Coevolution of the Asymmetric Morphology and the Behaviour of Simple Predator Agents in Predator-Prey Pursuit Problem.

Abstract

Humanity has long strived to create microscopic machines for various purposes. Most prominent of them employ nanorobots for medical purposes and procedures, otherwise deemed hard or impossible to perform. However, the main advantage of this kind of machines is also their main drawback—their small size. The miniature scale, they work in, brings many problems, such as not having enough space for the computational power needed for their operation or the specifics of the laws of physics that govern their behaviour. In our study, we focus on the former challenge, by introducing a new standpoint to the well-studied predator-prey pursuit problem using an implementation of very simple predator agents. Intended to model the small-scale (micro and nano) robots, these agents are morphologically simple—they feature a single line-of-sight sensor. The behaviour of the predator agents is simple as well—the (few) perceived environmental variables are mapped directly into corresponding pairs of rotational velocities of the wheels' motors. We implemented genetic algorithm to evolve such a mapping that results in a successful capturing of the prey by the team of predator agents. However, as the preliminary results indicated, the predators that use a straightforward sensor could not resolve more than just few of the tested initial situations. Thus, to improve the generality of the evolved behaviour, we proposed an asymmetric sensory morphology of predators—an angular offset to the sensor relative to the longitudinal axis—and coevolved the amount of such an offset together with the behaviour of predators. The behaviours, coevolved with a sensor offset between 12° and 38°, resulted in both an efficient and consistent capture of the prey in all tested initial situations. Moreover, some of the behaviours, coevolved with sensor offset between 18° and 24°, demonstrated a good generality to the increased speed of the prey and a good robustness to perception noise. The obtained results could be seen as a step towards the engineering of asymmetric small-scale for delivery of medicine, locating and destroying cancer cells, microscopic imaging, etc.