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

2025-02-07

AI Summary

This work addresses the control challenge of single-wheel robots (Mini Wheelbot) under highly nonlinear yaw dynamics, nonholonomic actuation, and discrete contact switching. To enable rigorous evaluation of learning-based control algorithms, we develop a hardware testbed integrating rigid-body dynamics modeling, gyroscopic effect analysis, and discrete contact-switching modeling. Our method combines Bayesian optimization for hyperparameter tuning, imitation learning for policy transfer, and nonlinear model predictive control (NMPC). To our knowledge, this is the first implementation enabling closed-loop velocity and heading tracking from high-level user commands, supporting autonomous uprighting, high-dynamic half-flips, and automatic environment reset. Experiments demonstrate robust balance stabilization, arbitrary-pose recovery, and command-following locomotion under strong nonlinearity and nonholonomic constraints. The platform provides a reproducible, scalable benchmark for data-driven control of unstable dynamical systems.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Search and Optimization: Mixed Discrete/Continuous Search
• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

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.

Problem

• Learning-based control algorithms
• Unstable nonlinear yaw dynamics
• Articulated driving and flips

Innovation

• Learning-based control algorithms
• Bayesian optimization balancing
• Imitation learning MPC