Towards Preference Learning for Autonomous Ground Robot Navigation Tasks

TL;DR

This paper explores a novel approach combining reinforcement learning, motion planning, and natural language processing to enable autonomous ground robots to learn user preferences through ongoing dialogue for improved navigation behaviors.

Contribution

It introduces a new method that allows robots to adapt navigation behaviors based on user preferences learned via preference-based reinforcement learning and natural language interaction.

Findings

Integrates reinforcement learning with natural language processing for personalized navigation.

Enables robots to learn user preferences through sustained dialogue.

Proposes a framework for user-specific behavior adaptation in autonomous navigation.

Abstract

We are interested in the design of autonomous robot behaviors that learn the preferences of users over continued interactions, with the goal of efficiently executing navigation behaviors in a way that the user expects. In this paper, we discuss our work in progress to modify a general model for robot navigation behaviors in an exploration task on a per-user basis using preference-based reinforcement learning. The novel contribution of this approach is that it combines reinforcement learning, motion planning, and natural language processing to allow an autonomous agent to learn from sustained dialogue with a human teammate as opposed to one-off instructions.