Abstract
A novel approach for the realization of the humanoid robot’s reaching task using Support Vector Machine (SVM) is proposed. The main difficulty is how to ensure an appropriate SVM training data set. Control law is firstly devised, and SVM is trained to calculate driving torques according to control law. For purpose of training SVM, sufficiently dense training data set was generated using designed controller. However, dynamic parameters of the system change when grasping is performed, so SVM coefficients were altered in order to adapt to changes that have occurred. In the stage of verification, the target point to be reached by the robot’s hand is assigned. The trained SVM determines the necessary torques in a very efficient way, which has been demonstrated by several simulation examples.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Konczak, J., Dichgans, J.: The development toward stereotypic arm kinematics during reaching in the first 3 years of life. Exp. Brain. Res. 117, 346–354 (1997)
Konczak, J., Borutta, M., Dichgans, J.: The development of goal-directed reaching in infants, II. Learning to produce task-adequate patterns of joint torque. Exp. Brain. Res. 113, 465–474 (1997)
Grosso, E., Metta, G., Oddera, A., Sandini, G.: Robust Visual Servoing in 3-D Reaching Tasks. IEEE Tran. on Robotics and Automation 12(5), 732–742 (1996)
Coelho, J., Pater, J., Grupen, R.: Developing haptic and visual perceptual categories for reaching and grasping with a humanoid robot. Robotics and Autonomous Systems 37, 195–218 (2006)
Gaskett, C., Cheng, G.: Online Learning of a Motor Map for Humanoid Robot Reaching. In: Proc.of 2nd Int. Conf. Computational Intelligence, Robotics and Autonomous Systems, Singapore (2003)
Blackburn, M., Nygen, H.: Learning in robot vision directed reaching: A comparison of methods. In: Proc. of the ARPA Image Understanding Workshop, Moterey, CA (1994)
Vapnik, V.: The nature of statistical learning theory. Springer, Heidelberg (2000)
Kecman, V.: Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models. The MIT Press, Cambridge (2001)
Potkonjak, V., Vukobratović, M., Babković, K., Borovac, B.: General Model of Dynamics of Human and Humanoid Motion: Feasibility, Potentials and Verification. Int. Jour. of Humanoid Robotics 3(2), 21–48 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Raković, M., Nikolić, M., Borovac, B. (2011). Humanoid Robot Reaching Task Using Support Vector Machine. In: Obdržálek, D., Gottscheber, A. (eds) Research and Education in Robotics - EUROBOT 2011. EUROBOT 2011. Communications in Computer and Information Science, vol 161. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21975-7_23
Download citation
DOI: https://doi.org/10.1007/978-3-642-21975-7_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21974-0
Online ISBN: 978-3-642-21975-7
eBook Packages: Computer ScienceComputer Science (R0)