Learning Local Receptive Fields and their Weight Sharing Scheme on Graphs

We propose a simple and generic layer formulation that extends the properties of convolutional layers to any domain that can be described by a graph. Namely, we use the support of its adjacency matrix to design learnable weight sharing filters able to exploit the underlying structure of signals in the same fashion as for images. The proposed formulation makes it possible to learn the weights of the filter as well as a scheme that controls how they are shared across the graph. We perform validation experiments with image datasets and show that these filters offer performances comparable with convolutional ones.

Cooperative interface of a swarm of UAVs

After presenting the broad context of authority sharing, we outline how introducing more natural interaction in the design of the ground operator interface of UV systems should help in allowing a single operator to manage the complexity of his/her task. Introducing new modalities is one one of the means in the realization of our vision of next- generation GOI. A more fundamental aspect resides in the interaction manager which should help balance the workload of the operator between mission and interaction, notably by applying a multi-strategy approach to generation and interpretation. We intend to apply these principles to the context of the Smaart prototype, and in this perspective, we illustrate how to characterize the workload associated with a particular operational situation.

Collaborative model of interaction and Unmanned Vehicle Systems' interface

The interface for the next generation of Unmanned Vehicle Systems should be an interface with multi-modal displays and input controls. Then, the role of the interface will not be restricted to be a support of the interactions between the ground operator and vehicles. Interface must take part in the interaction management too. In this paper, we show that recent works in pragmatics and philosophy provide a suitable theoretical framework for the next generation of UV System's interface. We concentrate on two main aspects of the collaborative model of interaction based on acceptance: multi-strategy approach for communicative act generation and interpretation and communicative alignment.