# The Mini Wheelbot: A Testbed for Learning-based Balancing, Flips, and Articulated Driving

arXiv: https://arxiv.org/abs/2502.04582 · HTML: https://mlsanity.com/paper/2502.04582/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving.
- Builds on 17 of its 61 references that are in the map.
- First posted on arXiv 7 Feb 2025.

## Placed in

- End-to-end autonomous driving / [Imitation-learning end-to-end planners](https://mlsanity.com/driving/imitation-learning-end-to-end-planners/)

## Builds on (most cited first, 17 of 17)

- [GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration](https://mlsanity.com/paper/1809.11165/) (2018)
- [Safe Controller Optimization for Quadrotors with Gaussian Processes](https://mlsanity.com/paper/1509.01066/) (2015)
- [Optimization-Based Autonomous Racing of 1:43 Scale RC Cars](https://mlsanity.com/paper/1711.07300/) (2017)
- [A survey on policy search algorithms for learning robot controllers in a handful of trials](https://mlsanity.com/paper/1807.02303/) (2018)
- [Autonomous Drone Racing: A Survey](https://mlsanity.com/paper/2301.01755/) (2023)
- [MPC-Net: A First Principles Guided Policy Search](https://mlsanity.com/paper/1909.05197/) (2019)
- [Automatic LQR Tuning Based on Gaussian Process Global Optimization](https://mlsanity.com/paper/1605.01950/) (2016)
- [The Robotarium: A remotely accessible swarm robotics research testbed](https://mlsanity.com/paper/1609.04730/) (2016)
- [Safe and Fast Tracking on a Robot Manipulator: Robust MPC and Neural Network Control](https://mlsanity.com/paper/1912.10360/) (2019)
- [Neural Networks for Fast Optimisation in Model Predictive Control: A Review](https://mlsanity.com/paper/2309.02668/) (2023)
- [Ascento: A Two-Wheeled Jumping Robot](https://mlsanity.com/paper/2005.11435/) (2020)
- [Parameter-Adaptive Approximate MPC: Tuning Neural-Network Controllers without Retraining](https://mlsanity.com/paper/2404.05835/) (2024)
- [Chronos and CRS: Design of a miniature car-like robot and a software framework for single and multi-agent robotics and control](https://mlsanity.com/paper/2209.12048/) (2022)
- [Fast integrators with sensitivity propagation for use in CasADi](https://mlsanity.com/paper/2211.01982/) (2022)
- [An Efficient Method for the Joint Estimation of System Parameters and Noise Covariances for Linear Time-Variant Systems](https://mlsanity.com/paper/2211.12302/) (2022)
- [The Wheelbot: A Jumping Reaction Wheel Unicycle](https://mlsanity.com/paper/2207.06988/) (2022)
- [Optimization-Based System Identification and Moving Horizon Estimation Using Low-Cost Sensors for a Miniature Car-Like Robot](https://mlsanity.com/paper/2404.08362/) (2024)

## Built on by (most cited first, 4 of 4)

- [Diffusion-Based Approximate MPC: Fast and Consistent Imitation of Multi-Modal Action Distributions](https://mlsanity.com/paper/2504.04603/) (2025)
- [End-to-End Low-Level Neural Control of an Industrial-Grade 6D Magnetic Levitation System](https://mlsanity.com/paper/2509.01388/) (2025)
- [Learning to Race in Minutes: Infoprop Dyna on the Mini Wheelbot](https://mlsanity.com/paper/2605.01096/) (2026)
- [All Models are Wrong, Knowing Where is Useful: On Model Uncertainty in Reinforcement Learning](https://mlsanity.com/paper/2606.01363/) (2026)

## Abstract (arXiv)

The Mini Wheelbot is a balancing, reaction wheel unicycle robot designed as a testbed for learning-based control. It is an unstable system with highly nonlinear yaw dynamics, non-holonomic driving, and discrete contact switches in a small, powerful, and rugged form factor. The Mini Wheelbot can use its wheels to stand up from any initial orientation - enabling automatic environment resets in repetitive experiments and even challenging half flips. We illustrate the effectiveness of the Mini Wheelbot as a testbed by implementing two popular learning-based control algorithms. First, we showcase Bayesian optimization for tuning the balancing controller. Second, we use imitation learning from an expert nonlinear MPC that uses gyroscopic effects to reorient the robot and can track higher-level velocity and orientation commands. The latter allows the robot to drive around based on user commands - for the first time in this class of robots. The Mini Wheelbot is not only compelling for testing learning-based control algorithms, but it is also just fun to work with, as demonstrated in the video of our experiments.