Exploring Machine Learning Techniques for Identification of Cues for Robot Navigation with a LIDAR Scanner

In this paper, we report on our explorations of machine learning techniques based on backpropagation neural networks and support vector machines in building a cue identifier for mobile robot navigation using a LIDAR scanner. We use synthetic 2D laser data to identify a technique that is most promising for actual implementation in a robot, and then validate the model using realistic data. While we explore data preprocessing applicable to machine learning, we do not apply any specific extraction of features from the raw data; instead, our feature vectors are the raw data. Each LIDAR scan represents a sequence of values for measurements taken from progressive scans (with angles vary from 0 degrees to 180 degrees); i.e., a curve plotting distances as a functions of angles. Such curves are different for each cue, and so can be the basis for identification. We apply varied grades of noise to the ideal scanner measurement to test the capability of the generated models to accommodate for both laser inaccuracy and robot motion. Our results indicate that good models can be built with both back-propagation neural network applying Broyden-Fletcher-Goldfarb-Shannon (BFGS) optimization, and with Support Vector Machines (SVM) assuming that data shaping took place with a [-0.5, 0.5] normalization followed by a principal component analysis (PCA). Furthermore, we show that SVM can create models much faster and more resilient to noise, so that is what we will be using in our further research and can recommend for similar applications.