Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives

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 perspective on imitation learning by predicting variability, correlations and uncertainty using a single model. This rich set of information is used in combination with the fusion of optimal controllers to learn robot actions from data, with two main advantages: i) robots become safe when uncertain about their actions and ii) they are able to leverage partial demonstrations, given as elementary sub-tasks, to optimally perform a higher level, more complex task. We showcase our approach in a painting task, where a human user and a KUKA robot collaborate to paint a wooden board. The task is divided into two sub-tasks and we show that the robot becomes compliant (hence safe) outside the training regions and executes the two sub-tasks with optimal gains otherwise.

Authors

• João Silvério
• Yanlong Huang
• Fares J. Abu-Dakka
• Leonel Rozo
• Darwin G. Caldwell

Keywords

• Training
• Uncertainty
• Imitation learning
• Predictive models
• Feature extraction
• Probabilistic logic
• Trajectory
• Paints
• Intelligent robots
• Painting
• Movement Primitives
• Optimal Control
• Wooden Board
• Variance In The Data
• Hyperparameters
• Covariance Matrix
• Diagonal Matrix
• Task Completion
• Gaussian Process
• Kriging
• Gaussian Mixture Model
• Prediction Uncertainty
• Hand Position
• Part Of The Task
• Reference Trajectory
• Human Hand
• Bottom Plot
• Riccati Equation
• Linear Quadratic Regulator
• Distribution Of Trajectories
• Task Space
• Precision Matrix
• Full Uncertainty
• Training Data
• Beginning Of The Task
• Stiffness Matrix
• Test Points
• Kernel Function