Real World Morphological Evolution is Feasible

TL;DR

This paper demonstrates that real-world morphological evolution of robots is feasible by using a shape-shifting quadruped robot to co-evolve control and morphology directly in the physical environment, overcoming limitations of virtual simulations.

Contribution

It introduces a practical method for evolving robot morphology and control in real-world settings, showcasing the potential for adaptive physical robots.

Findings

Real-world evolution of robot morphology is achievable.

The shape-shifting quadruped successfully co-evolved control and structure.

Evolution exploits dynamic morphology through physical experiments.

Abstract

Evolutionary algorithms offer great promise for the automatic design of robot bodies, tailoring them to specific environments or tasks. Most research is done on simplified models or virtual robots in physics simulators, which do not capture the natural noise and richness of the real world. Very few of these virtual robots are built as physical robots, and the few that are will rarely be further improved in the actual environment they operate in, limiting the effectiveness of the automatic design process. We utilize our shape-shifting quadruped robot, which allows us to optimize the design in its real-world environment. The robot is able to change the length of its legs during operation, and is robust enough for complex experiments and tasks. We have co-evolved control and morphology in several different scenarios, and have seen that the algorithm is able to exploit the dynamic morphology solely through real-world experiments.