Mobile Robots Navigation in Indoor Environments Using Kinect Sensor

TLDR

The system is composed of two parts and represents the environment as a graph-based topological map. The paper develops a perception system enabling autonomous navigation of surveillance mobile robots in indoor environments. The system combines a Kinect-based reactive obstacle‑avoidance module with an ANN trained on Kinect data to recognize environmental configurations, enabling topological navigation that merges reactive avoidance and deliberative localization, and was evaluated on a Pioneer P3‑AT robot. The system functions effectively in darkness and demonstrates promise for autonomous mobile robot navigation.

Abstract

This paper presents the development of a perception system for indoor environments to allow autonomous navigation for surveillance mobile robots. The system is composed by two parts. The first part is a reactive navigation system in which a mobile robot moves avoiding obstacles in environment, using the distance sensor Kinect. The second part of this system uses a artificial neural network (ANN) to recognize different configurations of the environment, for example, path ahead, left path, right path and intersections. The ANN is trained using data captured by the Kinect sensor in indoor environments. This way, the robot becomes able to perform a topological navigation combining internal reactive behavior to avoid obstacles and the ANN to locate the robot in the environment, in a deliberative behavior. The topological map is represented by a graph which represents the configuration of the environment, where the hallways (path ahead) are the edges and locations (left path and intersection, for example) are the vertices. The system also works in the dark, which is a great advantage for surveillance systems. The experiments were performed with a Pioneer P3-AT robot equipped with a Kinect sensor in order to validate and evaluate this approach. The proposed method demonstrated to be a promising approach to autonomous mobile robots navigation.