My thesis topic involves the sharing of knowledge and experiences among heterogeneous robots with differing perceptual and motor capabilities.
I am currently looking at multi-robot tasks such as joint mapping and tracking of objects in an outdoor environment as well as search and rescue. We use information theoretic metrics to enable two heterogeneous robots (with some overlap) to effectively communicate. Publications on these are coming soon!
Mapping Grounded Object Properties across Perceptually Heterogeneous Embodiments
In the first paper involving building of models of robot differences, we have shown that confusion matrices, describing mappings between various object properties (such as color and texture), can be learned using instances from each robot in a shared context. These models describe which properties represent similar object properties across different robots, and can subsequently be used to faciliate knowledge sharing.
The Role of Shared Context
As an initial step towards the overall goal, the first paper published involves proposing to leverage similarity to deal with heterogeneity. Specifically, we show how establishing a physically shared context can be used to learn models of the differences between two robots. This is similar to the joint attention or gaze following subfields, but in this case the purpose is to ensure a shared context in order to figure out perception differences arising from robot heterogeneity. In the paper, we analyzed the cost and accuracy of several methods for the establishment of the physically shared context with respect to such modeling. We will apply these methods to use information-theoretic measures developed during the candidacy proposal to determine what perceptual differences and similarities exist between two robots.