake model that is applicable to real-time vision problems. The grasping method is experimentally verified using both simple and complex unknown grasping targets. These experiments demonstrate the effectiveness of using the proposed snakes to grasp previously unknown objects in minimally structured environments. We also present a novel method for active monocular depth recovery (second application of our snakes). It combines new, highly stable active deformable models with a structured camera motion along the optical axis to produce depth estimates for all snake control points. The method has a simple formulation and is suitable for real-time, vision-based robotic applications. Experiments with a variety of objects and depths demonstrate the practicality of the method. Finally, we present a novel method for localizing miniature mobile robots (Scouts) using dynamic contours. The miniature robot is tracked as it moves and jumps in the environment. The proposed dynamic contours are very effective in tracking the fast accelerations and decelerations of this small robot. We show initial experimental results emphasizing the task of monitoring a Scout's jumps.

Original languageEnglish (US)
Pages (from-to)855-871
Number of pages17
JournalInternational Journal of Robotics Research
Volume22
Issue number10-11
DOIs
StatePublished - Jan 1 2003

Fingerprint

Grasping
Snakes
Curvature
Mobile robots
Deformable Models
Robots
Visual servoing
Mobile Robot
Unknown
Grippers
Robotics
Deceleration
Jump
End effectors
Robot
Visual Servoing
Real-time
Experiments
Cameras
Control Points

Keywords

  • Active deformable models
  • Real-time computer vision
  • Snakes
  • Visual servoing and grasping

Cite this

Grasping and tracking using constant curvature dynamic contours. / Perrin, Douglas P.; Kadioglu, Esra; Stoeter, Sascha A.; Papanikolopoulos, Nikolaos P.

In: International Journal of Robotics Research, Vol. 22, No. 10-11, 01.01.2003, p. 855-871.

Research output: Contribution to journalArticle

Perrin, Douglas P. ; Kadioglu, Esra ; Stoeter, Sascha A. ; Papanikolopoulos, Nikolaos P. / Grasping and tracking using constant curvature dynamic contours. In: International Journal of Robotics Research. 2003 ; Vol. 22, No. 10-11. pp. 855-871.
@article{a7fc959bce5a4850880131a5e9dd7fcf,
title = "Grasping and tracking using constant curvature dynamic contours",
abstract = "In this paper we present our constant curvature dynamic contours (snakes) and three applications of these: visual servoing and grasping, occluding contour depth extraction, and localization of miniature mobile robots. For the first application, a novel deformable contour model is implemented for the automatic determination of plausible grasp axes of unknown objects using an eye-in-hand robotic system. The system finds potential grasp point pairs, ranks them based upon measurements taken from the contour, and executes a vision-guided grasp using the highest ranked grasp point pair to determine the gripper alignment. Our method is based upon statistical active deformable models. We have developed a new snake model that is applicable to real-time vision problems. The grasping method is experimentally verified using both simple and complex unknown grasping targets. These experiments demonstrate the effectiveness of using the proposed snakes to grasp previously unknown objects in minimally structured environments. We also present a novel method for active monocular depth recovery (second application of our snakes). It combines new, highly stable active deformable models with a structured camera motion along the optical axis to produce depth estimates for all snake control points. The method has a simple formulation and is suitable for real-time, vision-based robotic applications. Experiments with a variety of objects and depths demonstrate the practicality of the method. Finally, we present a novel method for localizing miniature mobile robots (Scouts) using dynamic contours. The miniature robot is tracked as it moves and jumps in the environment. The proposed dynamic contours are very effective in tracking the fast accelerations and decelerations of this small robot. We show initial experimental results emphasizing the task of monitoring a Scout's jumps.",
keywords = "Active deformable models, Real-time computer vision, Snakes, Visual servoing and grasping",
author = "Perrin, {Douglas P.} and Esra Kadioglu and Stoeter, {Sascha A.} and Papanikolopoulos, {Nikolaos P}",
year = "2003",
month = "1",
day = "1",
doi = "10.1177/027836490302210005",
language = "English (US)",
volume = "22",
pages = "855--871",
journal = "International Journal of Robotics Research",
issn = "0278-3649",
publisher = "SAGE Publications Inc.",
number = "10-11",

}

TY - JOUR

T1 - Grasping and tracking using constant curvature dynamic contours

AU - Perrin, Douglas P.

AU - Kadioglu, Esra

AU - Stoeter, Sascha A.

AU - Papanikolopoulos, Nikolaos P

PY - 2003/1/1

Y1 - 2003/1/1

N2 - In this paper we present our constant curvature dynamic contours (snakes) and three applications of these: visual servoing and grasping, occluding contour depth extraction, and localization of miniature mobile robots. For the first application, a novel deformable contour model is implemented for the automatic determination of plausible grasp axes of unknown objects using an eye-in-hand robotic system. The system finds potential grasp point pairs, ranks them based upon measurements taken from the contour, and executes a vision-guided grasp using the highest ranked grasp point pair to determine the gripper alignment. Our method is based upon statistical active deformable models. We have developed a new snake model that is applicable to real-time vision problems. The grasping method is experimentally verified using both simple and complex unknown grasping targets. These experiments demonstrate the effectiveness of using the proposed snakes to grasp previously unknown objects in minimally structured environments. We also present a novel method for active monocular depth recovery (second application of our snakes). It combines new, highly stable active deformable models with a structured camera motion along the optical axis to produce depth estimates for all snake control points. The method has a simple formulation and is suitable for real-time, vision-based robotic applications. Experiments with a variety of objects and depths demonstrate the practicality of the method. Finally, we present a novel method for localizing miniature mobile robots (Scouts) using dynamic contours. The miniature robot is tracked as it moves and jumps in the environment. The proposed dynamic contours are very effective in tracking the fast accelerations and decelerations of this small robot. We show initial experimental results emphasizing the task of monitoring a Scout's jumps.

AB - In this paper we present our constant curvature dynamic contours (snakes) and three applications of these: visual servoing and grasping, occluding contour depth extraction, and localization of miniature mobile robots. For the first application, a novel deformable contour model is implemented for the automatic determination of plausible grasp axes of unknown objects using an eye-in-hand robotic system. The system finds potential grasp point pairs, ranks them based upon measurements taken from the contour, and executes a vision-guided grasp using the highest ranked grasp point pair to determine the gripper alignment. Our method is based upon statistical active deformable models. We have developed a new snake model that is applicable to real-time vision problems. The grasping method is experimentally verified using both simple and complex unknown grasping targets. These experiments demonstrate the effectiveness of using the proposed snakes to grasp previously unknown objects in minimally structured environments. We also present a novel method for active monocular depth recovery (second application of our snakes). It combines new, highly stable active deformable models with a structured camera motion along the optical axis to produce depth estimates for all snake control points. The method has a simple formulation and is suitable for real-time, vision-based robotic applications. Experiments with a variety of objects and depths demonstrate the practicality of the method. Finally, we present a novel method for localizing miniature mobile robots (Scouts) using dynamic contours. The miniature robot is tracked as it moves and jumps in the environment. The proposed dynamic contours are very effective in tracking the fast accelerations and decelerations of this small robot. We show initial experimental results emphasizing the task of monitoring a Scout's jumps.

KW - Active deformable models

KW - Real-time computer vision

KW - Snakes

KW - Visual servoing and grasping

UR - http://www.scopus.com/inward/record.url?scp=0142123162&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0142123162&partnerID=8YFLogxK

U2 - 10.1177/027836490302210005

DO - 10.1177/027836490302210005

M3 - Article

VL - 22

SP - 855

EP - 871

JO - International Journal of Robotics Research

JF - International Journal of Robotics Research

SN - 0278-3649

IS - 10-11

ER -