CoRL 2025: Demonstrating Artistic Drawing on Low-Cost Robot

Demonstrating Artistic Drawing on Low-Cost Robot

Heedon Jeong*, Minsu Joo*, Heejung Shin*, Hyunmin Song*,
Hyondong Oh, Jeong hwan Jeon, Taehwan Kim, and Hyemin Ahn**
*Equally Contributed, **Corresponding Author

Abstract

In this demo, we propose a low-cost robotic drawing system that makes robotic art more accessible to the public. While existing robotic drawing systems require expensive hardware and complex control mechanisms, our system utilizes low-cost manipulators and computationally efficient stroke extraction techniques. The system integrates a text-based generative model with a robot execution pipeline to convert text prompts into vectorized line drawings optimized for robotic drawing. The quality of the generated images is improved using prompt engineering, and then a structured stroke extraction process ensures smooth robotic execution. The drawing process is improved through PID gain tuning, trajectory optimization, and inverse kinematics optimization. Experimental evaluations conducted in simulations and real environments evaluate the fidelity of the generated sketches compared to the AI-generated counterparts. Although challenges remain in handling complex drawings and maintaining stability, our results demonstrate that combining low-cost robotics with generative AI is a viable way to create artistic applications

Overview

Demo Video

Result

AI-Generated Image

Processed Image

Robot-Drawn Image

References

[1] Jess Moss. Low-Cost Robot Arm: Koch v1.1. https://github.com/jess-moss/koch-v1-1.

[2] Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., Müller, J., ... & Rombach, R. (2023). Sdxl: Improving latent diffusion models for high- resolution image synthesis. arXiv preprint arXiv:2307.01952.

[3] Betker, J., Goh, G., Jing, L., Brooks, T., Wang, J., Li, L., ... & Ramesh, A. (2023). Improving image generation with better captions. Computer Science. https://cdn. openai. com/papers/dall-e-3. pdf, 2(3), 8.

[4] Gao, Y., Gong, L., Guo, Q., Hou, X., Lai, Z., Li, F., ... & Huang, W. (2025). Seedream 3.0 technical report. arXiv preprint arXiv:2504.11346.

[5] Vision Cortex. VTracer: Raster to Vector Graphics Converter. GitHub repository, 2024. https://github.com/visioncortex/vtracer.

[6] Bézier, P. (1972). Numerical control-mathematics and applications. Translated by AR Forrest.

[7] Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4), 600-612.