The Application of Augmented Reality

Developing mobile robot applications in a real world environment presents a number of challenges. The challenges are a result of the researcher developing the application often being remote from the robot, real environments are dynamic and the information provided by sensors can not be interpreted easily in real time with classical techniques. AR (Augmented Reality) provides a means to solve many of these problems placing the sensor data geographically with the robot in real time and the associated physical surrounding.

The application domains for AR are diverse and ranging from medical displays, to entertainment, to treating psychological disorders. AR has been used in to aid an operator when maneuvering a vehicle in limited or no visibility. The design of the AR system is presented discussing hardware and integration of a near scene map building algorithm. An AR system is used to aid in commissioning helicopter tasks for agriculture. Their work focusing in tracking the camera pose using natural features as markers, with results given from a mock up simulation.

It is generally agreed that it is the developer’s lack of understanding of the robot’s world view that makes it difficult to code new tasks and algorithms, debug problems in the resulting actions and commission integrated systems for real world work. The problem of understanding can be overcome with a shared perceptual space. AR provides this shared space between robots and developers enabling the developer to view he world through the robots sensors.

The ARDev (Augmented Reality Visualization Project), originally created in 2006, was designed to allow visual debugging of robot data. ARDev integrates with the open source player project, providing intuitive visualizations of player robot data. The integration into the player projects makes ARDev very accessible with easy access to existing sensors through the generic player interfaces. The AR visualization used in ARDev provides developers with a clear, visual representation of robot data, and can be used by the researcher to detect problems between the real world and the robot.