ON as ALC: Active Loop Closing Object Goal Navigation

TL;DR

This paper introduces ALCON, a novel approach combining active loop closing and object goal navigation to improve long-distance autonomous navigation without relying on prior maps.

Contribution

It pioneers the integration of mapless object goal navigation with active loop closing, extending existing methods to enhance long-distance autonomous navigation.

Findings

Extended a mapless ON planner with prior map utilization

Maximized ALC performance by minimizing ALC and ON losses

Proposed ALCON to accelerate long-distance ALC technology

Abstract

In simultaneous localization and mapping, active loop closing (ALC) is an active vision problem that aims to visually guide a robot to maximize the chances of revisiting previously visited points, thereby resetting the drift errors accumulated in the incrementally built map during travel. However, current mainstream navigation strategies that leverage such incomplete maps as workspace prior knowledge often fail in modern long-term autonomy long-distance travel scenarios where map accumulation errors become significant. To address these limitations of map-based navigation, this paper is the first to explore mapless navigation in the embodied AI field, in particular, to utilize object-goal navigation (commonly abbreviated as ON, ObjNav, or OGN) techniques that efficiently explore target objects without using such a prior map. Specifically, in this work, we start from an off-the-shelf mapless ON planner, extend it to utilize a prior map, and further show that the performance in long-distance ALC (LD-ALC) can be maximized by minimizing ``ALC loss" and ``ON loss". This study highlights a simple and effective approach, called ALC-ON (ALCON), to accelerate the progress of challenging long-distance ALC technology by leveraging the growing frontier-guided, data-driven, and LLM-guided ON technologies.