David A. Stenger

Johanna Menn, David Stenger, Sebastian Trimpe

Bayesian optimization is a popular black-box optimization method for parameter learning in control and robotics. It typically requires an objective function that reflects the user's optimization goal. However, in practical applications, this objective function is often inaccessible due to complex or unmeasurable performance metrics. Preferential Bayesian optimization (PBO) overcomes this limitation by leveraging human feedback through pairwise comparisons, eliminating the need for explicit performance quantification. When applying PBO to hardware systems, such as in quadcopter control, crashes can cause time-consuming experimental resets, wear and tear, or otherwise undesired outcomes. Standard PBO methods cannot incorporate feedback from such crashed experiments, resulting in the exploration of parameters that frequently lead to experimental crashes. We thus introduce CrashPBO, a user-friendly mechanism that enables users to both express preferences and report crashes during the optimization process. Benchmarking on synthetic functions shows that this mechanism reduces crashes by 63% and increases data efficiency. Through experiments on three robotics platforms, we demonstrate the wide applicability and transferability of CrashPBO, highlighting that it provides a flexible, user-friendly framework for parameter learning with human feedback on preferences and crashes.

Alexander von Rohr, David Stenger, Dominik Scheurenberg et al.

Controller tuning is crucial for closed-loop performance but often involves manual adjustments. Although Bayesian optimization (BO) has been established as a data-efficient method for automated tuning, applying it to large and high-dimensional search spaces remains challenging. We extend a recently proposed local variant of BO to include crash constraints, where the controller can only be successfully evaluated in an a-priori unknown feasible region. We demonstrate the efficiency of the proposed method through simulations and hardware experiments. Our findings showcase the potential of local BO to enhance controller performance and reduce the time and resources necessary for tuning.

Ali Gharib, David Stenger, Robert Ritschel et al.

This paper tackles the multi-objective optimization of the cost functional of a path-following model predictive control for vehicle longitudinal and lateral control. While the inherent optimal character of the model predictive control and the direct consideration of constraints gives a very powerful tool for many applications, is the determination of an appropriate cost functional a non-trivial task. This results on the one hand from the number of degrees of freedom or the multitude of adjustable parameters and on the other hand from the coupling of these. To overcome this situation a Bayesian optimization procedure is present, which gives the possibility to determine optimal cost functional parameters for a given desire. Moreover, a Pareto-front for a whole set of possible configurations can be computed.