Automatic robot kinematic modeling with a modular artificial skin

Mittendorfer, Philipp; Dean, Emmanuel; Cheng, Gordon

doi:10.1109/humanoids.2014.7041447

Cited by 9 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method can be considered as local kinematic modeling (nongeometric/analytic form association). The second method is divided into two stages: skin patch localization with respect to the robot body frames and the estimation of the joint offsets using the skin information to obtain D-H-like parameters, describing the robot kinematic configuration [46]. The skin patch localization can be obtained automatically [47] or manually using an interactive graphical user interface (GUI) (see Fig.…”

Section: Self-acquired Kinematic/dynamic Knowledgementioning

confidence: 99%

“…In this step, we subtract the gravity vector from the measurements and compute the tangential acceleration using singular value decomposition. 3) Computing the radial minimum distance, using the magnitude of the tangential component and fitting a least-squares linear model [46]. The obtained parameters can be described in the form of DH-parameters (see Fig.…”

Section: Self-acquired Kinematic/dynamic Knowledgementioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Realization of Robot Skin: Sensors, Sensing, Control, and Applications

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Self-acquired Kinematic/dynamic Knowledgementioning

confidence: 99%

Section: Self-acquired Kinematic/dynamic Knowledgementioning

confidence: 99%

A Comprehensive Realization of Robot Skin: Sensors, Sensing, Control, and Applications

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…c) Computing the Radial Distance. This step is performed using the amplitude of the tangential component and fitting a least-squares linear model Mittendorfer et al (2014b). The obtained parameters can be described in the form of DH-parameters, see Fig.…”

Section: Dh-like Parametrizationmentioning

confidence: 99%

Robot Skin: Fully-Compliant Control Framework Using Multi-modal Tactile Events

Dean

Ramirez-Amaro

Bergner

et al. 2019

ICBI

Self Cite

View full text Add to dashboard Cite

In this paper, we present a multi-modal control framework to provide compliant behaviors on industrial robots, even when the robots are position commanded. This is obtained by fusing multi-modal sensor signals from robot skin with different control approaches. These compliant behaviors allow to teach robots safely. The presented framework is able to bridge kinesthetically demonstrated activities with low-level robot commands using a state-of-the-art teaching by demonstration method based on a semantic engine. We validate our framework in a real wheeled robot for an industrial scenario, where our presented framework enables a stiff robotic system to be compliant, flexible, and adaptable to different working conditions, e.g. different end-effectors with multiple command interfaces (position/velocity and torque interfaces).

show abstract

“…gravity. Performing specific motion patterns of individual joints, they can determine its kinematics parameters [10]; and deriving the local connectivity structure and exploiting the known geometry of the units, their relative position on the robot surface can be estimated too [9].…”

Section: Introductionmentioning

confidence: 99%

Towards body schema learning using training data acquired by continuous self-touch

Haschke

Ritter

2015

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)

View full text Add to dashboard Cite

Abstract-To augment traditionally vision-based body schema learning with a sensory channel that provides more accurate positional information, we propose a tactile-servoing feedback controller that allows a robot to continuously acquire self-touch information while sliding a fingertip across its own body. In this manner one can quickly acquire a large amount of training data representing the body shape.We compare three approaches to track the common contact point observed when one robot arm is touching the other in a bimanual setup: feed-forward control, solely relying on a CAD-based kinematics, performs worst; a controller that is only based on tactile feedback typically lacks behind; only the combination of both approaches yields satisfactory results.As a first, preliminary application, we use the self-touch capability to calibrate the closed kinematic chain formed by both arms touching each other. The obtained homogeneous transform describing the relative mounting pose of both arms, improves end-effector position estimations by a magnitude compared to a traditional, vision-based approach.

show abstract

Automatic robot kinematic modeling with a modular artificial skin

Cited by 9 publications

References 20 publications

A Comprehensive Realization of Robot Skin: Sensors, Sensing, Control, and Applications

A Comprehensive Realization of Robot Skin: Sensors, Sensing, Control, and Applications

Robot Skin: Fully-Compliant Control Framework Using Multi-modal Tactile Events

Towards body schema learning using training data acquired by continuous self-touch

Contact Info

Product

Resources

About