Distributed Object Modeling Using Object Relations in Dynamic Environments

In this paper we describe how a group of agents can commonly estimate the position of objects. Furthermore we will show how these modeled object positions can be used for an improved self localization. Modeling of moving objects is commonly done by a single agent and in a robo-centric coordinate frame because this information is sufficient for most low level robot control and it is independent of the quality of the current robot localization. Especially when many robots cooperate with each other in a partially observable environment they have to share and to communicate information. For multiple robots to cooperate and to share information, though, they need to agree on a global, allocentric frame of reference. But when transforming the egocentric object model into a global one, it inherits the localization error of the robot in addition to the error associated with the egocentric model. We propose using the relation of objects detected in camera images to other objects in the same camera image as a basis for estimating the position of the object in a global coordinate system. The spacial relation of objects with respect to stationary objects (e.g., landmarks) offers several advantages: The information is independent of robot localization and odometry. It can be easily communicated. We present experimental evidence that shows how two robots are able to infer the position of an object within a global frame of reference, even though they are not localized themselves. We will also show, how to use this object information for self localization. A third aspect of this work will cope with the communication delay therefore we will show, how the Markov Model can be extended for distributed object tracking.