AErOMAt - Automatisiertes Entwickeln aerodynamischer Strukturen und Fahrzeuge mithilfe evolutionärer Optimierung und Surrogatmodellierung (DE/BMBF/03FH012PX5,13FH012PX5)
Refine
H-BRS Bibliography
- yes (11)
Departments, institutes and facilities
Document Type
- Conference Object (11) (remove)
Language
- English (11)
Has Fulltext
- no (11)
Keywords
- Aerodynamics (2)
- MAP-Elites (2)
- Neuroevolution (2)
- Quality Diversity (2)
- surrogate modeling (2)
- 3D design (1)
- Autoencoder (1)
- Evolutionary algorithms (1)
- Evolutionary computation (1)
- Illumination algorithms (1)
The encoding of solutions in black-box optimization is a delicate, handcrafted balance between expressiveness and domain knowledge between exploring a wide variety of solutions, and ensuring that those solutions are useful. Our main insight is that this process can be automated by generating a dataset of high-performing solutions with a quality diversity algorithm (here, MAP-Elites), then learning a representation with a generative model (here, a Varia-tional Autoencoder) from that dataset. Our second insight is that this representation can be used to scale quality diversity optimization to higher dimensions-but only if we carefully mix solutions generated with the learned representation and those generated with traditional variation operators. We demonstrate these capabilities by learning an low-dimensional encoding for the inverse kinemat-ics of a thousand joint planar arm. The results show that learned representations make it possible to solve high-dimensional problems with orders of magnitude fewer evaluations than the standard MAP-Elites, and that, once solved, the produced encoding can be used for rapid optimization of novel, but similar, tasks. The presented techniques not only scale up quality diversity algorithms to high dimensions, but show that black-box optimization encodings can be automatically learned, rather than hand designed.
Surrogate models are used to reduce the burden of expensive-to-evaluate objective functions in optimization. By creating models which map genomes to objective values, these models can estimate the performance of unknown inputs, and so be used in place of expensive objective functions. Evolutionary techniques such as genetic programming or neuroevolution commonly alter the structure of the genome itself. A lack of consistency in the genotype is a fatal blow to data-driven modeling techniques: interpolation between points is impossible without a common input space. However, while the dimensionality of genotypes may differ across individuals, in many domains, such as controllers or classifiers, the dimensionality of the input and output remains constant. In this work we leverage this insight to embed differing neural networks into the same input space. To judge the difference between the behavior of two neural networks, we give them both the same input sequence, and examine the difference in output. This difference, the phenotypic distance, can then be used to situate these networks into a common input space, allowing us to produce surrogate models which can predict the performance of neural networks regardless of topology. In a robotic navigation task, we show that models trained using this phenotypic embedding perform as well or better as those trained on the weight values of a fixed topology neural network. We establish such phenotypic surrogate models as a promising and flexible approach which enables surrogate modeling even for representations that undergo structural changes.
Are quality diversity algorithms better at generating stepping stones than objective-based search?
(2019)
The route to the solution of complex design problems often lies through intermediate "stepping stones" which bear little resemblance to the final solution. By greedily following the path of greatest fitness improvement, objective-based search overlooks and discards stepping stones which might be critical to solving the problem. Here, we hypothesize that Quality Diversity (QD) algorithms are a better way to generate stepping stones than objective-based search: by maintaining a large set of solutions which are of high-quality, but phenotypically different, these algorithms collect promising stepping stones while protecting them in their own "ecological niche". To demonstrate the capabilities of QD we revisit the challenge of recreating images produced by user-driven evolution, a classic challenge which spurred work in novelty search and illustrated the limits of objective-based search. We show that QD far outperforms objective-based search in matching user-evolved images. Further, our results suggest some intriguing possibilities for leveraging the diversity of solutions created by QD.
The initial phase in real world engineering optimization and design is a process of discovery in which not all requirements can be made in advance, or are hard to formalize. Quality diversity algorithms, which produce a variety of high performing solutions, provide a unique chance to support engineers and designers in the search for what is possible and high performing. In this work we begin to answer the question how a user can interact with quality diversity and turn it into an interactive innovation aid. By modeling a user's selection it can be determined whether the optimization is drifting away from the user's preferences. The optimization is then constrained by adding a penalty to the objective function. We present an interactive quality diversity algorithm that can take into account the user's selection. The approach is evaluated in a new multimodal optimization benchmark that allows various optimization tasks to be performed. The user selection drift of the approach is compared to a state of the art alternative on both a planning and a neuroevolution control task, thereby showing its limits and possibilities.
Surrogate-assistance approaches have long been used in computationally expensive domains to improve the data-efficiency of optimization algorithms. Neuroevolution, however, has so far resisted the application of these techniques because it requires the surrogate model to make fitness predictions based on variable topologies, instead of a vector of parameters. Our main insight is that we can sidestep this problem by using kernel-based surrogate models, which require only the definition of a distance measure between individuals. Our second insight is that the well-established Neuroevolution of Augmenting Topologies (NEAT) algorithm provides a computationally efficient distance measure between dissimilar networks in the form of "compatibility distance", initially designed to maintain topological diversity. Combining these two ideas, we introduce a surrogate-assisted neuroevolution algorithm that combines NEAT and a surrogate model built using a compatibility distance kernel. We demonstrate the data-efficiency of this new algorithm on the low dimensional cart-pole swing-up problem, as well as the higher dimensional half-cheetah running task. In both tasks the surrogate-assisted variant achieves the same or better results with several times fewer function evaluations as the original NEAT.
The MAP-Elites algorithm produces a set of high-performing solutions that vary according to features defined by the user. This technique to 'illuminate' the problem space through the lens of chosen features has the potential to be a powerful tool for exploring design spaces, but is limited by the need for numerous evaluations. The Surrogate-Assisted Illumination (SAIL) algorithm, introduced here, integrates approximative models and intelligent sampling of the objective function to minimize the number of evaluations required by MAP-Elites.
The ability of SAIL to efficiently produce both accurate models and diverse high-performing solutions is illustrated on a 2D airfoil design problem. The search space is divided into bins, each holding a design with a different combination of features. In each bin SAIL produces a better performing solution than MAP-Elites, and requires several orders of magnitude fewer evaluations. The CMA-ES algorithm was used to produce an optimal design in each bin: with the same number of evaluations required by CMA-ES to find a near-optimal solution in a single bin, SAIL finds solutions of similar quality in every bin.
A new method for design space exploration and optimization, Surrogate-Assisted Illumination (SAIL), is presented. Inspired by robotics techniques designed to produce diverse repertoires of behaviors for use in damage recovery, SAIL produces diverse designs that vary according to features specified by the designer. By producing high-performing designs with varied combinations of user-defined features a map of the design space is created. This map illuminates the relationship between the chosen features and performance, and can aid designers in identifying promising design concepts. SAIL is designed for use with compu-tationally expensive design problems, such as fluid or structural dynamics, and integrates approximative models and intelligent sampling of the objective function to minimize the number of function evaluations required. On a 2D airfoil optimization problem SAIL is shown to produce hundreds of diverse designs which perform competitively with those found by state-of-the-art black box optimization. Its capabilities are further illustrated in a more expensive 3D aerodynamic optimization task.
Evolutionary illumination is a recent technique that allows producing many diverse, optimal solutions in a map of manually defined features. To support the large amount of objective function evaluations, surrogate model assistance was recently introduced. Illumination models need to represent many more, diverse optimal regions than classical surrogate models. In this PhD thesis, we propose to decompose the sample set, decreasing model complexity, by hierarchically segmenting the training set according to their coordinates in feature space. An ensemble of diverse models can then be trained to serve as a surrogate to illumination.
Neuroevolution methods evolve the weights of a neural network, and in some cases the topology, but little work has been done to analyze the effect of evolving the activation functions of individual nodes on network size, an important factor when training networks with a small number of samples. In this work we extend the neuroevolution algorithm NEAT to evolve the activation function of neurons in addition to the topology and weights of the network. The size and performance of networks produced using NEAT with uniform activation in all nodes, or homogenous networks, is compared to networks which contain a mixture of activation functions, or heterogenous networks. For a number of regression and classification benchmarks it is shown that, (1) qualitatively different activation functions lead to different results in homogeneous networks, (2) the heterogeneous version of NEAT is able to select well performing activation functions, (3) the produced heterogeneous networks are significantly smaller than homogeneous networks.