Abstract
We discuss about the modeling technology in the object manipulation of the robot arm that is equipped with flexible finger joints. In recent years, flexible robot fingers are getting attention because of their handling capability and safety. However, the position and contact force of manipulated object take much non-linear uncertainty from the flexibility. In this paper, we propose the modeling framework of the position and contact force of the manipulated object. The proposed framework is an online learning method that is composed of motor babbling, dynamics learning tree (DLT), and \(\epsilon \)-greedy method. In the experiments, the effectiveness of DLT was compared with neural network (NN), the effectiveness of the proposed framework was validated using a drawing task of a humanoid robot that equipped with flexible finger joints. The proposed framework was able to realize a fully automated incremental-manipulation-learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The same algorithm is used in another proposition [17] that is presented in this conference.
- 2.
The humanoid robot NAO was placed on the top of the figures. It moved a pen using its right hand. The result of Exploitation mode has a bias compared with the others. This might be because Exploitation mode searches pen tip positions conservatively by exploiting the knowledge of DLT.
References
Sugano, S., Kato, I.: WABOT-2: autonomous robot with dexterous finger-arm - finger-arm coordination control in keyboard performance. In: IEEE International Conference on Robotics and Automation (1987)
Kajikawa, S., Kon, H., Kikuchi, K., Satoh, S.: Development of a soft finger-joint for human-care robot. In: IEEE International Conference on Mechatronics and Automation (2005)
Yoshimi, T., Iwata, N., Mizukawa, M., Ando, Y.: Picking up operation of thin objects by robot arm with two-fingered parallel soft gripper. In: IEEE International Workshop on Advanced Robotics and its Social Impacts (2012)
Sugaiwa, T., Fujii, G., Iwata, H., Sugano, S.: A methodology for setting grasping force for picking up an object with unknown weight, friction, and stiffness. In: IEEE/RAS International Conference on Humanoid Robots (2010)
Doulgeri, Z., Simeonidis, A., Arimoto, S.: A position/force control for a soft tip robot finger under kinematic uncertainties. In: IEEE International Conference on Robotics and Automation (2000)
Kim, B.H., Hirai, S.: Characterizing the dynamics deformation of soft fingertips and analyzing its significance for multi-fingered operations. In: IEEE International Conference on Robotics and Automation (2004)
Yoshida, M., Arimoto, S., Bae, J.H.: Blind grasp and manipulation of a rigid object by a pair of robot fingers with soft tips. In: IEEE International Conference on Robotics and Automation (2007)
Funabashi, S., Schmitz, A., Sato, T., Somlor, S., Sugano, S.: Robust in-hand manipulation of variously sized and shaped objects. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (2015)
Asada, M., Dorman, K.M., Ishiguro, H., Kuniyoshi, Y.: Cognitive developmental robotics as a new paradigm for the design of humanoid robots. Robot. Auton. Syst. 33, 185–193 (2001)
Schillaci, G., Hafner, V.V.: Random movement strategies in self-exploration for a humanoid robot. In: IEEE/ACM International Conference on Human Robot Interaction, pp. 245–246 (2011)
Saegusa, R., Metta, G., Sandini, G.: Active learning for multiple sensorimotor coordination based on state confidenc. In: IEEE/RSJ International Conference on Robotics and Systems, pp. 2598–2603 (2009)
Dawood, F., Loo, C.K.: Humanoid behavior learning through visuomotor association by self-imitation. In: SCIS and ISIS, pp. 922–929 (2014)
Grimes, D.B., Rao, R.P.N.: Learning actions through imitation and exploration: towards humanoid robots that learn from humans. In: Sendhoff, B., Körner, E., Sporns, O., Ritter, H., Doya, K. (eds.) Creating Brain-Like Intelligence. LNCS, vol. 5436, pp. 103–138. Springer, Heidelberg (2009)
Mochizuki, K., Nishide, S., Okuno, H., Ogata, T.: Developmental imitation learning of robot on drawing with neuro dynamical mode. In: Annual Conference of IPSJ (2013). (In Japanese)
Yamashita, Y., Tani, J.: Emergence of functional hierarchy in a multiple timescale neural network model: a humanoid robot experiment. PLoS Comput. Biol. 4(11), e1000220 (2008)
Nishide, S., Mochizuki, K., Okuno, H.G., Ogata, T.: Insertion of pause in drawing from babbling for robot’s developmental imitation learning. In: IEEE International Conference on Robotics and Automation, pp. 4785–4791 (2014)
Eto, K., Kobayashi, Y., Kim, C.H.: Vehicle dynamics modeling using FDA learning. In: International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (2016, in press)
French, R.M.: Catastrophic forgetting in connectionist networks. Trends Cogn. Sci. 3(4), 128–135 (1999)
Nagai, Y., Asada, M., Hosoda, K.: Learning for joint attention helped by functional development. Adv. Robot. 20(10), 1165–1181 (2006)
Nakaoka, S., Nakazawa, A. Yokoi, K., Hirukawa, H., Ikeuchi, K.: Generating whole body motions for a biped humanoid robot from captured human dances. In: IEEE International Conference on Robotics and Automation, pp. 905–3910 (2003)
Takahashi, K., Ogata, T., Yamada, H., Tjandra, H., Sugano, S.: Effective motion learning for a flexible-joint robot using motor babbling. In: IEEE International Conference on Robotics and Systems (2015)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Kim, C.H., Sugano, S.: Tree based trajectory optimization based on local linearity of continuous non-linear dynamics. IEEE Trans. Autom. Control 61(9) (2016, in press)
Kim, C.H., Sugano, S.: Closed loop trajectory optimization based on reverse time tree. Int. J. Control Autom. Syst. (in press)
Kim, C.H., Yamazaki, S., Sugano, S.: Motion optimization using state-dispersion based phase space partitions. Multibody Syst. Dyn. 32(2), 159–173 (2013)
Kim, C.H., Sugano, S.: A GPU parallel computing method for LPUSS. Adv. Robot. 27(15), 1199–1207 (2013)
Acknowledgement
This work was supported by JSPS KAKENHI Grant Numbers, 15K00363, 15K20850, 24119003, 25730159, and SCAT Technology Research Foundation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Watanabe, K., Nishide, S., Gouko, M., Kim, C.H. (2016). Fully Automated Learning for Position and Contact Force of Manipulated Object with Wired Flexible Finger Joints. In: Fujita, H., Ali, M., Selamat, A., Sasaki, J., Kurematsu, M. (eds) Trends in Applied Knowledge-Based Systems and Data Science. IEA/AIE 2016. Lecture Notes in Computer Science(), vol 9799. Springer, Cham. https://doi.org/10.1007/978-3-319-42007-3_64
Download citation
DOI: https://doi.org/10.1007/978-3-319-42007-3_64
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-42006-6
Online ISBN: 978-3-319-42007-3
eBook Packages: Computer ScienceComputer Science (R0)