Wheeled Lab: Modern Sim2Real for Low-cost, Open-source Wheeled Robotics

Tyler Han, Preet Shah, Sidharth Rajagopal, Yanda Bao, Sanghun Jung, Sidharth Talia, Gabriel Guo, Bryan Xu, Bhaumik Mehta, Emma Romig, Rosario Scalise, Byron Boots

Keywords: Sim2Real, Open-source, Reinforcement Learning, Education

TL;DR: Wheeled Lab is a framework which integrates accessible wheeled robots with state-of-the-art robotics simulation to help introduce modern techniques in Sim2Real for education and research.

Abstract: Simulation has been pivotal in recent robotics milestones and is poised to play a prominent role in the field's future. However, recent robotic advances often rely on expensive and high-maintenance platforms, limiting access to broader robotics audiences. This work introduces Wheeled Lab, a framework for integrating the low-cost, open-source wheeled platforms that are already widely established in education and research with Isaac Lab, an open-source, widely adopted, and rapidly growing simulation framework for robotics research. Wheeled Lab thus introduces to new user communities modern techniques in Sim2Real, such as domain randomization, sensor simulation, and end-to-end learning. To kickstart educational uses, we demonstrate three state-of-the-art policies for small-scale RC cars: controlled drifting, elevation traversal, and visual navigation, each trained and deployed through zero-shot reinforcement learning. By bridging the gap between advanced Sim2Real methods and affordable, available robotics, Wheeled Lab aims to democratize access to cutting-edge tools, fostering innovation and education in a broader robotics context. The full stack, from hardware to software, is low cost and open-source.

Submission Number: 11