Robotic Scene Cloning:Advancing Zero-Shot Robotic Scene Adaptation in Manipulation via Visual Prompt Editing

TL;DR

This paper introduces Robotic Scene Cloning (RSC), a method that enables robots to adapt to new scenes by editing existing trajectories using visual prompts, improving zero-shot transfer and generalization in diverse environments.

Contribution

The paper presents a novel scene-specific adaptation technique for robots that leverages visual prompts and trajectory editing, advancing zero-shot capabilities without extensive data collection.

Findings

RSC improves task performance across various object types.

RSC enhances policy generalization in simulated and real environments.

RSC enables moderate shape and texture adaptations based on visual prompts.

Abstract

Modern robots can perform a wide range of simple tasks and adapt to diverse scenarios in the well-trained environment. However, deploying pre-trained robot models in real-world user scenarios remains challenging due to their limited zero-shot capabilities, often necessitating extensive on-site data collection. To address this issue, we propose Robotic Scene Cloning (RSC), a novel method designed for scene-specific adaptation by editing existing robot operation trajectories. RSC achieves accurate and scene-consistent sample generation by leveraging a visual prompting mechanism and a carefully tuned condition injection module. Not only transferring textures but also performing moderate shape adaptations in response to the visual prompts, RSC demonstrates reliable task performance across a variety of object types. Experiments across various simulated and real-world environments demonstrate that RSC significantly enhances policy generalization in target environments.