Task-adaptive inertial parameter estimation of rigid-body dynamics with modeling error for model-based control using covariate shift adaptation.
Takamitsu MatsubaraHiroaki TakadaKenji SugimotoPublished in: AIM (2014)
Keyphrases
- parameter estimation
- covariate shift
- model selection
- rigid body
- cross validation
- dynamic model
- maximum likelihood
- least squares
- motion parameters
- markov random field
- domain adaptation
- rigid body motion
- parameter estimation algorithm
- machine learning
- motion segmentation
- error rate
- semi supervised learning
- em algorithm
- expectation maximization
- kalman filter
- feature selection
- cross domain
- ls svm
- d objects
- training and test data
- image sequences
- three dimensional