Date of Award
Bachelor of Science
soft robotics, algorithm, genetic algorithm, computation
The ﬁeld of soft robotics is very promising; applications in-clude urban search and rescue and covert surveillance, but these projects are not yet realized, partly because of the diﬃculties in soft robot shape and locomotion design. Be-cause of this, traditional design methods do not prove to be eﬀective. This project attempts to come up with solu-tions to this soft robot design problem; utilizing a genetic algorithm, a computer simulation of Darwin’s “Survival of the Fittest,” this project attempts to make soft bodies move. This genetic algorithm evaluates each solution in simulation, and assigns each one a ﬁtness based on distance travelled. Furthermore, this project implements a technique called co-evolution, which evolves two diﬀerent things in lockstep, uti-lizing new found advancements in one to help bolster the other. This project evolves soft bodies’ physical properties, values that aﬀect how they move, alongside locomotion tech-niques, the gaits deﬁning their movement. Optimizations to this process are realized in the use of scalable soft meshes; this system starts on a simple mesh, and slowly increases its density, reducing the overall computation time.
Knox, Davis K., "Scalable Co-Evolution of Soft Robot Properties and Gaits" (2011). Honors Theses. 1008.