Robot Navigation Based on an Artificial Somatosensorial System

An artificial somatosensory system processes robot’s perceptions by mean of suitable soft sensors. The robot moves in a real and complex environment, and the physical sensing of it causes a positive or negative reaction. A global wellness function drives the robot’s movements and constitutes a basis to compute the motivation of a cognitive architecture. The paper presents preliminary experimentations and explains the influence of the parameters on the robot behavior and personality. Pepper freely moves in an office environment searching for people to engage. The robot searches for a safe path, avoiding obstacles and aiming to explore a significant part of a known space by an approximative map stored in its long term memory (LTM). The short-term memory (STM) stores somatosensory values related to perceptions considered relevant for the navigation task. The collection of previous navigation experiences allows the robot to memorize on the map places that have positive (or negative) effects on robot’s wellness state. The robot could reach the places labeled as negative, but it needs some positive counter effects to contrast its reluctance.