Grid-based simultaneous localization and mapping using Rao-blackwellized particle filter with neural network for mini robots / Norhidayah Mohamad Yatim

Mini robots can be used in many applications such as in domestic, industrial or humanitarian fields. Typically, mini robot platforms are equipped with sparse and noisy sensors on board such as array of infrared sensors. In robotics, the ability to map the surrounding area and determine self-location is essential for a robot to be truly autonomous. This research aims to develop such capability known as Simultaneous Localization and Mapping (SLAM) algorithm for mini robots with array of infrared (IR) sensors. Existing methods had implemented either feature-based or occupancy grid map (OG) as map representation. In SLAM with feature-based map, prior knowledge of the environment is required to associate sensor measurements with the right features. OG map representation does not need for landmark identification but described occupancy of an area. In this research, to enable mini robots to operate in various environment, OG map with SLAM or grid-based SLAM algorithm was developed. Previous works in this domain had to assume for all walls in the environment are either parallel or perpendicular to each other.