Robot gaining accurate pouring skills through self-supervised learning and generalization

Paulius, 2019, Manipulation motion taxonomy and coding for robots, 5596 Billard, 2008, Robot programming by demonstration, 1371 Huang, 2019, A dataset of daily interactive manipulation, Int. J. Robot. Res., 38, 879, 10.1177/0278364919849091 Schenck, 2017, Visual closed-loop control for pouring liquids, 2629 Kennedy, 2019, Autonomous precision pouring from unknown containers, IEEE Robot. Autom. Lett., 4, 2317, 10.1109/LRA.2019.2902075 Do, 2018, Accurate pouring with an autonomous robot using an RGB-D camera, 210 Do, 2018, Learning to pour using deep deterministic policy gradients, 3074 Chen, 2019, Accurate pouring using model predictive control enabled by recurrent neural network, 7688 Calinon, 2008, A probabilistic programming by demonstration framework handling constraints in joint space and task space, 367 Lim, 2005, Movement primitives, principal component analysis, and the efficient generation of natural motions, 4630 Min, 2009, Interactive generation of human animation with deformable motion models, ACM Trans. Graph., 29, 9:1, 10.1145/1640443.1640452 Ramsay, 2009 Dai, 2013, Functional analysis of grasping motion, 3507 Huang, 2015, Generating manipulation trajectory using motion harmonics, 4949 Paulius, 2016, Functional object-oriented network for manipulation learning, 2655 Hersch, 2008, Dynamical system modulation for robot learning via kinesthetic demonstrations, IEEE Trans. Robot., 24, 1463, 10.1109/TRO.2008.2006703 Ijspeert, 2013, Dynamical movement primitives: Learning attractor models for motor behaviors, Neural Comput., 25, 328, 10.1162/NECO_a_00393 Amor, 2014, Interaction primitives for human-robot cooperation tasks, 2831 Paraschos, 2013, Probabilistic movement primitives, 2616 H. Sakoe, S. Chiba, Dynamic programming algorithm optimization for spoken word recognition, 26 (1) (1978) 43–49. Han, 2004, Modeling dynamic system by recurrent neural network with state variables Trischler, 2016, Synthesis of recurrent neural networks for dynamical system simulation, Neural Netw., 80, 67, 10.1016/j.neunet.2016.04.001 Sutskever, 2014, Sequence to sequence learning with neural networks, 3104 Graves, 2013 Huang, 2017, Learning to pour, 7005 Pan, 2016, Robot motion planning for pouring liquids, 518 Pan, 2017, Feedback motion planning for liquid pouring using supervised learning, 1252 Tamosiunaite, 2011, Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives, Robot. Auton. Syst., 59, 910, 10.1016/j.robot.2011.07.004 Rozo, 2013, Force-based robot learning of pouring skills using parametric hidden Markov models, 227 Yano, 2007, Supervisory control of automatic pouring process considering residual pouring quantity, 2045 Noda, 2008, Predictive filling weight sequence control in automatic pouring system, 1527 Yamaguchi, 2015, Pouring skills with planning and learning modeled from human demonstrations, Int. J. Humanoid Robot., 12, 10.1142/S0219843615500309 Liang, 2019, Making sense of audio vibration for liquid height estimation in robotic pouring, 5333 Kennedy, 2017, Precise dispensing of liquids using visual feedback, 1260 Huang, 2019 Wilches, 2020, Generalizing learned manipulation skills in practice, 9322 Neyshabur, 2017, Exploring generalization in deep learning, 5947 Wu, 2017 Dinh, 2017, Sharp minima can generalize for deep nets, 1019 Werbos, 1990, Backpropagation through time: what it does and how to do it, Proc. IEEE, 78, 1550, 10.1109/5.58337 Bengio, 1994, Learning long-term dependencies with gradient descent is difficult, Trans. Neural Netw., 5, 157, 10.1109/72.279181 Hochreiter, 1997, Long short-term memory, Neural Comput., 9, 1735, 10.1162/neco.1997.9.8.1735 Gers, 2003, Learning precise timing with lstm recurrent networks, J. Mach. Learn. Res., 3, 115 Huang, 2016, Recent data sets on object manipulation: A survey, Big Data, 4, 197, 10.1089/big.2016.0042 Zaremba, 2014 Zeng, 2020, Tossingbot: Learning to throw arbitrary objects with residual physics, IEEE Trans. Robot. Jelodar, 2018 Jelodar, 2019, Joint object and state recognition using language knowledge, 3352 Paulius, 2020, A motion taxonomy for manipulation embedding Alibayev, 2020, Estimating motion codes from demonstration videos Kiyokawa, 2019, Generation of a tactile-based pouring motion using fingertip force sensors, 669