Utility Functions for Human/Robot Interaction

TL;DR

This paper explores a utility-based model for human-robot interaction, focusing on how a robot's decision-making can be governed by a utility aggregation function that incorporates responsibility over its actions.

Contribution

It introduces a novel utility aggregation function that embeds responsibility into the robot's decision-making model, advancing cognitive robot modeling.

Findings

Proposes desiderata for utility aggregation functions

Analyzes properties of utility functions in robot decision-making

Highlights the importance of responsibility in utility models

Abstract

In this paper, we place ourselves in the context of human robot interaction and address the problem of cognitive robot modelling. More precisely we are investigating properties of a utility-based model that will govern a robot's actions. The novelty of this approach lies in embedding the responsibility of the robot over the state of affairs into the utility model via a utility aggregation function. We describe desiderata for such a function and consider related properties.