Mobile Robot Navigation for Person Following in Indoor Environments

Service robotics is a rapidly growing area of interest in robotics research. Service robots inhabit human-populated environments and carry out specific tasks. The goal of this dissertation is to develop a service robot capable of following a human leader around populated indoor environments. A classification system for person followers is proposed such that it clearly defines the expected interaction between the leader and the robotic follower. In populated environments, the robot needs to be able to detect and identify its leader and track the leader through occlusions, a common characteristic of populated spaces. An appearance-based person descriptor, which augments the Kinect skeletal tracker, is developed and its performance in detecting and overcoming short and long-term leader occlusions is demonstrated. While following its leader, the robot has to ensure that it does not collide with stationary and moving obstacles, including other humans, in the environment. This requirement necessitates the use of a systematic navigation algorithm. A modified version of navigation function path planning, called the predictive fields path planner, is developed. This path planner models the motion of obstacles, uses a simplified representation of practical workspaces, and generates bounded, stable control inputs which guide the robot to its desired position without collisions with obstacles. The predictive fields path planner is experimentally verified on a non-person follower system and then integrated into the robot navigation module of the person follower system. To