Using assembly representations to enable evolutionary design of Lego structures

Abstract

This paper presents an approach to the automatic generation of electromechanical engineering designs. We apply messy genetic algorithm~GA! optimization techniques to the evolution of assemblies composed of Lego TM structures. Each design is represented as a labeled assembly graph and is evaluated based on a set of behavior and structural equations. The initial populations are generated at random, and design candidates for subsequent generations are produced by user-specified selection techniques. Crossovers are applied by using cut and splice operators at the random points of the chromosomes; random mutations are applied to modify the graph with a certain low probability. This cycle continues until a suitable design is found. The research contributions in this work include the development of a new GA encoding scheme for mechanical assemblies~Legos!, as well as the creation of selection criteria for this domain. Our eventual goal is to introduce a simulation of electromechanical devices into our evaluation functions. We believe that this research creates a foundation for future work and it will apply GA techniques to the evolution of more complex and realistic electromechanical structures.

Finding an Optimal LEGO® Brick Layout of Voxelized 3D Object Using a Genetic Algorithm

“…Peysakhov et al [9,10] used a messy genetic algorithm to evolve assemblies of the bricks in order to obtain complex and realistic electromechanical structures. Mueller et al [6] used a 3D printer to print the bricks and used the layout in prototyping of an object.…”

Security impact assessment of industrial automation systems using genetic algorithm and simulation

“…A chromosome, a potential solution to the problem, is encoded to a string, with strings consisting of binary characters being a popular choice due to computational efficiency [31]. However, when the encoding must capture a design, more complex data structures are needed [32,33], and constraints may be necessary to prevent the GA from producing chromosomes that do not represent feasible products [34].…”

Robustness and the Halting Problem for Multicellular Artificial Ontogeny

“…While originally used for simulating artificial plant development, evolvable L-systems or, more generally, grammar-based developmental systems, have been applied in the seminal work of Karl Sims to evolve the morphologies of artificial creatures [74], work that had some recent followers [59], [51], [48]. Other application regard Lego structures [68], [69], table design [38], robot design [40], antennae design [55] (as a follow-up to [56]) and architecture form generation by combining a variation of L-system with Grammatical Evolution [65].…”