Natural Landmark Recognition using Neural Networks for Autonomous Vacuuming Robots

Two types of neural networks were trained and tested on a real robot for a natural landmark recognition task. The neural networks investigated were the multilayer perceptron (MLP) and learning vector quantisation (LVQ). The intended application is for autonomous vacuuming robots in completely unknown indoor environments, using a novel topological world model and region filling algorithm. A topological world model based on natural landmarks is built incrementally while the robot systematically cleans the environment. The implementation of this world model depends on robust and accurate recognition of natural landmarks. Both types of neural network were found to be able to successfully recognise the natural landmarks selected.