Designing Air Flow with Surrogate-Assisted Phenotypic Niching

Abstract

In complex, expensive optimization domains we often narrowly focus on finding high performing solutions, instead of expanding our understanding of the domain itself. But what if we could quickly understand the complex behaviors that can emerge in said domains instead? We introduce surrogate-assisted phenotypic niching, a quality diversity algorithm which allows to discover a large, diverse set of behaviors by using computationally expensive phenotypic features. In this work we discover the types of air flow in a 2D fluid dynamics optimization problem. A fast GPU-based fluid dynamics solver is used in conjunction with surrogate models to accurately predict fluid characteristics from the shapes that produce the air flow. We show that these features can be modeled in a data-driven way while sampling to improve performance, rather than explicitly sampling to improve feature models. Our method can reduce the need to run an infeasibly large set of simulations while still being able to design a large diversity of air flows and the shapes that cause them. Discovering diversity of behaviors helps engineers to better understand expensive domains and their solutions.

Artificial Intelligence in Elite Sports—A Narrative Review of Success Stories and Challenges

“…Bayesian optimization has also been used in the context of multi-criteria optimization (Emmerich et al, 2016 ) and QD (Gaier et al, 2017a ; Hagg et al, 2020a ). Moreover, generative models can also be applied to optimization and planning (Hagg et al, 2020b , 2021 ).…”

Covariance Matrix Adaptation MAP-Annealing

“…Several works combine gradient information with quality diversity optimization in ways that do not leverage the objective and measure gradients directly. For example, in model-based quality diversity optimization [26,31,6,46,54,78,27], prior work [66] trains an autoencoder on the archive of solutions and leverages the Jacobian of the decoder network to compute the covariance of the Gaussian perturbation. In quality diversity reinforcement learning (QD-RL), several works [60,62,57,75] approximate a reward gradient or diversity gradient via a critic network, action space noise, or evolution strategies and incorporate those gradients into a QD-RL algorithm.…”

T-DominO: Exploring Multiple Criteria with Quality-Diversity and the Tournament Dominance Objective

“…QD approaches such as MAP-Elites [7,33] search for solutions along a continuum of user-defined features, making them ideal for exploration. MAP-Elites has been used for design exploration in domains such as aerodynamics [15,16,17,23,24], and game design [1,5,19,20], but has been restricted to consideration of a single objective. MAP-Elites operates by first discretizing the feature space into bins, collectively known as a map or archive.…”