Grounding the experience of a visual field through sensorimotor contingencies

NEUROCOMPUTING

卷:268

Article

Laflaquiere, Alban¹ 

[1] SoftBank Robot Europe, AI Lab, 43 Rue Col Pierre Avia, F-75015 Paris, France

关键词: Autonomous systems;    Developmental robotics;    Sensorimotor contingencies;    Predictive processing;    Sensorimotor learning;    Human-like vision;   

DOI  :  10.1016/j.neucom.2016.11.085

来源: Elsevier

【 摘 要 】

Artificial perception is traditionally handled by hand-designing task specific algorithms. However, a truly autonomous robot should develop perceptive abilities on its own, by interacting with its environment, and adapting to new situations. The sensorimotor contingencies theory proposes to ground the development of those perceptive abilities in the way the agent can actively transform its sensory inputs. We propose a sensorimotor approach, inspired by this theory, in which the agent explores the world and discovers its properties by capturing the sensorimotor regularities they induce. This work presents an application of this approach to the discovery of a so-called visual field as the set of regularities that a visual sensor imposes on a naive agent's experience. A formalism is proposed to describe how those regularities can be captured in a sensorimotor predictive model. Finally, the approach is evaluated on a simulated system coarsely inspired from the human retina. (C) 2017 Elsevier B.V. All rights reserved.

【 授权许可】

Free