Aligning Robot Navigation Behaviors with Human Intentions and Preferences

TL;DR

This paper presents new machine learning methods for mobile robots to learn navigation behaviors that align with human intentions and preferences, addressing the value misalignment problem in autonomous navigation.

Contribution

It introduces a novel imitation learning approach with a new objective function, terrain-aware algorithms for off-road navigation, and a dataset for socially compliant navigation in human environments.

Findings

Robots can imitate human navigation intentions effectively.

Terrain-aware algorithms improve off-road navigation in novel terrains.

The dataset enables development of socially compliant navigation algorithms.

Abstract

Recent advances in the field of machine learning have led to new ways for mobile robots to acquire advanced navigational capabilities. However, these learning-based methods raise the possibility that learned navigation behaviors may not align with the intentions and preferences of people, a problem known as value misalignment. To mitigate this risk, this dissertation aims to answer the question: "How can we use machine learning methods to align the navigational behaviors of autonomous mobile robots with human intentions and preferences?" First, this dissertation addresses this question by introducing a new approach to learning navigation behaviors by imitating human-provided demonstrations of the intended navigation task. This contribution allows mobile robots to acquire autonomous visual navigation capabilities through imitation, using a novel objective function that encourages the agent to align with the human's navigation objectives and penalizes misalignment. Second, this dissertation introduces two algorithms to enhance terrain-aware off-road navigation for mobile robots by learning visual terrain awareness in a self-supervised manner. This contribution enables mobile robots to respect a human operator's preferences for navigating different terrains in urban outdoor environments, while extrapolating these preferences to visually novel terrains by leveraging multi-modal representations. Finally, in the context of robot navigation in human-occupied environments, this dissertation introduces a dataset and an algorithm for robot navigation in a socially compliant manner in both indoor and outdoor environments. In summary, the contributions in this dissertation take significant steps toward addressing the value alignment problem in autonomous navigation, enabling mobile robots to navigate autonomously with objectives that align with human intentions and preferences.