K-VIL: Keypoints-based Visual Imitation Learning

TL;DR

K-VIL introduces a method for robotic visual imitation that automatically extracts object-centric keypoints and geometric constraints from minimal demonstrations, enabling robust skill transfer in complex, real-world scenes.

Contribution

The paper presents a novel keypoint-based approach for visual imitation learning that works from a single demonstration and incrementally updates task representations.

Findings

Effective in cluttered scenes and viewpoint mismatches.

Capable of handling large object variations and new instances.

Works in one-shot and few-shot learning scenarios.

Abstract

Visual imitation learning provides efficient and intuitive solutions for robotic systems to acquire novel manipulation skills. However, simultaneously learning geometric task constraints and control policies from visual inputs alone remains a challenging problem. In this paper, we propose an approach for keypoint-based visual imitation (K-VIL) that automatically extracts sparse, object-centric, and embodiment-independent task representations from a small number of human demonstration videos. The task representation is composed of keypoint-based geometric constraints on principal manifolds, their associated local frames, and the movement primitives that are then needed for the task execution. Our approach is capable of extracting such task representations from a single demonstration video, and of incrementally updating them when new demonstrations become available. To reproduce manipulation skills using the learned set of prioritized geometric constraints in novel scenes, we introduce a novel keypoint-based admittance controller. We evaluate our approach in several real-world applications, showcasing its ability to deal with cluttered scenes, viewpoint mismatch, new instances of categorical objects, and large object pose and shape variations, as well as its efficiency and robustness in both one-shot and few-shot imitation learning settings. Videos and source code are available at https://sites.google.com/view/k-vil.