Distributed visual servoing: a cross-platform agent-based implementation

Visual control tasks demand very fast processing and transfer of huge amounts of data - live video images. Nowadays, computers and communication systems have become powerful enough to allow more flexible implementations of visual control tasks, enlarging the field of application to embrace networked systems, e.g. cooperative robots or mobile manipulators. In such setups, video grabbing, vision processing, and control might be located in different platforms across the network. This paper presents a cross-platform, networked implementation of visual control tasks based on software agents and video streaming technologies. This implementation consists of free, off-the-shelf, software components, resulting in a transparent system whose configuration can be adapted to existing hardware in very different ways, without any modification in the source code. We present several configurations which span onboard and offboard camera setups, and we experimentally determine the control loop delay of a real system, to test the feasibility of the proposed approach.