Home »
Academic Articles »
C »
Multilevel Cognitive Machine-Learning-Based Concept for Artificial Awareness: Application to Humanoid Robot Awareness Using Visual Saliency
Multilevel Cognitive Machine-Learning-Based Concept for Artificial Awareness: Application to Humanoid Robot Awareness Using Visual Saliency
Kurosh Madani
(Images, Signals and Intelligence Systems Laboratory (LISSI/EA 3956) and Senart-FB Institute of Technology,
University Paris-EST Créteil (UPEC), Bât.A, avenue Pierre Point, 77127 Lieusaint, France)
Dominik M. Ramik
(Images, Signals and Intelligence Systems Laboratory (LISSI/EA 3956) and Senart-FB Institute of Technology,
University Paris-EST Créteil (UPEC), Bât.A, avenue Pierre Point, 77127 Lieusaint, France)
Cristophe Sabourin
(Images, Signals and Intelligence Systems Laboratory (LISSI/EA 3956) and Senart-FB Institute of Technology,
University Paris-EST Créteil (UPEC), Bât.A, avenue Pierre Point, 77127 Lieusaint, France)
As part of “intelligence,” the “awareness” is the state or ability to perceive, feel, or be mindful of events, objects, or sensory patterns: in other words, to be conscious of the surrounding environment and its interactions. Inspired by early-ages human skills developments and especially by early-ages awareness maturation, the present paper accosts the robots intelligence from a different slant directing the attention to combining both “cognitive” and “perceptual” abilities. Within such a slant, the machine (robot) shrewdness is constructed on the basis of a multilevel cognitive concept attempting to handle complex artificial behaviors. The intended complex behavior is the autonomous discovering of objects by robot exploring an unknown environment: in other words, proffering the robot autonomy and awareness in and about unknown backdrop.