Online Learning of Reusable Abstract Models for Object Goal Navigation

TL;DR

This paper introduces a method for incrementally learning and reusing abstract environment models to improve object goal navigation performance in unknown environments.

Contribution

It proposes a novel finite state machine-based abstract model that is learned online and reused for navigation tasks, enhancing efficiency and effectiveness.

Findings

Reusing learned models boosts navigation success rates.

The approach outperforms baseline methods on public benchmarks.

Incremental learning adapts to new environments effectively.

Abstract

In this paper, we present a novel approach to incrementally learn an Abstract Model of an unknown environment, and show how an agent can reuse the learned model for tackling the Object Goal Navigation task. The Abstract Model is a finite state machine in which each state is an abstraction of a state of the environment, as perceived by the agent in a certain position and orientation. The perceptions are high-dimensional sensory data (e.g., RGB-D images), and the abstraction is reached by exploiting image segmentation and the Taskonomy model bank. The learning of the Abstract Model is accomplished by executing actions, observing the reached state, and updating the Abstract Model with the acquired information. The learned models are memorized by the agent, and they are reused whenever it recognizes to be in an environment that corresponds to the stored model. We investigate the effectiveness of the proposed approach for the Object Goal Navigation task, relying on public benchmarks. Our results show that the reuse of learned Abstract Models can boost performance on Object Goal Navigation.