One-shot Video Imitation via Parameterized Symbolic Abstraction Graphs
This addresses the problem of scalable robot learning from limited demonstrations for tasks involving deformable objects, representing an incremental improvement over prior methods.
The paper tackles learning to manipulate dynamic and deformable objects from a single demonstration video by proposing Parameterized Symbolic Abstraction Graphs (PSAG) to interpret videos and estimate invisible physical attributes, achieving successful generalization to novel objects with distinct properties in tasks like cutting avocado and pouring liquid.
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.