Gregory S. Hornby

Creating high-level components with a generative representation for body-brain evolution

One of the main limitations of scalability in body-brain evolution systems is the representation chosen for encoding creatures. This paper defines a class of representations called generative representations, which are identified by their ability to reuse elements of the genotype in the translation to the phenotype. This paper presents an example of a generative representation for the concurrent evolution of the morphology and neural controller of simulated robots, and also introduces GENRE, an evolutionary system for evolving designs using this representation. Applying GENRE to the task of evolving robots for locomotion and comparing it against a non-generative (direct) representation shows that the generative representation system rapidly produces robots with significantly greater fitness. Analyzing these results shows that the generative representation system achieves better performance by capturing useful bias from the design space and by allowing viable large scale mutations in the phenotype. Generative representations thereby enable the encapsulation, coordination, and reuse of assemblies of parts.

Modeling Building-Block Interdependency

The Building-Block Hypothesis appeals to the notion of problem decomposition and the assembly of solutions from sub-solutions. Accordingly, there have been many varieties of GA lest problems with a structure based on building-blocks. Many of these problems use deceptive fitness functions to model interdependency between the bits within a block. However, very few have any model of interdependency between building-blocks; those that do are not consistent in the type of interaction used intra-block and inter-block. This paper discusses the inadequacies of the various lest problems in the literature and clarifies the concept of building-block interdependency. We formulate a principled model of hierarchical interdependency that can be applied through many levels in a consistent manner and introduce Hierarchical If-and-only-if (H-1FF) as a canonical example. We present some empirical results of GAs on H-1FF showing that if population diversity is maintained and linkage is tight then the GA is able to identify and manipulate building-blocks over many levels of assembly, as the Building-Block Hypothesis suggests.

ALPS: the age-layered population structure for reducing the problem of premature convergence

To reduce the problem of premature convergence we define a new method for measuring an individuals age and propose the Age-Layered Population Structure (ALPS). This new measure of age measures how long the genetic material has been evolving in the population: offspring start with an age of 1 plus the age of their oldest parent instead of starting with an age of 0 as with traditional measures of age. ALPS differs from a typical evolutionary algorithm (EA) by segregating individuals into different age-layers by their age and by regularly introducing new, randomly generated individuals in the youngest layer. The introduction of randomly generated individuals at regular intervals results in an EA that is never completely converged and is always exploring new parts of the fitness landscape. By using age to restrict competition and breeding, younger individuals are able to develop without being dominated by older ones. Analysis of the search behavior of ALPS finds that the offspring of individuals that are randomly generated mid-way through a run are able to move the population out of mediocre local-optima to better parts of the fitness landscape. In comparison against a traditional EA, a multi-start EA and two other EAs with diversity maintenance schemes we find that ALPS produces significantly better designs with a higher reliability than the other EAs.

The advantages of generative grammatical encodings for physical design

One of the applications of evolutionary algorithms is the automatic creation of designs. For evolutionary techniques to scale to the complexities necessary for actual engineering problems, it has been argued that generative systems, where the genotype is an algorithm for constructing the final design, should be used as the encoding. We describe a system for creating generative specifications by combining Lindenmayer systems with evolutionary algorithms, and we apply it to the problem of generating table designs. Designs evolved by our system reach an order of magnitude more parts than previous generative systems. Comparing it against a non-generative encoding, we find that the generative system produces designs with higher fitness and is faster than the non-generative system. Finally, we demonstrate the ability of our system to go from design to manufacture by constructing evolved table designs using rapid prototyping equipment.

Generative representations for the automated design of modular physical robots

The field of evolutionary robotics has demonstrated the ability to automatically design the morphology and controller of simple physical robots through synthetic evolutionary processes. However, it is not clear if variation-based search processes can attain the complexity of design necessary for practical engineering of robots. Here, we demonstrate an automatic design system that produces complex robots by exploiting the principles of regularity, modularity, hierarchy, and reuse. These techniques are already established principles of scaling in engineering design and have been observed in nature, but have not been broadly used in artificial evolution. We gain these advantages through the use of a generative representation, which combines a programmatic representation with an algorithmic process that compiles the representation into a detailed construction plan. This approach is shown to have two benefits: it can reuse components in regular and hierarchical ways, providing a systematic way to create more complex modules from simpler ones; and the evolved representations can capture intrinsic properties of the design space, so that variations in the representations move through the design space more effectively than equivalent-sized changes in a nongenerative representation. Using this system, we demonstrate for the first time the evolution and construction of modular, three-dimensional, physically locomoting robots, comprising many more components than previous work on body-brain evolution.

Autonomous evolution of dynamic gaits with two quadruped robots

A challenging task that must be accomplished for every legged robot is creating the walking and running behaviors needed for it to move. In this paper we describe our system for autonomously evolving dynamic gaits on two of Sonys quadruped robots. Our evolutionary algorithm runs on board the robot and uses the robots sensors to compute the quality of a gait without assistance from the experimenter. First, we show the evolution of a pace and trot gait on the OPEN-R prototype robot. With the fastest gait, the robot moves at over 10 m/min, which is more than forty body-lengths/min. While these first gaits are somewhat sensitive to the robot and environment in which they are evolved, we then show the evolution of robust dynamic gaits, one of which is used on the ERS-110, the first consumer version of AIBO.

Evolving robust gaits with AIBO

An evolutionary algorithm is used to evolve gaits with the Sony entertainment robot, AIBO. All processing is handled by the robots on-board computer with individuals evaluated using the robots hardware. By sculpting the experimental environment, we increase the robustness to different surface types and different AIBOs. Evolved gaits are faster than those created by hand. Using this technique we evolve a gait used in the consumer version of AIBO.

Evolving L-systems to generate virtual creatures

Abstract Virtual creatures play an increasingly important role in computer graphics as special effects and background characters. The artificial evolution of such creatures potentially offers some relief from the difficult and time consuming task of specifying morphologies and behaviors. But, while artificial life techniques have been used to create a variety of virtual creatures, previous work has not scaled beyond creatures with 50 components and the most recent work has generated creatures that are unnatural looking. Here we describe a system that uses Lindenmayer systems (L-systems) as the encoding of an evolutionary algorithm (EA) for creating virtual creatures. Creatures evolved by this system have hundreds of parts, and the use of an L-system as the encoding results in creatures with a more natural look.

An Evolved Antenna for Deployment on Nasa’s Space Technology 5 Mission

We present an evolved X-band antenna design and flight prototype currently on schedule to be deployed on NASA’s Space Technology 5 (ST5) spacecraft. Current methods of designing and optimizing antennas by hand are time and labor intensive, limit complexity, and require significant expertise and experience. Evolutionary design techniques can overcome these limitations by searching the design space and automatically finding effective solutions that would ordinarily not be found. The ST5 antenna was evolved to meet a challenging set of mission requirements, most notably the combination of wide beamwidth for a circularly-polarized wave and wide bandwidth. Two evolutionary algorithms were used: one used a genetic algorithm style representation that did not allow branching in the antenna arms; the second used a genetic programming style tree-structured representation that allowed branching in the antenna arms. The highest performance antennas from both algorithms were fabricated and tested, and both yielded very similar performance. Both antennas were comparable in performance to a hand-designed antenna produced by the antenna contractor for the mission, and so we consider them examples of human-competitive performance by evolutionary algorithms. As of this writing, one of our evolved antenna prototypes is undergoing flight qualification testing. If successful, the resulting antenna would represent the first evolved hardware in space, and the first deployed evolved antenna.

Evolution of generative design systems for modular physical robots

Recent research has demonstrated the ability for automatic design of the morphology and control of real physical robots using techniques inspired by biological evolution. The main criticism of the evolutionary design approach, however, is that it is doubtful whether it will reach the high complexities necessary for practical engineering. Here we claim that for automatic design systems to scale in complexity the designs they produce must be made of re-used modules. Our approach is based on the use of a generative design grammar subject to an evolutionary process. Unlike a direct encoding of a design, a generative design specification can re-use components, giving it the ability to create more complex modules from simpler ones. Re-used modules are also valuable for improved efficiency in testing and construction. We describe a system for creating generative specifications capable of hierarchical modularity by combining Lindenmayer systems with evolutionary algorithms. Using this system we demonstrate for the first time a generative system for physical, modular, 2D locomoting robots and their controllers.