CoFRIDA: Self-Supervised Fine-Tuning for Human-Robot Co-Painting

TL;DR

CoFRIDA introduces a self-supervised fine-tuning method enabling robots to collaboratively co-paint with humans by improving text-image alignment and understanding robot constraints, resulting in more accurate and interactive paintings.

Contribution

This work presents a novel self-supervised fine-tuning approach that adapts pre-trained text-image models for real-world human-robot co-painting tasks, addressing prior limitations.

Findings

CoFRIDA produces paintings that better match input prompts than previous methods.

The fine-tuning encodes robot constraints, improving realism and collaboration.

The approach reduces sim-to-real gaps in robot painting applications.

Abstract

Prior robot painting and drawing work, such as FRIDA, has focused on decreasing the sim-to-real gap and expanding input modalities for users, but the interaction with these systems generally exists only in the input stages. To support interactive, human-robot collaborative painting, we introduce the Collaborative FRIDA (CoFRIDA) robot painting framework, which can co-paint by modifying and engaging with content already painted by a human collaborator. To improve text-image alignment, FRIDA's major weakness, our system uses pre-trained text-to-image models; however, pre-trained models in the context of real-world co-painting do not perform well because they (1) do not understand the constraints and abilities of the robot and (2) cannot perform co-painting without making unrealistic edits to the canvas and overwriting content. We propose a self-supervised fine-tuning procedure that can tackle both issues, allowing the use of pre-trained state-of-the-art text-image alignment models with robots to enable co-painting in the physical world. Our open-source approach, CoFRIDA, creates paintings and drawings that match the input text prompt more clearly than FRIDA, both from a blank canvas and one with human created work. More generally, our fine-tuning procedure successfully encodes the robot's constraints and abilities into a foundation model, showcasing promising results as an effective method for reducing sim-to-real gaps.