Incremental Learning, Clustering and Hierarchy Formation of Whole Body Motion Patterns using Adaptive Hidden Markov Chains

Authors:
Dana Kulić;Wataru Takano;Yoshihiko Nakamura
Affiliations:
Department of Mechano-Informatics, University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan;Department of Mechano-Informatics, University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan;Department of Mechano-Informatics, University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan
Venue:
International Journal of Robotics Research
Year:
2008

Citing 10
Cited 24

Factorial Hidden Markov Models

Machine Learning - Special issue on learning with probabilistic representations
Data clustering: a review

ACM Computing Surveys (CSUR)
Factorial hidden Markov models and the generalized backfitting algorithm

Neural Computation
Human-Machine Collaborative Systems for Microsurgical Applications

International Journal of Robotics Research
Incremental learning of gestures by imitation in a humanoid robot

Proceedings of the ACM/IEEE international conference on Human-robot interaction
A sensor fusion approach for recognizing continuous human grasping sequences using hidden Markov models

IEEE Transactions on Robotics
An adaptive visual attentive tracker for human communicational behaviors using HMM-based TD learning with new State distinction capability

IEEE Transactions on Robotics
Online task recognition and real-time adaptive assistance for computer-aided machine control

IEEE Transactions on Robotics
On Learning, Representing, and Generalizing a Task in a Humanoid Robot

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Human action learning via hidden Markov model

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Growing Hidden Markov Models: An Incremental Tool for Learning and Predicting Human and Vehicle Motion

International Journal of Robotics Research
Incremental Learning and Memory Consolidation of Whole Body Human Motion Primitives

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Whole body motion primitive segmentation from monocular video

ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Incremental clustering of gesture patterns based on a self organizing incremental neural network

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Online segmentation and clustering from continuous observation of whole body motions

IEEE Transactions on Robotics
Comparative study of representations for segmentation of whole body human motion data

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Recognition of affect based on gait patterns

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics - Special issue on gait analysis
Contact-state classification in human-demonstrated robot compliant motion tasks using the boosting algorithm

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A biomimetic approach to inverse kinematics for a redundant robot arm

Autonomous Robots
Machine learning approaches for time-series data based on self-organizing incremental neural network

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Task-specific generalization of discrete and periodic dynamic movement primitives

IEEE Transactions on Robotics
Human motion database with a binary tree and node transition graphs

Autonomous Robots
Learning Non-linear Multivariate Dynamics of Motion in Robotic Manipulators

International Journal of Robotics Research
On-line unsupervised segmentation for multidimensional time-series data and application to spatiotemporal gesture data

IEA/AIE'10 Proceedings of the 23rd international conference on Industrial engineering and other applications of applied intelligent systems - Volume Part I
Conceptual Imitation Learning in a Human-Robot Interaction Paradigm

ACM Transactions on Intelligent Systems and Technology (TIST)
Incremental learning of full body motion primitives and their sequencing through human motion observation

International Journal of Robotics Research
A Self-Training Approach for Visual Tracking and Recognition of Complex Human Activity Patterns

International Journal of Computer Vision
Estimating the non-linear dynamics of free-flying objects

Robotics and Autonomous Systems
On-the-fly behavior coordination for interactive virtual agents: a model for learning, recognizing and reproducing hand-arm gestures online

Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems - Volume 3
Towards the detection of unusual temporal events during activities using HMMs

Proceedings of the 2012 ACM Conference on Ubiquitous Computing
Simple and complex behavior learning using behavior hidden Markov model and CobART

Neurocomputing
A robot learning from demonstration framework to perform force-based manipulation tasks

Intelligent Service Robotics
Skill learning and inference framework

AGI'13 Proceedings of the 6th international conference on Artificial General Intelligence
Discriminative functional analysis of human movements

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a novel approach for autonomous and incremental learning of motion pattern primitives by observation of human motion. Human motion patterns are abstracted into a dynamic stochastic model, which can be used for both subsequent motion recognition and generation, analogous to the mirror neuron hypothesis in primates. The model size is adaptable based on the discrimination requirements in the associated region of the current knowledge base. A new algorithm for sequentially training the Markov chains is developed, to reduce the computation cost during model adaptation. As new motion patterns are observed, they are incrementally grouped together using hierarchical agglomerative clustering based on their relative distance in the model space. The clustering algorithm forms a tree structure, with specialized motions at the tree leaves, and generalized motions closer to the root. The generated tree structure will depend on the type of training data provided, so that the most specialized motions will be those for which the most training has been received. Tests with motion capture data for a variety of motion primitives demonstrate the efficacy of the algorithm.