Tracking and Following Algorithms of Mobile Robots for Service Activities in Dynamic Environments

Abstract

By providing the capability of following a human target in an appropriate manner, the robot can assist people in various ways under different environments. One of the main difficulties when performing human tracking and following is the occlusion problem caused by static as well as dynamic obstacles. The aim of the paper is to tackle the occlusion problem by planning a robotic trajectory of maximizing target visibility and following the moving target. Initially, a laser range finder is used to detect the human target and then robustly track the target using the Kalman filter. Afterward, a human following algorithm based on a look-ahead algorithm, DWA*, is implemented to pursue the target while avoiding any static or dynamic obstacles. Fundamental experiments have been extensively tested to evaluate robot maneuvers and several field tests are conducted in more complex environments such as student cafeteria, computer center, and university library.

Keywords

• Human following, path planning, dynamic window approach, detecting and tracking moving object.