Hierarchical mixtures of experts and the EM algorithm
Neural Computation
Multiple paired forward and inverse models for motor control
Neural Networks - Special issue on neural control and robotics: biology and technology
Multiple paired forward-inverse models for human motor learning and control
Proceedings of the 1998 conference on Advances in neural information processing systems II
Hidden Markov Models for Speech Recognition
Hidden Markov Models for Speech Recognition
Multiple model-based reinforcement learning
Neural Computation
Scaling Large Learning Problems with Hard Parallel Mixtures
SVM '02 Proceedings of the First International Workshop on Pattern Recognition with Support Vector Machines
Isotropic sequence order learning
Neural Computation
Neural Networks - 2004 Special issue: New developments in self-organizing systems
2006 Special issue: Mirror neurons and imitation: A computationally guided review
Neural Networks - 2006 Special issue: The brain mechanisms of imitation learning
2006 Special issue: A probabilistic model of gaze imitation and shared attention
Neural Networks - 2006 Special issue: The brain mechanisms of imitation learning
Neural Networks - 2006 Special issue: Neurobiology of decision making
Neural Networks - 2006 Special issue: Neurobiology of decision making
Reinforcement learning by reward-weighted regression for operational space control
Proceedings of the 24th international conference on Machine learning
Context-dependent predictions and cognitive arm control with XCSF
Proceedings of the 10th annual conference on Genetic and evolutionary computation
Anticipations, Brains, Individual and Social Behavior: An Introduction to Anticipatory Systems
Anticipatory Behavior in Adaptive Learning Systems
Anticipatory Behavior in Adaptive Learning Systems
Perturbational Neural Networks for Incremental Learning in Virtual Learning System
Neural Information Processing
Self-organized Reinforcement Learning Based on Policy Gradient in Nonstationary Environments
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Modular Neural Networks for Model-Free Behavioral Learning
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Robotics and Autonomous Systems
Combining modalities with different latencies for optimal motor control
Journal of Cognitive Neuroscience
A Two-Level Model of Anticipation-Based Motor Learning for Whole Body Motion
Anticipatory Behavior in Adaptive Learning Systems
A Groovy Virtual Drumming Agent
IVA '09 Proceedings of the 9th International Conference on Intelligent Virtual Agents
Refining the execution of abstract actions with learned action models
Journal of Artificial Intelligence Research
Intelligence Dynamics: a concept and preliminary experiments for open-ended learning agents
Autonomous Agents and Multi-Agent Systems
Levels and Types of Action Selection: The Action Selection Soup
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Autonomous robots with both body and behavior self-knowledge
PerMIS '07 Proceedings of the 2007 Workshop on Performance Metrics for Intelligent Systems
Active learning for sensorimotor coordinations of autonomous robots
HSI'09 Proceedings of the 2nd conference on Human System Interactions
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Incremental learning of integrated semiotics based on linguistic and behavioral symbols
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Active learning for multiple sensorimotor coordination based on state confidence
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Self-organizing multiple models for imitation: teaching a robot to dance the YMCA
IEA/AIE'07 Proceedings of the 20th international conference on Industrial, engineering, and other applications of applied intelligent systems
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
A self-organising multiple model architecture for motor imitation
International Journal of Intelligent Information and Database Systems
A hybrid controller based on the egocentric perceptual principle
Robotics and Autonomous Systems
Multisensory learning cues using analytical collision detection between a needle and a tube
HAPTICS'04 Proceedings of the 12th international conference on Haptic interfaces for virtual environment and teleoperator systems
From force control and sensory-motor informations to mass discrimination
SAB'10 Proceedings of the 11th international conference on Simulation of adaptive behavior: from animals to animats
eMOSAIC model for humanoid robot control
SAB'10 Proceedings of the 11th international conference on Simulation of adaptive behavior: from animals to animats
A minimum relative entropy principle for learning and acting
Journal of Artificial Intelligence Research
Task-specific generalization of discrete and periodic dynamic movement primitives
IEEE Transactions on Robotics
Learning multiple models of non-linear dynamics for control under varying contexts
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
Mosaic for multiple-reward environments
Neural Computation
Coupled inverse-forward models for action execution leading to tool-use in a humanoid robot
HRI '12 Proceedings of the seventh annual ACM/IEEE international conference on Human-Robot Interaction
An online adaptation control system using mnSOM
ICONIP'06 Proceedings of the 13 international conference on Neural Information Processing - Volume Part I
Hierarchies in action and motor control
Journal of Cognitive Neuroscience
The eMOSAIC model for humanoid robot control
Neural Networks
Motor simulation via coupled internal models using sequential Monte Carlo
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three
Learning local linear Jacobians for flexible and adaptive robot arm control
Genetic Programming and Evolvable Machines
Dynamics model abstraction scheme using radial basis functions
Journal of Control Science and Engineering - Special issue on Dynamic Neural Networks for Model-Free Control and Identification
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Internal simulations for behaviour selection and recognition
HBU'12 Proceedings of the Third international conference on Human Behavior Understanding
On the Development of an Ants-Inspired Navigational Network for Autonomous Robots
International Journal of Intelligent Mechatronics and Robotics
International Journal of Bioinformatics Research and Applications
Hi-index | 0.01 |
Humans demonstrate a remarkable ability to generate accurate and appropriate motor behavior under many different and often uncertain environmental conditions. We previously proposed a new modular architecture, the modular selection and identification for control (MOSAIC) model, for motor learning and control based on multiple pairs of forward (predictor) and inverse (controller) models. The architecture simultaneously learns the multiple inverse models necessary for control as well as how to select the set of inverse models appropriate for a given environment. It combines both feedforward and feedback sensorimotor information so that the controllers can be selected both prior to movement and subsequently during movement. This article extends and evaluates the MOSAIC architecture in the following respects. The learning in the architecture was implemented by both the original gradient-descent method and the expectation-maximization (EM) algorithm. Unlike gradient descent, the newly derived EM algorithm is robust to the initial starting conditions and learning parameters. Second, simulations of an object manipulation task prove that the architecture can learn to manipulate multiple objects and switch between them appropriately. Moreover, after learning, the model shows generalization to novel objects whose dynamics lie within the polyhedra of already learned dynamics. Finally, when each of the dynamics is associated with a particular object shape, the model is able to select the appropriate controller before movement execution. When presented with a novel shape-dynamic pairing, inappropriate activation of modules is observed followed by on-line correction.