One-shot optimization for vehicle dynamics control systems

Thomaser, André; Kononova, Anna V.; Vogt, Marc-Eric; Bäck, Thomas

doi:10.1145/3520304.3533979

Cited by 5 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As an example, anti-lock braking and variable damper control systems (ABS and VDS, respectively) which are responsible for driving safety depend on hundreds of parameters of a vehicle that cover different driving situations [26]. While the former controls the relative motion between a tire and a road during braking by adjusting the brake pressure, the latter manipulates braking force by adjusting damper constants of the shock absorbers.…”

Section: B Vehicle Dynamics Optimizationmentioning

confidence: 99%

“…While the former controls the relative motion between a tire and a road during braking by adjusting the brake pressure, the latter manipulates braking force by adjusting damper constants of the shock absorbers. The approach discussed in Section II has been successfully used to find a set of ABS and VDC parameters that deliver minimal (simulated) braking distance [26].…”

Section: B Vehicle Dynamics Optimizationmentioning

confidence: 99%

See 1 more Smart Citation

AI for Expensive Optimization Problems in Industry

Stein

Winter

Bäck

et al. 2023

2023 IEEE Conference on Artificial Intelligence (CAI)

Self Cite

View full text Add to dashboard Cite

The optimization of real-world engineering problems can be a challenging task, owing to the limited understanding of problem characteristics and the high cost of evaluating objectives and constraints in terms of computing time or licenses. This study proposes an AI-assisted optimization pipeline that addresses these challenges by using proxy functions in order to select and optimize the optimization algorithm and its hyperparameters, thereby significantly accelerating the optimization process on the real (expensive) problem. These proxy functions are inexpensive to evaluate and are selected to exhibit similar landscape characteristics as the original problem. To obtain such proxy functions, we adopt an approach, which involves computing Exploratory Landscape Analysis (ELA) features to characterize the problem's landscape. The ELA features are then used to identify an artificial function that replicates the original problem's properties, which can then be employed as a lowcost proxy function for the hyper-parameter optimization of our pipeline. Several real-world industrial applications are discussed as use-case of our proposed approach.

show abstract

Section: B Vehicle Dynamics Optimizationmentioning

confidence: 99%

Section: B Vehicle Dynamics Optimizationmentioning

confidence: 99%