Abstract
In the human environment service robots have to be able to manipulate autonomously a large variety of objects in a workspace restricted by collisions with obstacles, self-collisions and task constraints. Planning enables the robot system to generalize predefined or learned manipulation knowledge to new environments. For dexterous manipulation tasks the manual definition of planning models is time-consuming and error-prone. In this work, planning models for dexterous tasks are learned based on multiple human demonstrations using a general feature space including automatically generated contact constraints, which are automatically relaxed to consider the correspondence problem. In order to execute the learned planning model with different objects, the contact location is transformed to given object geometry using morphing. The initial, overspecialized planning model is generalized using a previously described, parallelized optimization algorithm with the goal to find a maximal subset of task constraints, which admits a solution to a set of test problems. Experiments on two different, dexterous tasks show the applicability of the learning approach to dexterous manipulation tasks.
Similar content being viewed by others
Notes
By using the quaternion representation, a rotation matrix can be represented as a single rotation around a fixed axis with a fixed angle. The scaled axis representation is the product of this axis and angle.
References
Azad P, Gockel T, Dillmann R (2007) Computer vision—das praxisbuch. Elektor, Aachen
Berenson D, Srinivasa S, Ferguson D, Kuffner J (2009) Manipulation planning on constraint manifolds. In: IEEE int conf on robotics and automation
Breazeal C, Berlin M, Brooks AG, Gray J, Thomaz AL (2006) Using perspective taking to learn from ambiguous demonstrations. Robot Auton Syst 54(5):385–393
Calinon S, Billard A (2006) Teaching a humanoid robot to recognize and reproduce social cues. In: Proceedings of the IEEE international symposium on robot and human interactive communication (RO-MAN), pp 346–351
Calinon S, Guenter F, Billard A (2005) Goal-directed imitation in a humanoid robot. In: Proceedings of the IEEE international conference on robotics and automation
Calinon S, Guenter F, Billard A (2007) On learning, representing, and generalizing a task in a humanoid robot. IEEE Trans Syst Man Cybern, Part B, Cybern 37(2):286–298
Eiben A, Smith J (2003) Introduction to evolutionary computing. Springer, Berlin
Erlhagen W, Mukovskiy A, Bicho E, Panin G, Kiss C, Knoll A, van Schie HT, Bekkering H (2006) Goal-directed imitation for robots: a bio-inspired approach to action understanding and skill learning. Robot Auton Syst 54(5):353–360
Friedrich H, Dillmann R (1995) Robot programming based on a single demonstration and user intentions. In: 3rd European workshop on learning robots at ECML’95
Friedrich H, Dillmann R, Rogalla O (1999) Interactive robot programming based on human demonstration and advice. In: Selected papers from the international workshop on sensor based intelligent robots. Springer, London, pp 96–119
Hu H, Gao X, Li J, Wang J, Liu H (2004) Calibrating human hand for teleoperating the hit/dlr hand. In: IEEE international conference on robotics and automation, pp 4571–4576
Ijspeert AJ, Nakanishi J, Schaal S (2002) Movement imitation with nonlinear dynamical systems in humanoid robots. In: IEEE int conf on robotics and automation. IEEE Press, New York, pp 1398–1403
Jäkel R, Schmidt-Rohr SR, Loesch M, Dillmann R (2010) Representation and constrained planning of manipulation strategies in the context of programming by demonstration. In: IEEE international conference on robotics and automation (ICRA’10)
Jäkel R, Schmidt-Rohr SR, Loesch M, Kasper A, Dillmann R (2010) Learning of generalized manipulation strategies in the context of programming by demonstration. In: 10th IEEE-RAS international conference on humanoid robots (Humanoids)
Jäkel R, Meißner P, Schmidt-Rohr SR, Dillmann R (2011) Distributed generalization of learned planning models in robot programming by demonstration. In: IEEE/RSJ int conf on intelligent robots and systems
Kasper A, Xue Z, Dillmann R (2012) A object model database for object recognition, localisation and manipulation in service robotics. Int J Robot Res. doi:10.1177/0278364912445831
Keijzer M, Merelo JJ, Romero G, Schoenauer M (2002) Evolving objects: a general purpose evolutionary computation library. Artif Evol 2310:829–888
Kim V, Lipman Y, Funkhouser T (2011) Blended intrinsic maps. ACM Trans Graph 30:4. doi:10.1145/2010324.1964974
Kuniyoshi Y, Inaba M, Inoue H (1994) Learning by watching: extracting reusable task knowledge from visual observation of human performance. IEEE Trans Robot Autom 10:799–822
Muhlig M, Gienger M, Steil J, Goerick C (2009) Automatic selection of task spaces for imitation learning. In: IEEE/RSJ international conference on intelligent robots and systems, IROS 2009, pp 4996–5002
Pardowitz M, Glaser B, Dillmann R (2007) Learning repetitive robot programs from demonstrations using version space algebra. In: Proceedings of the 13th IASTED international conference on robotics and applications. ACTA Press, Anaheim, pp 394–399
Pastor P, Hoffmann H, Asfour T, Schaal S (2009) Learning and generalization of motor skills by learning from demonstration. In: IEEE international conference on robotics and automation
Pastor P, Kalakrishnan M, Chitta S, Theodorou E, Schaal S (2011) Skill learning and task outcome prediction for manipulation. In: IEEE international conference on robotics and automation
Rybski P, Yoon K, Stolarz J, Veloso M (2007) Interactive robot task training through dialog and demonstration. In: 2nd ACM/IEEE international conference on human-robot interaction
Siciliano B, Villani L, Oriolo G, Sciavicco L (2008) Robotics. Springer, New York
Steffen J, Elbrechter C, Haschke R, Ritter H (2010) Bio-inspired motion strategies for a bimanual manipulation task. In: 10th IEEE-RAS international conference on humanoid robots (Humanoids), pp 625–630
Tang M, Kim Y, Manocha D (2009) C2a: controlled conservative advancement for continuous collision detection of polygonal models. In: IEEE international conference on robotics and automation (ICRA’09). IEEE Press, New York, pp 849–854
van Lent M, Laird JE (2001) Learning procedural knowledge through observation. In: Proceedings of the 1st international conference on knowledge capture, K-CAP ’01. ACM Press, New York, pp 179–186
Veeraraghavan H (2008) Teaching sequential tasks with repetition through demonstration (short paper). In: Proceedings of the international conference on autonomous agents and multiagent systems, AAMAS’08
Acknowledgements
This work has been partially conducted within the German SFB 588 “Humanoid Robots” granted by DFG and within the ECs Integrated Project DEXMART under grant agreement no. 126239 (FP7/2007-2013).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jäkel, R., Schmidt-Rohr, S.R., Rühl, S.W. et al. Learning of Planning Models for Dexterous Manipulation Based on Human Demonstrations. Int J of Soc Robotics 4, 437–448 (2012). https://doi.org/10.1007/s12369-012-0162-y
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12369-012-0162-y