Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives
This work addresses safety and efficiency in robotics for tasks like human-robot collaboration, but it is incremental as it builds on existing probabilistic imitation learning methods.
The paper tackled the problem of imitation learning by using kernelized movement primitives to predict variability, correlations, and uncertainty in robot actions, resulting in a robot that becomes safe when uncertain and optimally performs complex tasks from partial demonstrations, as shown in a collaborative painting task with a KUKA robot.
During the past few years, probabilistic approaches to imitation learning have earned a relevant place in the literature. One of their most prominent features, in addition to extracting a mean trajectory from task demonstrations, is that 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 about robot actions. This rich set of information is used in combination with optimal controller fusion to learn 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 using our approach the robot becomes compliant (hence safe) outside the training regions and executes the two sub-tasks with optimal gains.