A Distributed Vision-Based Navigation System for Khepera IV Mobile Robots

This work presents the development and implementation of a distributed navigation system based on object recognition algorithms. The main goal is to introduce advanced algorithms for image processing and artificial intelligence techniques for teaching control of mobile robots. The autonomous system consists of a wheeled mobile robot with an integrated color camera. The robot navigates through a laboratory scenario where the track and several traffic signals must be detected and recognized by using the images acquired with its on-board camera. The images are sent to a computer server that performs a computer vision algorithm to recognize the objects. The computer calculates the corresponding speeds of the robot according to the object detected. The speeds are sent back to the robot, which acts to carry out the corresponding manoeuvre. Three different algorithms have been tested in simulation and a practical mobile robot laboratory. The results show an average of 84% success rate for object recognition in experiments with the real mobile robot platform.

A Distributed Vision-Based Navigation System for Khepera IV Mobile Robots

This work presents the development and implementation of a distributed navigation system based on computer vision. The autonomous system consists of a wheeled mobile robot with an integrated colour camera. The robot navigates through a laboratory scenario where the track and several traffic signals must be detected and recognized by using the images acquired with its on-board camera. The images are sent to a computer server that processes them and calculates the corresponding speeds of the robot using a cascade of trained classifiers. These speeds are sent back to the robot, which acts to carry out the corresponding manoeuvre. The classifier cascade should be trained before experimentation with two sets of positive and negative images. The number of images in these sets should be considered to limit the training stage time and avoid overtraining the system.

From Softimage to Postimage

With the digital revolution, the photographic paradigm of the image has become supplemented with an algorithmic paradigm. The result is a new kind of image capable to gather, compute, merge and display heterogeneous data in real time; no longer a solid representation of a solid world but a softimage—a program-mable database view. In today’s neurosciences and machine vision, the very concept of “image” as a stable visual entity becomes questionable. As a result, the authors propose that the need exists to radically expand the definition of image and abandon its humanist and subjective frame: The posthuman image—which the authors propose to call the postimage—is a collaborative image created through the process of distributed vision involving humans, animals and machines.