One-shot Video Imitation via Parameterized Symbolic Abstraction Graphs

TL;DR

This paper introduces a novel method using Parameterized Symbolic Abstraction Graphs to enable one-shot video imitation for manipulating dynamic objects, effectively capturing invisible physical attributes and generalizing across diverse tasks.

Contribution

The paper presents a new PSAG-based framework that interprets demonstrations, incorporates physical constraints via simulation, and generalizes to unseen objects and tasks.

Findings

Successful generalization to new objects and tasks

Effective capture of invisible physical attributes

Validated across multiple manipulation tasks

Abstract

Learning to manipulate dynamic and deformable objects from a single demonstration video holds great promise in terms of scalability. Previous approaches have predominantly focused on either replaying object relationships or actor trajectories. The former often struggles to generalize across diverse tasks, while the latter suffers from data inefficiency. Moreover, both methodologies encounter challenges in capturing invisible physical attributes, such as forces. In this paper, we propose to interpret video demonstrations through Parameterized Symbolic Abstraction Graphs (PSAG), where nodes represent objects and edges denote relationships between objects. We further ground geometric constraints through simulation to estimate non-geometric, visually imperceptible attributes. The augmented PSAG is then applied in real robot experiments. Our approach has been validated across a range of tasks, such as Cutting Avocado, Cutting Vegetable, Pouring Liquid, Rolling Dough, and Slicing Pizza. We demonstrate successful generalization to novel objects with distinct visual and physical properties.