Direct transfer of optimized controllers to similar systems using dimensionless MPC
Josip Kir Hromatko, Shambhuraj Sawant, Šandor Ileš, Sébastien Gros
TL;DR
Dynamic similarity across scaled systems is often challenging for direct controller transfer. The paper presents a dimensionless MDP/MPC framework that nondimensionalizes dynamics, costs, and constraints, enabling zero-shot transfer of tuned controllers between dynamically similar systems. Policy tuning is performed via reinforcement learning or Bayesian optimization in the dimensionless domain, demonstrated on cart-pole and race-car tasks with successful cross-scale transfer. This approach allows learning from multi-scale data and can substantially reduce costly full-scale experiments while maintaining closed-loop performance.
Abstract
Scaled model experiments are commonly used in various engineering fields to reduce experimentation costs and overcome constraints associated with full-scale systems. The relevance of such experiments relies on dimensional analysis and the principle of dynamic similarity. However, transferring controllers to full-scale systems often requires additional tuning. In this paper, we propose a method to enable a direct controller transfer using dimensionless model predictive control, tuned automatically for closed-loop performance. With this reformulation, the closed-loop behavior of an optimized controller transfers directly to a new, dynamically similar system. Additionally, the dimensionless formulation allows for the use of data from systems of different scales during parameter optimization. We demonstrate the method on a cartpole swing-up and a car racing problem, applying either reinforcement learning or Bayesian optimization for tuning the controller parameters. Software used to obtain the results in this paper is publicly available at https://github.com/josipkh/dimensionless-mpcrl.