# Enabling Robots to Communicate their Objectives

## TL;DR

This paper proposes a method for robots to select behaviors that help humans quickly understand their objectives, by modeling how humans infer goals from observed actions, and demonstrates its effectiveness in autonomous driving scenarios.

## Contribution

The work introduces models of human inference for robot behavior selection, improving human understanding of robot objectives in novel situations.

## Key findings

- Certain inference models enable robots to produce more informative behaviors.
- User study shows improved human anticipation of robot actions.
- Further research needed on human extrapolation from robot behaviors.

## Abstract

The overarching goal of this work is to efficiently enable end-users to correctly anticipate a robot's behavior in novel situations. Since a robot's behavior is often a direct result of its underlying objective function, our insight is that end-users need to have an accurate mental model of this objective function in order to understand and predict what the robot will do. While people naturally develop such a mental model over time through observing the robot act, this familiarization process may be lengthy. Our approach reduces this time by having the robot model how people infer objectives from observed behavior, and then it selects those behaviors that are maximally informative. The problem of computing a posterior over objectives from observed behavior is known as Inverse Reinforcement Learning (IRL), and has been applied to robots learning human objectives. We consider the problem where the roles of human and robot are swapped. Our main contribution is to recognize that unlike robots, humans will not be exact in their IRL inference. We thus introduce two factors to define candidate approximate-inference models for human learning in this setting, and analyze them in a user study in the autonomous driving domain. We show that certain approximate-inference models lead to the robot generating example behaviors that better enable users to anticipate what it will do in novel situations. Our results also suggest, however, that additional research is needed in modeling how humans extrapolate from examples of robot behavior.