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.

• Publication year

  2017

• Venue

  Italian National Conference on Sensors

• Publication date

  2017-12-01

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.3390/s17122907PMID 29240694PMCID 5751097
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Auto-Conditioned LSTM Network for Extended Complex Human Motion Synthesis

  2017cited by this paper
• Phase-functioned neural networks for character control

  2017cited by this paper
• Novel Methods for Surface EMG Analysis and Exploration Based on Multi-Modal Gaussian Mixture Models

  2016cited by this paper
• A Deep Learning Framework for Character Motion Synthesis and Editing

  2016cited by this paper
• Maximal switchability of centralized networks

  2016influential reference
• Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition

  2016influential reference
• Recurrent Network Models for Human Dynamics

  2015cited by this paper
• Motion reconstruction using very few accelerometers and ground contacts

  2015cited by this paper
• Efficient Unsupervised Temporal Segmentation of Motion Data

  2015cited by this paper
• Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors

  2013influential reference
• Flexible and Robust Networks

  2012cited by this paper
• Encoding of periodic and their transient motions by a single dynamic movement primitive

  2012influential reference
• Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives

  2011cited by this paper
• Flexible and Robust Patterning by Centralized Gene Networks

  2011cited by this paper
• Motion reconstruction using sparse accelerometer data

  2011cited by this paper
• Fast local and global similarity searches in large motion capture databases

  2010influential reference
• Motion fields for interactive character locomotion

  2010cited by this paper
• Emergent complex neural dynamics

  2010cited by this paper
• Model based inference in the life sciences: A primer on evidence, by David R. Anderson

  2009cited by this paper
• Central pattern generators for locomotion control in animals and robots: A review

  2008cited by this paper
• Networks in ecology

  2007cited by this paper
• Dynamic Movement Primitives -A Framework for Motor Control in Humans and Humanoid Robotics

  2006cited by this paper
• Dynamical principles in neuroscience

  2006cited by this paper
• Performance animation from low-dimensional control signals

  2005cited by this paper
• Automated extraction and parameterization of motions in large data sets

  2004influential reference
• Optimization of network robustness to waves of targeted and random attacks.

  2004cited by this paper
• Response of complex networks to stimuli.

  2004cited by this paper
• Control, Planning, Learning, and Imitation with Dynamic Movement Primitives

  2003cited by this paper
• Invariant properties in coevolutionary networks of plant-animal interactions

  2002cited by this paper
• Motion capture assisted animation: texturing and synthesis

  2002cited by this paper
• Food-web structure and network theory: The role of connectance and size

  2002cited by this paper
• Complexity and robustness

  2001cited by this paper
• Statistical mechanics of complex networks

  2001cited by this paper
• Halting viruses in scale-free networks.

  2001cited by this paper
• Lethality and centrality in protein networks

  2001cited by this paper
• Approximation of nonlinear systems with radial basis function neural networks

  2001cited by this paper
• Error and attack tolerance of complex networks

  2000cited by this paper
• The large-scale organization of metabolic networks

  2000cited by this paper
• Three machine learning techniques for automatic determination of rules to control locomotion

  1999cited by this paper
• A modular network for legged locomotion

  1998cited by this paper
• Hard-wired central pattern generators for quadrupedal locomotion

  1994cited by this paper
• A system of coupled oscillators can have arbitrary prescribed attractors

  1994cited by this paper
• Robustness of a distributed neural network controller for locomotion in a hexapod robot

  1992cited by this paper
• Orthogonal least squares learning algorithm for radial basis function networks

  1991cited by this paper

• Non-equilibrium dynamics in complex networks via asymmetric Glauber models

  2025cites this paper
• Generating Stochastic Processes Through Convolutional Neural Networks

  2020cites this paper
• A Gait Trajectory Control Scheme Through Successive Approximation Based on Radial Basis Function Neural Networks for the Lower Limb Exoskeleton Robot

  2020cites this paper
• Conventional and non conventional body motions modelling and control. Application to the handwriting process

  2019cites this paper
• Deep Learning Intervention for Health Care Challenges: Some Biomedical Domain Considerations

  2019cites this paper
• Deep Learning Intervention for Health Care Challenges: Some Biomedical Domain Considerations (Preprint)

  2018cites this paper