Direct transfer of optimized controllers to similar systems using dimensionless MPC
This work addresses the challenge of controller transfer in engineering applications, offering a direct method that reduces tuning efforts for dynamically similar systems.
The paper tackles the problem of transferring optimized controllers to similar systems without additional tuning by proposing a dimensionless model predictive control method, demonstrating it on cartpole swing-up and car racing problems with reinforcement learning or Bayesian optimization for tuning.
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.