Data-efficient learning of robotic clothing assistance using Bayesian Gaussian process latent variable model

References

• Kober J, Bagnell JA, Peters J. Reinforcement learning in robotics: a survey. Int J Rob Res. 2013;32(11):1238–1274.
   Web of Science ®Google Scholar
• Deisenroth MP, Neumann G, Peters J, et al. A survey on policy search for robotics. Found Trends Robot. 2013;2(1–2):1–142.
   Google Scholar
• Tamei T, Matsubara T, Rai A, et al. Reinforcement learning of clothing assistance with a dual-arm robot. In: IEEE-RAS International Conference on Humanoid Robots (Humanoids). IEEE; 2011. p. 733–738.
   Google Scholar
• Titsias MK, Lawrence ND. Bayesian Gaussian process latent variable model. Proceedings of the 13th International Conference on Artificial Intelligence and Statistics; 2010; Sardinia, Italy; Vol. 9. 2010. p. 844–851.
   Google Scholar
• Kober J, Peters JR. Policy search for motor primitives in robotics. International Conference on Neural Information Processing Systems; 2009; Vancouver, Canada; p. 849–856.
   Google Scholar
• Jolliffe I. Principal component analysis. Springer Berlin Heidelberg; 2002.
   Google Scholar
• Brunskill E, Roy N. SLAM using incremental probabilistic PCA and dimensionality reduction. In: IEEE International Conference on Robotics and Automation (ICRA). IEEE; 2005. p. 342–347.
   Google Scholar
• Calinon S, Guenter F, Billard A. On learning, representing, and generalizing a task in a humanoid robot. IEEE Trans Syst Man Cybern Part B (Cybern). 2007;37(2):286–298.
   PubMed Web of Science ®Google Scholar
• Ciocarlie M, Goldfeder C, Allen P. Dimensionality reduction for hand-independent dexterous robotic grasping. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE; 2007. p. 3270–3275.
   Google Scholar
• Artemiadis PK, Kyriakopoulos KJ. EMG-based control of a robot arm using low-dimensional embeddings. IEEE Trans Robot. 2010;26(2):393–398.
   Web of Science ®Google Scholar
• Watter M, Springenberg J, Boedecker J, et al. Embed to control: a locally linear latent dynamics model for control from raw images. International Conference on Neural Information Processing Systems; 2015; Montreal, Canada; p. 2746–2754.
   Google Scholar
• van Hoof H, Chen N, Karl M, et al. Stable reinforcement learning with autoencoders for tactile and visual data. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE; 2016. p. 3928–3934.
   Google Scholar
• Shon AP, Grochow K, Hertzmann A, et al. Learning shared latent structure for image synthesis and robotic imitation. International Conference on Neural Information Processing Systems; 2006; Vancouver, Canada; Vol. 18. 2006. p. 1233.
   Google Scholar
• Ko J, Fox D. Learning GP-bayesfilters via Gaussian process latent variable models. Auton Robots. 2011;30(1):3–23.
   Web of Science ®Google Scholar
• Wang Z, Mülling K, Deisenroth MP, et al. Probabilistic movement modeling for intention inference in human-robot interaction. Int J Rob Res. 2013;32(7):841–858.
   Web of Science ®Google Scholar
• Nakamura T, Nagai T, Mochihashi D, et al. Segmenting continuous motions with hidden semi-Markov models and Gaussian processes. Front Neurorobot. 2017;11:67.
   PubMed Web of Science ®Google Scholar
• Koskinopoulou M, Piperakis S, Trahanias PE. Learning from demonstration facilitates human-robot collaborative task execution. In: ACM/IEEE International Conference on Human Robot Interaction (HRI). IEEE Press; 2016. p. 59–66.
   Google Scholar
• Doumanoglou A, Kargakos A, Kim TK, et al. Autono-mous active recognition and unfolding of clothes using random decision forests and probabilistic planning. In: 2014 IEEE International Conference on Robotics and automation (ICRA). IEEE; 2014. p. 987–993.
   Google Scholar
• Huang SH, Pan J, Mulcaire G, et al. Leveraging appearance priors in non-rigid registration, with application to manipulation of deformable objects. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE; 2015. p. 878–885.
   Google Scholar
• Yang PC, Sasaki K, Suzuki K, et al. Repeatable folding task by humanoid robot worker using deep learning. IEEE Robot Autom Lett. 2017;2(2):397–403.
   Web of Science ®Google Scholar
• Balaguer B, Carpin S. Combining imitation and reinforcement learning to fold deformable planar objects. In: 2011 IEEE/RSJ International Conference on Intelligent robots and systems (IROS). IEEE; 2011. p. 1405–1412.
   Google Scholar
• Monsó P, Alenyà G, Torras C. Pomdp approach to robotized clothes separation. In: 2012 IEEE/RSJ International Conference on Intelligent robots and systems (IROS). IEEE; 2012. p. 1324–1329.
   Google Scholar
• Lee AX, Lu H, Gupta A, et al. Learning force-based manipulation of deformable objects from multiple demonstrations. In: IEEE International Conference on Robotics and Automation (ICRA). IEEE; 2015. p. 177–184.
   Google Scholar
• Hu Z, Sun P, Pan J. Three-dimensional deformable object manipulation using fast online Gaussian process regression. IEEE Robot Autom Lett. 2018;3(2):979–986.
   Web of Science ®Google Scholar
• Deisenroth MP, Fox D, Rasmussen CE. Gaussian processes for data-efficient learning in robotics and control. IEEE Trans Pattern Anal Mach Intell. 2015;37(2):408–423.
   PubMed Web of Science ®Google Scholar
• Bitzer S, Howard M, Vijayakumar S. Using dimensionality reduction to exploit constraints in reinforcement learning. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE; 2010. p. 3219–3225.
   Google Scholar
• Luck KS, Neumann G, Berger E, et al. Latent space policy search for robotics. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE; 2014. p. 1434–1440.
   Google Scholar
• Zhang C, Zhang H, Parker LE. Feature space decomposition for effective robot adaptation. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE; 2015. p. 441–448.
   Google Scholar
• Burleson W, Lozano C, Ravishankar V, et al. Assistive dressing system: a capabilities study for personalized support of dressing activities for people living with dementia. Iproceedings. 2015;1(1):e13.
   Google Scholar
• Orr C, Nugent C, Wang H, et al. A multi-agent approach to assist with dressing in a smart environment. International Summit on eHealth 360; 2016; Budapest, Hungary: Springer. p. 220–223.
   Google Scholar
• Klee SD, Ferreira BQ, Silva R, et al. Personalized assistance for dressing users. International Conference on Social Robotics; 2015; Paris, France: Springer. p. 359–369.
   Google Scholar
• Clegg A, Tan J, Turk G, et al. Animating human dressing. ACM Trans Graph (TOG). 2015;34(4):116.
   Web of Science ®Google Scholar
• Erickson Z, Clegg A, Yu W, et al. What does the person feel? learning to infer applied forces during robot-assisted dressing. In: 2017 IEEE International Conference on Robotics and automation (ICRA). IEEE; 2017. p. 6058–6065.
   Google Scholar
• Yu W, Kapusta A, Tan J, et al. Haptic simulation for robot-assisted dressing. In: 2017 IEEE International Conference on Robotics and Automation (ICRA). IEEE; 2017. p. 6044–6051.
   Google Scholar
• Yamazaki K, Oya R, Nagahama K, et al. Bottom dressing by a life-sized humanoid robot provided failure detection and recovery functions. In: IEEE/SICE International Symposium on System Integration (SII). IEEE; 2014. p. 564–570.
   Google Scholar
• Colomé A, Planells A, Torras C. A friction-model based framework for reinforcement learning of robotic tasks in non-rigid environments. In: IEEE International Conference on Robotics and Automation (ICRA). IEEE; 2015. p. 5649–5654.
   Google Scholar
• Kapusta A, Yu W, Bhattacharjee T, et al. Data-driven haptic perception for robot-assisted dressing. In: IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN). IEEE; 2016. p. 451–458.
   Google Scholar
• Gao Y, Chang HJ, Demiris Y. Iterative path optimisation for personalised dressing assistance using vision and force information. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE; 2016. p. 4398–4403.
   Google Scholar
• Koganti N, Ngeo JG, Tomoya T, et al. Cloth dynamics modeling in latent spaces and its application to robotic clothing assistance. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE; 2015. p. 3464–3469.
   Google Scholar
• Koganti N, Tamei T, Ikeda K, et al. Bayesian nonparametric learning of cloth models for real-time state estimation. IEEE Trans Robot. 2017;33(2):916–931.
   Web of Science ®Google Scholar
• Damianou AC, Titsias MK, Lawrence ND. Variational inference for latent variables and uncertain inputs in Gaussian processes. J Mach Learn Res. 2016;17(1):1425–1486.
   Google Scholar
• Lawrence N. Probabilistic non-linear principal component analysis with Gaussian process latent variable models. J Mach Learn Res. 2005;6(Nov):1783–1816.
   Google Scholar
• Rasmussen C, Williams C. Gaussian processes for machine learning. Vol. 10. Cambridge; The MIT Press; 2006.
   Google Scholar
• Ijspeert AJ, Nakanishi J, Hoffmann H, et al. Dynamical movement primitives: learning attractor models for motor behaviors. Neural Comput. 2013;25(2):328–373.
   PubMed Web of Science ®Google Scholar
• Schaal S, Atkeson CG. Constructive incremental learning from only local information. Neural Comput. 1998;10(8):2047–2084.
   PubMed Web of Science ®Google Scholar
• Wada Y, Kawato M. A theory for cursive handwriting based on the minimization principle. Biol Cybern. 1995;73(1):3–13.
   PubMed Web of Science ®Google Scholar
• Wilcoxon F. Individual comparisons by ranking methods. Biom Bull. 1945;1(6):80–83.
   Google Scholar
• Joshi RP, Koganti N, Shibata T. A framework for robotic clothing assistance by imitation learning. Adv Robot. 2019. Under review.
   Google Scholar
• Ngo G, Gaurav V, Shibata T. Clothing extremity identification using convolutional neural network regressor. In: IEEE International Conference on Informatics, Electronics & Vision (ICIEV) and International Conference on Imaging, Vision & Pattern Recognition (icIVPR). IEEE; 2018. p. 436–441.
   Google Scholar
• Saxena K, Labuguen R, Joshi RP, et al. A study on human-robot collaboration for table-setting task. In: IEEE International Conference on Robotics and Biomimetics (ROBIO). IEEE; 2017. p. 183–188.
   Google Scholar