Developer oriented visualisation of a robot program

摘要

Robot programmers are faced with the challenging problem of understanding the robot's view of its world, both when creating and when debugging robot software. As a result tools are created as needed in different laboratories for different robots and different applications. We discuss the requirements for effective interaction under these conditions, and propose an augmented reality approach to visualising robot input, output and state information, including geometric data such as laser range scans, temporal data such as the past robot path, conditional data such as possible future robot paths, and statistical data such as localisation distributions. The visualisation techniques must scale appropriately as robot data and complexity increases. Our current progress in developing a robot visualisation toolkit is presented.