Learning Human Preferences Over Robot Behavior as Soft Planning Constraints

TL;DR

This paper introduces a planning-based approach to learning human preferences in robot behavior, distinguishing between required and desired actions, and demonstrates its effectiveness in simulated rearrangement tasks.

Contribution

It proposes a novel formulation encoding preferences as soft planning constraints and a data-driven method for inferring these preferences through user queries.

Findings

Effective inference of preferences under noisy user choices

Successful application in simulated rearrangement tasks

Potential for adaptable planning-based robot behavior

Abstract

Preference learning has long been studied in Human-Robot Interaction (HRI) in order to adapt robot behavior to specific user needs and desires. Typically, human preferences are modeled as a scalar function; however, such a formulation confounds critical considerations on how the robot should behave for a given task, with desired -- but not required -- robot behavior. In this work, we distinguish between such required and desired robot behavior by leveraging a planning framework. Specifically, we propose a novel problem formulation for preference learning in HRI where various types of human preferences are encoded as soft planning constraints. Then, we explore a data-driven method to enable a robot to infer preferences by querying users, which we instantiate in rearrangement tasks in the Habitat 2.0 simulator. We show that the proposed approach is promising at inferring three types of preferences even under varying levels of noise in simulated user choices between potential robot behaviors. Our contributions open up doors to adaptable planning-based robot behavior in the future.