| Summary: | It is desirable in many applications that a mobile robot is able to track and follow a person. There have been various efforts in literature to create person-tracking robots. However, current person-tracking robots are not capable of operating in unstructured environments. The problem of creating a person-tracking mobile robot has been studied by many researchers in literature. There are two main issues associated with this problem. The first issue is to equip a robot with proper sensory devices so that it is able to identify and locate the target person in a crowd in real time. Various approaches have been investigated, including vision, infrared sensors, ultrasonic sensors, and other approaches. The second issue is to control and navigate the robot so that it follows the target person within a certain distance. This seems to be simple, but in reality it is a fairly difficult task. For example, if the target person is in a busy corridor with many people standing and walking, the robot has to constantly avoid other people while following the target. There is still no reported evidence that a person-tracking robot has been implemented that is able to track a person in arbitrary environmental conditions. In this research, by using an innovative RF/ultrasonic sensor system, an intelligent person-tracking mobile robot is to be implemented that is able to follow the target person in unstructured, practical environments. The main focus of the thesis is development and implementation of control algorithms.
|
|---|
