Autonomous observer: a tool for remote experimentation in robotics

This paper describes a robotics technology - the Autonomous Observer (AO) - developed to facilitate experimentation over the Internet. The AO is a mobile robot equipped with visual sensors. It applies visual tracking and motion planning techniques to track a designated moving object (the target) in an environment cluttered by obstacles and repeatedly measure the target's pose. This pose is sent over the Internet to remote users who can observe 3-D real-time graphic renderings of the target's motion in its environment under individually selected viewpoints. The AO was used to set up an experiment in which a can-collecting robot (playing the role of the target) equipped with a range sensor and a simple arm automatically detects coke cans and collects them in a bag. Observation of the can-collector's behavior through the AO allowed remote experimenters to correct software bugs causing failures on this robot (e.g., colliding with obstacles, missing cans). It is well-known in experimental robotics that direct observation of the performance of a robot is crucial for debugging and tuning the software controlling this robot. The AO has proven to be an adequate (though perfectible) telepresence tool for remote experimenters. Other information, e.g., ambient sound and live videos, can also be transmitted to these users to complement the graphic rendering made possible by the AO. Multiple AO's could be used in the future to observe more complex environments with multiple moving targets. Applications of AO technology are not limited to collaborative experiments. The same basic technologies could benefit other domains as well, such as teleconferencing, surveillance, and interactive TV.

Duke Scholars

Author Carlo Tomasi Computer Science