A model-based manipulation system with skill-based execution

Hasegawa, Tsutomu; Suehiro, Takashi; Takase, Kunikatsu

doi:10.1109/70.163779

Cited by 125 publications

(77 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…If we ignore the servo layer, the skill layer, which consists of elements such as the move-to-touch and rotate-to-level skills, is located in the lowest layer called the task (0) layer. One tier above the task (0) layer is the task (1) The project layer might also be hierarchized, but we will not discuss this here.…”

Section: Concept Of Skillsmentioning

confidence: 99%

“…6. (i0) , the result is judged to be correct or a failure by an automatic Skillprimitive task (2) task (1) task (0) project (1) task (max) … … project (MAX) project (2) Fig . task (1) …”

Section: Error Recovery Based On Classificationmentioning

confidence: 99%

“…Changing the sensing parameters Changing the modeling parameters Changing the planning parameters Executing the necessary changes Sensing(task (1) )…”

Section: Class 2 Class 3 Classmentioning

confidence: 99%

“…We call each motion primitive a "skill" and have shown that most maintenance and production tasks can be composed of a number of skills. [1][2][3] Ideally, a robotic task has to be successfully completed as planned. However, in the actual tasks of complicated plant maintenance and industrial production, it is not rare for the execution of a task to terminate before completion.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Error Recovery of Pick-and-Place Tasks in Consideration of Reusability of Planning

Nakamura

Nagata

Harada

et al. 2015

JRNAL

View full text Add to dashboard Cite

show abstract

Section: Concept Of Skillsmentioning

confidence: 99%

“…6. (i0) , the result is judged to be correct or a failure by an automatic Skillprimitive task (2) task (1) task (0) project (1) task (max) … … project (MAX) project (2) Fig . task (1) …”

Section: Error Recovery Based On Classificationmentioning

confidence: 99%

“…Changing the sensing parameters Changing the modeling parameters Changing the planning parameters Executing the necessary changes Sensing(task (1) )…”

Section: Class 2 Class 3 Classmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Error Recovery of Pick-and-Place Tasks in Consideration of Reusability of Planning

Nakamura

Nagata

Harada

et al. 2015

JRNAL

View full text Add to dashboard Cite

show abstract

“…An adequately defined skill can have generality to be applied to various similar tasks. Until now, most of the research work on skill-based manipulation deals with rigid objects [14,15] . (2) To be appeared in J. of Robotic Systems S.G. YUE & D. HENRICH, Manipulating DLOs: Adjustment-motions (10/10/00) Skill-based manipulation for handling deformable linear materials has been touched upon recently.…”

Section: Introductionmentioning

confidence: 99%

Manipulating deformable linear objects: Attachable adjustment‐motions for vibration reduction

Yue

Henrich

2001

J. Robotic Syst.

View full text Add to dashboard Cite

This paper addresses the problem of handling deformable linear objects (DLOs) in a suitable way to avoid acute vibration. Different types of adjustment-motions that eliminate vibration of deformable objects and can be attached to the end of an arbitrary end-effector's trajectory are presented. For describing the dynamics of deformable linear objects, the finite element method is used to derive the dynamic differential equations. Genetic algorithm is used to find the optimal adjustment motion for each simulation example. Experiments are conducted to verify the presented manipulating method.

show abstract

Manipulating deformable linear objects: Sensor-based skills of adjustment motions for vibration reduction

Yue

Henrich

2005

J. Robotic Syst.

View full text Add to dashboard Cite

The vibration of a deformable object is often problematic during automatic handling by robot manipulators. However, humans can often handle and damp the vibration of deformable objects with ease. This paper presents force/torque sensor-based skills for handling deformable linear objects in a manner suitable to reduce acute vibration with simple human skill inspired strategies that consist of one or two adjustment motions. The adjustment motion is a simple open-loop motion that can be attached to the end of any arbitrary end-effector's trajectory. As an ordinary industrial robot's simple action, it has three periods, i.e., acceleration, constant speed, and deceleration period; it starts from a predicted time tightly close to a force/moment maximum. The predicted time for the adjustment action is generated automatically on-line based on the vibration rhythm and the data sensed by a force/torque sensor mounted on the robot's wrist. To find the matching point between the vibrational signal of the deformable object and a template, template matching techniques including cross-correlation and minimum squared error methods are used and compared. Experiments are conducted with an industrial robot to test the new skills under various conditions. The results demonstrate that an industrial robot could perform effective vibration reduction skills with simple strategies

show abstract

A model-based manipulation system with skill-based execution

Cited by 125 publications

References 11 publications

Error Recovery of Pick-and-Place Tasks in Consideration of Reusability of Planning

Error Recovery of Pick-and-Place Tasks in Consideration of Reusability of Planning

Manipulating deformable linear objects: Attachable adjustment‐motions for vibration reduction

Manipulating deformable linear objects: Sensor-based skills of adjustment motions for vibration reduction

Contact Info

Product

Resources

About