Grounding object perception in a naive agent's sensorimotor experience
This addresses the challenge of developing object perception from scratch in AI, though it appears incremental as it builds on developmental and sensorimotor theories.
The paper tackled the problem of grounding object perception in a naive agent's sensorimotor experience, proposing an algorithm that identifies objects as consistent networks of sensorimotor transitions without prior knowledge, and tested it to illustrate the approach.
Artificial object perception usually relies on a priori defined models and feature extraction algorithms. We study how the concept of object can be grounded in the sensorimotor experience of a naive agent. Without any knowledge about itself or the world it is immersed in, the agent explores its sensorimotor space and identifies objects as consistent networks of sensorimotor transitions, independent from their context. A fundamental drive for prediction is assumed to explain the emergence of such networks from a developmental standpoint. An algorithm is proposed and tested to illustrate the approach.