A Collision Detection System for a Mobile Robot Inspired by the Locust Visual System

Abstract

The lobula giant movement detector (LGMD) is an identified neuron in the locust brain that responds most strongly to the image of an approaching object such as a predator. A computational neural network model based on the structure of the LGMD and its afferent inputs is also able to detect approaching objects. In order for the LGMD network to be used as a robust collision detector for robotic applications, we proposed a new mechanism to enhance the feature of colliding objects before the excitations are gathered by LGMD cell. The new model favours grouped excitation but tends to ignore isolated excitation with selective passing coefficients. Experiments with a Khepera robot showed the proposed collision detector worked in real time in an arena surrounded with blocks.