CON: Continual Object Navigation via Data-Free Inter-Agent Knowledge Transfer in Unseen and Unfamiliar Places

TL;DR

This paper introduces a data-free, inter-agent knowledge transfer framework for robotic object navigation in unfamiliar environments, using minimal communication and a query-based occupancy map to improve navigation performance.

Contribution

It proposes a novel, lightweight knowledge transfer module enabling non-cooperative black-box robots to share object navigation knowledge without data sharing or retraining.

Findings

Effective in unseen environments

Outperforms baseline methods

Validates in Habitat environment

Abstract

This work explores the potential of brief inter-agent knowledge transfer (KT) to enhance the robotic object goal navigation (ON) in unseen and unfamiliar environments. Drawing on the analogy of human travelers acquiring local knowledge, we propose a framework in which a traveler robot (student) communicates with local robots (teachers) to obtain ON knowledge through minimal interactions. We frame this process as a data-free continual learning (CL) challenge, aiming to transfer knowledge from a black-box model (teacher) to a new model (student). In contrast to approaches like zero-shot ON using large language models (LLMs), which utilize inherently communication-friendly natural language for knowledge representation, the other two major ON approaches -- frontier-driven methods using object feature maps and learning-based ON using neural state-action maps -- present complex challenges where data-free KT remains largely uncharted. To address this gap, we propose a lightweight, plug-and-play KT module targeting non-cooperative black-box teachers in open-world settings. Using the universal assumption that every teacher robot has vision and mobility capabilities, we define state-action history as the primary knowledge base. Our formulation leads to the development of a query-based occupancy map that dynamically represents target object locations, serving as an effective and communication-friendly knowledge representation. We validate the effectiveness of our method through experiments conducted in the Habitat environment.