Robot Learning to Paint from Demonstrations

1 Seoul National University, 2 KAIST, 3 NAVER LABS
IROS 2022
🏆 Award Winner: Best Entertainment & Amusement Paper 🏆

* Equal Contribution, Work done as an intern at NAVER LABS

This drawing robot, named ARTO-1, creates an artwork on a canvas
using the drawing skills learned from human demonsrations!


Robotic painting tasks in the real world are often made complicated by the highly complex and stochastic nature of the dynamics that underlie, e.g., physical contact between the painting tool and a canvas, color blendings between painting mediums, and many more. Simulation-based inverse graphics algorithms, for example, can not be directly transferred to the real-world due in large to the considerable gap in the viable range of painting strokes the robot can accurately generate onto the physical canvas. In this paper, we aim at minimizing this gap by appealing to a data-driven skill learning approach. The core idea lies in allowing the robot to learn continuous stroke-level skills that jointly encodes action trajectories and painted outcomes from an extensive collection of human demonstrations. We demonstrate the efficacy of our method through extensive real-world experiments using a 4-dof torque-controllable manipulator with a digital canvas(iPad).

Collecting Stroke Demonstrations

Training Robot Painting Skills

Painting by planning on skill space

Robotic Paintings

Video Presentation


        title={Robot Learning to Paint from Demonstrations},
        author={Park, Younghyo and Jeon, Seunghun and Lee, Taeyoon},
        booktitle={2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},