Smart Walker V: Implementation of RTAB-Map Algorithm

Abstract

Autonomous Navigation has been a field of major attraction to a large number of robotics enthusiasts all around the globe. Smart walker, a robot designed for assisting patients under intensive care, requires this exceptional add-on in order to have a better sense of the surrounding, captured through the RGB and depth sensor available on board. This paper addresses the navigation and mapping problem through a graph-based SLAM technique knows as Real-Time Appearance-based Mapping (RTAB-Map), which uses an interesting approach to map an area with the help of loop closures, and provides a number of visual feature tracking methods that can be used to detect the loop closures. The software stack on the Smart Walker has been built around ROS (Robot Operating System), and the necessary sensor, odometry and transformation messages have been configured accordingly, based on the onboard sensors and actuators attached to the Smart Walker. This paper discusses the implementation of RTAB-Map algorithm on the Smart Walker and steps involved in collecting a custom dataset. The approach also involves comparing the performance of visual feature tracking methods available in RTAB-Map algorithm on a standard dataset and on the custom dataset, based on non-statistical aspects in order to implement the right set of features for indoor use of the Smart Walker.