Composable Geometric Motion Policies using Multi-Task Pullback Bundle Dynamical Systems.
Andrew BylardRiccardo BonalliMarco PavonePublished in: ICRA (2021)
Keyphrases
- dynamical systems
- multi task
- multi task learning
- predictive state representations
- learning tasks
- partially observable markov decision processes
- feature selection
- nonlinear dynamical systems
- linear dynamical systems
- transfer learning
- state space
- multi class
- optimal policy
- human motion
- optical flow
- learning problems
- gaussian processes
- data mining
- image processing