One-Shot Imitation Learning: A Pose Estimation Perspective

Pietro Vitiello, Kamil Dreczkowski, Edward Johns

Keywords: One-Shot Imitation Learning, Unseen Object Pose Estimation, Robot Manipulation

TL;DR: We study one-shot imitation learning from the perspective of unseen object pose estimation, providing valuable insights as well as showing this framework's potential in real world robotics tasks.

Abstract: In this paper, we study imitation learning under the challenging setting of: (1) only a single demonstration, (2) no further data collection, and (3) no prior task or object knowledge. We show how, with these constraints, imitation learning can be formulated as a combination of trajectory transfer and unseen object pose estimation. To explore this idea, we provide an in-depth study on how state-of-the-art unseen object pose estimators perform for one-shot imitation learning on ten real-world tasks, and we take a deep dive into the effects that camera calibration, pose estimation error, and spatial generalisation have on task success rates. For videos, please visit www.robot-learning.uk/pose-estimation-perspective.

Student First Author: yes

Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)

Video: https://youtu.be/4N4czAm61Fc?si=inOJOsqb4fwJL7hT

Website: https://www.robot-learning.uk/pose-estimation-perspective