A massively parallel architecture for a self-organizing neural pattern recognition machine
Computer Vision, Graphics, and Image Processing
Minimalist mobile robotics: a colony-style architecture for an artificial creature
Minimalist mobile robotics: a colony-style architecture for an artificial creature
Introduction to the theory of neural computation
Introduction to the theory of neural computation
Automatic programming of behavior-based robots using reinforcement learning
Artificial Intelligence
Seeing the light: artificial evolution, real vision
SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
Robot shaping: developing autonomous agents through learning
Artificial Intelligence
Neural Network Perception for Mobile Robot Guidance
Neural Network Perception for Mobile Robot Guidance
Implementing active vision in embedded systems
M2VIP '97 Proceedings of the 4th Annual Conference on Mechatronics and Machine Vision in Practice
Image Processing, Analysis, and Machine Vision
Image Processing, Analysis, and Machine Vision
Learning reactive and planning rules in a motivationally autonomousanimat
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Evolution of homing navigation in a real mobile robot
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
An incremental approach to developing intelligent neural networkcontrollers for robots
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
| Hi-index | 0.00 |
This paper presents the design, implementation and evaluation of atrainable vision guided mobile robot. The robot, CORGI, has a CCD cameraas its only sensor which it is trained to use for a variety of tasks.The techniques used for training and the choice of natural light visionas the primary sensor makes the methodology immediately applicable totasks such as trash collection or fruit picking. For example, the robotis readily trained to perform a ball finding task which involvesavoiding obstacles and aligning with tennis balls. The robot is able tomove at speeds up to 0.8 ms^-1 while performing this task,and has never had a collision in the trained environment. It can processvideo and update the actuators at 11 Hz using a single $20microprocessor to perform all computation. Further results are shown toevaluate the system for generalization across unseen domains, faulttolerance and dynamic environments.