Centralized Networks to Generate Human Body Motions

We consider continuous-time recurrent neural networks as dynamical models for the simulation of human body motions. These networks consist of a few centers and many satellites connected to them. The centers evolve in time as periodical oscillators with different frequencies. The center states define the satellite neurons’ states by a radial basis function (RBF) network. To simulate different motions, we adjust the parameters of the RBF networks. Our network includes a switching module that allows for turning from one motion to another. Simulations show that this model allows us to simulate complicated motions consisting of many different dynamical primitives. We also use the model for learning human body motion from markers’ trajectories. We find that center frequencies can be learned from a small number of markers and can be transferred to other markers, such that our technique seems to be capable of correcting for missing information resulting from sparse control marker settings.

[1]  Jun Nakanishi,et al.  Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors , 2013, Neural Computation.

[2]  A. Barabasi,et al.  Lethality and centrality in protein networks , 2001, Nature.

[3]  Taku Komura,et al.  Phase-functioned neural networks for character control , 2017, ACM Trans. Graph..

[4]  S. Jonic,et al.  Three machine learning techniques for automatic determination of rules to control locomotion , 1999, IEEE Transactions on Biomedical Engineering.

[5]  Björn Krüger,et al.  Novel Methods for Surface EMG Analysis and Exploration Based on Multi-Modal Gaussian Mixture Models , 2016, PloS one.

[6]  Jessica K. Hodgins,et al.  Performance animation from low-dimensional control signals , 2005, ACM Trans. Graph..

[7]  Albert-László Barabási,et al.  Error and attack tolerance of complex networks , 2000, Nature.

[8]  Taku Komura,et al.  A Deep Learning Framework for Character Motion Synthesis and Editing , 2016, ACM Trans. Graph..

[9]  Randall D. Beer,et al.  Robustness of a distributed neural network controller for locomotion in a hexapod robot , 1992, IEEE Trans. Robotics Autom..

[10]  S. Vakulenko.  A system of coupled oscillators can have arbitrary prescribed attractors , 1994 .

[11]  R. Albert,et al.  The large-scale organization of metabolic networks , 2000, Nature.

[12]  Lucas Kovar,et al.  Automated extraction and parameterization of motions in large data sets , 2004, ACM Trans. Graph..

[13]  Peter A. Bednekoff,et al.  Model Based Inference in the Life Sciences: A Primer on Evidence David R. Anderson Model Based Inference in the L , 2009, Animal Behaviour.

[14]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[15]  Jun Nakanishi,et al.  Control, Planning, Learning, and Imitation with Dynamic Movement Primitives , 2003 .

[16]  Sergei Vakulenko,et al.  Flexible and Robust Networks , 2012, J. Bioinform. Comput. Biol..

[17]  I. Epstein,et al.  Response of complex networks to stimuli. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[18]  Björn Krüger,et al.  Motion reconstruction using very few accelerometers and ground contacts , 2015, Graph. Model..

[19]  Reinhard Klein,et al.  Efficient Unsupervised Temporal Segmentation of Motion Data , 2015, IEEE Transactions on Multimedia.

[20]  Auke Jan Ijspeert,et al.  Central pattern generators for locomotion control in animals and robots: A review , 2008, Neural Networks.

[21]  J. Bascompte,et al.  Invariant properties in coevolutionary networks of plant-animal interactions , 2002 .

[22]  A. Selverston,et al.  Dynamical principles in neuroscience , 2006 .

[23]  Jitendra Malik,et al.  Recurrent Network Models for Human Dynamics , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[24]  D. Chialvo.  Emergent complex neural dynamics , 2010, 1010.2530.

[25]  Ian Stewart,et al.  A modular network for legged locomotion , 1998 .

[26]  Albert-László Barabási,et al.  Statistical mechanics of complex networks , 2001, ArXiv.

[27]  A. Barabasi,et al.  Halting viruses in scale-free networks. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[28]  J. Bascompte.  Networks in ecology , 2007 .

[29]  Yi Zhou,et al.  Auto-Conditioned LSTM Network for Extended Complex Human Motion Synthesis , 2017, ArXiv.

[30]  Hans-Peter Seidel,et al.  Motion reconstruction using sparse accelerometer data , 2011, TOGS.

[31]  Zoran Popovic,et al.  Motion fields for interactive character locomotion , 2010, CACM.

[32]  Ales Ude,et al.  Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives , 2011, Robotics Auton. Syst..

[33]  Daniel Roggen,et al.  Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition , 2016, Sensors.

[34]  John Doyle,et al.  Complexity and robustness , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[35]  O. Radulescu,et al.  Maximal switchability of centralized networks , 2016, 1606.02859.

[36]  S. Havlin,et al.  Optimization of network robustness to waves of targeted and random attacks. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[37]  Stefan Schaal,et al.  Encoding of periodic and their transient motions by a single dynamic movement primitive , 2012, 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012).

[38]  James J. Carroll,et al.  Approximation of nonlinear systems with radial basis function neural networks , 2001, IEEE Trans. Neural Networks.

[39]  J. J. Collins,et al.  Hard-wired central pattern generators for quadrupedal locomotion , 1994, Biological Cybernetics.

[40]  S. Schaal.  Dynamic Movement Primitives -A Framework for Motor Control in Humans and Humanoid Robotics , 2006 .

[41]  Sergei Vakulenko,et al.  Flexible and Robust Patterning by Centralized Gene Networks , 2011, Fundam. Informaticae.

[42]  Christoph Bregler,et al.  Motion capture assisted animation: texturing and synthesis , 2002, ACM Trans. Graph..

[43]  Neo D. Martinez,et al.  Food-web structure and network theory: The role of connectance and size , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[44]  Arno Zinke,et al.  Fast local and global similarity searches in large motion capture databases , 2010, SCA '10.