Generative system

description7 papers

group3 followers

lightbulbAbout this topic

A generative system is a computational framework that produces complex outputs from simple rules or algorithms, often through iterative processes. It emphasizes the creation of new structures, patterns, or data, enabling exploration and innovation in various domains such as art, design, and artificial intelligence.

lightbulbAbout this topic

Graphical Smalltalk with My Optimization System for Urban Planning Tasks

by Reinhard Koenig

2016

Abstract. Based on the description of a conceptual framework for the representation of planning problems on various scales, we introduce an evolutionary design optimization system. This system is exemplified by means of the generation of... more

our evolutionary algorithm (EA). The main argument for EA is their flexibility in dealing with the problem representation, which is crucial for the problems de- scribed above. below.

Graphical Smalltalk with My Optimization System for Urban Planning Tasks Author(s): Koenig, Reinhard; Treyer, Lukas; Schmitt, Gerhard N.

left-hand network in Figure 6 we find that there is no single bottleneck, and at least one other populated route. As a result this network has the worst fitness of the three. the diagrams in the bottom row in Figure 7 is similar to that of the corresponding diagrams in Figure 6. This indicates that both fitness functions direct the search process in a similarly efficient way. Our third example is based on the initial sce- nario with two defined sub-areas as shown in the right-hand image of Figure 5. In Figure 8 the central sub-area is shown as a dotted ellipse and the quiet sub-area as a dotted rectangle. To include the spatial aspect in the fitness function, we have to define how to represent the graphical objects that represent the sub-areas with the corresponding specified proper- ties. The fact that the three best networks have differ- ent maximal fitness values (diagrams in the bottom row of Figures 6 and 7), indicates that the evolution- ary optimization process explores different parts of the search space each time it is run. But despite the small differences in the maximum fitness values of the variants, they all fulfill the requirements relative- ly well. When we consider the random points (repre- senting randomly generated variants) we can clearly see the advantage of using the evolutionary search process compared to randomly generated solutions. The best variants are improved continuously over the 50 generations and reach a level, which cannot be achieved by a random generation process.

for residential usage, we want to have only streets with low choice values in it. Therefore we sum all differences of the choice values from the street seg- ment ci that are located inside the quiet area A and the maximum choice value of the network cmax. The average of this sum is used as the second part of our fitness function: solution in the left-hand image of Figure 8. Here the maximum choice value is at the edge of the central area and there is a relatively populated road in the quiet sub-area. Maybe the optimization algorithm could have found a better solution with more gen- erations. But the combined fitness function may be hindering the improvement of this variant. We will discuss this problem in the next section.

descriptionView Paper arrow_downwardDownload

Graphical Smalltalk with My Optimization System for Urban Planning Tasks

by Reinhard Koenig

2013

Based on the description of a conceptual framework for the representation of planning problems on various scales, we introduce an evolutionary design optimization system. This system is exemplified by means of the generation of street... more

descriptionView Paper arrow_downwardDownload

Generative system

Related Topics