The Mini Wheelbot Dataset: High-Fidelity Data for Robot Learning

TL;DR

This paper presents a high-fidelity, comprehensive dataset for the Mini Wheelbot robot, enabling researchers to develop and benchmark learning-based control algorithms using diverse real-world data.

Contribution

The paper introduces a detailed, synchronized dataset for the Mini Wheelbot, including multiple control paradigms, sensor data, and applications for robotics research.

Findings

Dataset covers multiple hardware instances and surfaces.

Includes synchronized sensor, pose, and video data.

Facilitates benchmarking of robotics algorithms.

Abstract

The development of robust learning-based control algorithms for unstable systems requires high-quality, real-world data, yet access to specialized robotic hardware remains a significant barrier for many researchers. This paper introduces a comprehensive dynamics dataset for the Mini Wheelbot, an open-source, quasi-symmetric balancing reaction wheel unicycle. The dataset provides 1 kHz synchronized data encompassing all onboard sensor readings, state estimates, ground-truth poses from a motion capture system, and third-person video logs. To ensure data diversity, we include experiments across multiple hardware instances and surfaces using various control paradigms, including pseudo-random binary excitation, nonlinear model predictive control, and reinforcement learning agents. We include several example applications in dynamics model learning, state estimation, and time-series classification to illustrate common robotics algorithms that can be benchmarked on our dataset.