Specialization of perceptual processes
Specialization of perceptual processes
PADO: a new learning architecture for object recognition
Symbolic visual learning
Blurred Vision: Simulation-Reality Transfer of a Visually Guided Robot
Proceedings of the First European Workshop on Evolutionary Robotics
Appearance-Based Obstacle Detection with Monocular Color Vision
Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
Genetic programming for robot vision
ICSAB Proceedings of the seventh international conference on simulation of adaptive behavior on From animals to animats
Exploring artificial intelligence in the new millennium
Evolving Visual Features and Detectors
SIBGRAPHI '98 Proceedings of the International Symposium on Computer Graphics, Image Processing, and Vision
Visual Routine for Eye Detection Using Hybrid Genetic Architectures
ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276 - Volume 7276
The simulated evolution of robot perception
The simulated evolution of robot perception
Using learning to facilitate the evolution of features for recognizing visual concepts
Evolutionary Computation
Proceedings of the 10th annual conference on Genetic and evolutionary computation
Evolving Vision Controllers with a Two-Phase Genetic Programming System Using Imitation
SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Visual Navigation for Mobile Robots: A Survey
Journal of Intelligent and Robotic Systems
Dynamic population variation in genetic programming
Information Sciences: an International Journal
Automatic design of vision-based obstacle avoidance controllers using genetic programming
EA'07 Proceedings of the Evolution artificielle, 8th international conference on Artificial evolution
Hi-index | 0.00 |
To recover depth from images, the human visual system uses many monocular depth cues, which vision research has only begun to explore. Because a given image can have many possible interpretations, constraints are needed to eliminate ambiguity, and the most powerful constraints are domain specific. As an experiment in the automatic discovery and exploitation of constraints, genetic programming was used to find algorithms for obstacle detection. The algorithms are designed to be a replacement for sonar, returning the location of the nearest obstacle in a given direction. The evolved algorithms worked surprisingly well. Errors were largely transient. The algorithms generalized to both novel views of the office environment and to unseen obstacles. They were combined with a simple reactive wandering program originally written for sonar. The result exhibited good performance in an office environment, colliding only with obstacles outside the robot's field of view. Time to collision results and failure modes are presented. Code is available for download.