Imitation learning methods have proven effective in learning robotic tasks by leveraging multiple human-controlled demonstrations. However, existing approaches often struggle to generalize across a wide range of tasks, such as extrapolating to unseen object locations, incorporating via-point modulation, accurately modeling orientation, handling trajectories with multiple options, and capturing aiming actions. In this study, we propose a novel framework that combines ideas from task-parameterized Gaussian mixture models and probabilistic movement primitives to address these limitations and satisfy all the aforementioned properties within a single framework. We conduct comprehensive evaluations of our approach on four real-life tasks: pick-and-place, water pouring, shooting a hockey puck into a net, and sweeping.
@article{yao2023improved,
title={Improved generalization of probabilistic movement primitives for manipulation trajectories},
author={Yao, Xueyang and Chen, Yinghan and Tripp, Bryan},
journal={IEEE Robotics and Automation Letters},
volume={9},
number={1},
pages={287--294},
year={2023},
publisher={IEEE}
}