Spatial Frames of Reference and Action: A Study with Evolved Neuro-agents

Solving spatial tasks is crucial for adaptation and is made possible by the representation of space. It is still debated which is the exact nature of this representation that can rely on egocentric and allocentric frames of reference. In this paper, a modelling approach is proposed to complement research on humans and animal models. Artificial agents, simulated mobile robots ruled by an artificial neural network, are evolved through Evolutionary strategies to solve a spatial task that consists in locating the central area between 2 landmarks in a rectangular enclosure. This is a non-trivial task that requires the agent to identify landmarks' location, spatial relation between landmarks and landmark position relative to the environment. Different populations of agents with different spatial frames of reference are compared. Results indicate that both egocentric and allocentric frames of reference are effective, but allocentric frames gives advantages and leads to better performance.