Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives

  title={Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives},
  author={Jo{\~a}o Silv{\'e}rio and Yanlong Huang and Fares J. Abu-Dakka and L. Rozo and D. Caldwell},
  journal={2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
During the past few years, probabilistic approaches to imitation learning have earned a relevant place in the robotics literature. One of their most prominent features is that, in addition to extracting a mean trajectory from task demonstrations, they provide a variance estimation. The intuitive meaning of this variance, however, changes across different techniques, indicating either variability or uncertainty. In this paper we leverage kernelized movement primitives (KMP) to provide a new… Expand
A Linearly Constrained Nonparametric Framework for Imitation Learning
  • Yanlong Huang, D. Caldwell
  • Computer Science, Mathematics
  • 2020 IEEE International Conference on Robotics and Automation (ICRA)
  • 2020
A probabilistic framework for learning geometry-based robot manipulation skills
Multi-person Pose Tracking using Sequential Monte Carlo with Probabilistic Neural Pose Predictor
An Intuitive Formulation of the Human Arm Active Endpoint Stiffness


Kernelized movement primitives
Non-parametric Imitation Learning of Robot Motor Skills
Generalized Orientation Learning in Robot Task Space
An Uncertainty-Aware Minimal Intervention Control Strategy Learned from Demonstrations
Probabilistic Movement Primitives
Statistical Learning by Imitation of Competing Constraints in Joint Space and Task Space
Learning optimal controllers in human-robot cooperative transportation tasks with position and force constraints
Probabilistic Learning of Torque Controllers from Kinematic and Force Constraints
Uncertainty-Aware Learning from Demonstration Using Mixture Density Networks with Sampling-Free Variance Modeling
Bayesian uncertainty modeling for programming by demonstration