Show simple item record

dc.contributor.authorElibol, Ercanspa
dc.contributor.authorCalderón, Juanspa
dc.contributor.authorLlofriu, Martinspa
dc.contributor.authorQuintero, Carlosspa
dc.contributor.authorMoreno, Wilfridospa
dc.contributor.authorWeitzenfeld, Alfredospa
dc.date.accessioned2020-01-16T22:10:29Zspa
dc.date.available2020-01-16T22:10:29Zspa
dc.date.issued2016-01-29spa
dc.identifier.urihttp://hdl.handle.net/11634/20597spa
dc.description.abstractAn important area of research in humanoid robots is energy consumption, as it limits autonomy, and can harm task performance. This work focuses on power aware motion planning. Its principal aim is to find joint trajectories to allow for a humanoid robot to go from crouch to stand position while minimizing power consumption. Q-Learning (QL) is used to search for optimal joint paths subject to angular position and torque restrictions. A planar model of the humanoid is used, which interacts with QL during a simulated offline learning phase. The best joint trajectories found during learning are then executed by a physical humanoid robot, the Aldebaran NAO. Position, velocity, acceleration, and current of the humanoid system are measured to evaluate energy, mechanical power, and Center of Mass (CoM) in order to estimate the performance of the new trajectory which yield a considerable reduction in power consumption.spa
dc.format.mimetypeapplication/pdfspa
dc.rightsAtribución-NoComercial-CompartirIgual 2.5 Colombia*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/2.5/co/*
dc.titlePower usage reduction of humanoid standing process using Q-Learningspa
dc.typeGeneración de Nuevo Conocimiento: Artículos publicados en revistas especializadas - Electrónicosspa
dc.subject.keywordHumanoidspa
dc.subject.keywordDynamic modelingspa
dc.subject.keywordEnergy analysisspa
dc.subject.keywordOptimizationspa
dc.subject.keywordQ-learningspa
dc.coverage.campusCRAI-USTA Bogotáspa
dc.identifier.doihttps://doi.org/10.1007/978-3-319-29339-4 21spa
dc.description.domainhttp://unidadinvestigacion.usta.edu.cospa
dc.relation.referencesGonzalez-Fierro, M., Balaguer, C., Swann, N., Nanayakkara, T.: A humanoid robot standing up through learning from demonstration using a multimodal reward function. In: 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pp. 74–79. IEEE (2013)spa
dc.relation.referencesMistry, M., Murai, A., Yamane, K., Hodgins, J.: Sit-to-stand task on a humanoid robot from human demonstration. In: 2010 10th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pp. 218–223. IEEE (2010)spa
dc.relation.referencesMorimoto, J., Doya, K.: Acquisition of stand-up behavior by a real robot using hierarchical reinforcement learning. Robot. Auton. Syst. 36(1), 37–51 (2001)spa
dc.relation.referencesYamasakitt, F., Endot, K., Kitanots, H., Asada, M.: Acquisition of humanoid walking motion using genetic algorithm - considering characteristics of servo modules. In: Proceedings of the 2002 IEEE, International Conference on Robotics 8 Automation, Washington, DC (2002)spa
dc.relation.referencesLei, X-.S., Pan, J., Su, J.-.B.: Humanoid Robot Locomotion. In: Proceedings of the Fourth International Conference on Machine Learning and Cybernetics, Guangzhou (2005)spa
dc.relation.referencesKober, J., Bagnell, J.A., Peters, J.: Reinforcement learning in robotics: a survey. Int. J. Robot. Res. 32, 1238–1274 (2013)spa
dc.relation.referencesTedrake, R., Zhang, T.W., Seung, H.S.: Learning to walk in 20 minutes. In: Proceedings of the Fourteenth Yale Workshop on Adaptive and Learning Systems, vol. 95585 (2005)spa
dc.relation.referencesEndo, G., Morimoto, J., Matsubara, T., Nakanishi, J., Cheng, G.: Learning CPGbased biped locomotion with a policy gradient method: application to a humanoid robot. Int. J. Robot. Res. 27(2), 213–228 (2008)spa
dc.relation.referencesGeng, T., Porr, B., Wrgtter, F.: Fast biped walking with a reflexive controller and real-time policy searching. Adv. Neural Inf. Process. Syst. 18, 427–434 (2005)spa
dc.relation.referencesWhitman, E.C., Atkeson, C.G.: Control of instantaneously coupled systems applied to humanoid walking. In: 2010 10th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pp. 210–217 (2010)spa
dc.relation.referencesHester, T., Quinlan, M., Stone, P.: Generalized Model Learning for Reinforcement Learning on a Humanoid Robot. In: International Conference on Robotics and Automation (2010)spa
dc.relation.referencesKuindersma, S., Grupen, R., Barto, A.: Learning dynamic arm motions for postural recovery. In: 2011 11th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pp. 7–12 ( 2011)spa
dc.relation.referencesCalderon, J.M., Elibol, E., Moreno, W., Weitzenfeld, A.: Current usage reduction through stiffness control in humanoid robot. In: 8th Workshop on Humanoid Soccer Robots, IEEE-RAS International Conference on Humanoid Robots (2013)spa
dc.relation.referencesLjung, L.: System Identication - Theory for the User, 2nd edn. Prentice-Hall, Upper Saddle River (1999)spa
dc.relation.referencesSutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)spa
dc.relation.referencesSilva, F.M., Machado, J.A.T.: Energy analysis during biped walking. In: Proceedings IEEE International Conference Robotics and Automation, vol. 1–4, pp. 59–64 (1999)spa
dc.relation.referencesCalderon, J., Weitzenfeld, A., Elibol, E.: Optimizing energy usage through variable joint stiffness control during humanoid robot walking. In: Behnke, S., Veloso, M., Visser, A., Xiong, R. (eds.) RoboCup 2013. LNCS, vol. 8371, pp. 492–503. Springer, Heidelberg (2014)spa


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Atribución-NoComercial-CompartirIgual 2.5 Colombia
Except where otherwise noted, this item's license is described as Atribución-NoComercial-CompartirIgual 2.5 Colombia

Indexado por: