IMPASTO: Integrating Model-Based Planning with Learned Dynamics Models for Robotic Oil Painting Reproduction

TL;DR

IMPASTO is a robotic system that combines learned pixel dynamics with model-based planning to accurately reproduce oil paintings using force-sensitive control and multi-step stroke planning.

Contribution

It introduces a novel integration of learned dynamics models with model predictive control for robotic oil painting reproduction, learning solely from self-play.

Findings

Outperforms baselines in reproduction accuracy.

Learns from self-play without human demonstrations.

Successfully reproduces complex artworks with a robot arm.

Abstract

Robotic reproduction of oil paintings using soft brushes and pigments requires force-sensitive control of deformable tools, prediction of brushstroke effects, and multi-step stroke planning, often without human step-by-step demonstrations or faithful simulators. Given only a sequence of target oil painting images, can a robot infer and execute the stroke trajectories, forces, and colors needed to reproduce it? We present IMPASTO, a robotic oil-painting system that integrates learned pixel dynamics models with model-based planning. The dynamics models predict canvas updates from image observations and parameterized stroke actions; a receding-horizon model predictive control optimizer then plans trajectories and forces, while a force-sensitive controller executes strokes on a 7-DoF robot arm. IMPASTO integrates low-level force control, learned dynamics models, and high-level closed-loop planning, learns solely from robot self-play, and approximates human artists' single-stroke datasets and multi-stroke artworks, outperforming baselines in reproduction accuracy. Project website: https://impasto-robopainting.github.io/