MO-DDN: A Coarse-to-Fine Attribute-based Exploration Agent for Multi-object Demand-driven Navigation

TL;DR

This paper introduces MO-DDN, a new benchmark for multi-object demand-driven navigation that considers human-like preferences and multi-object searches, and proposes a modular coarse-to-fine exploration agent that outperforms baselines.

Contribution

The paper presents MO-DDN, a benchmark for realistic multi-object demand-driven navigation, and a novel coarse-to-fine attribute-based exploration method for improved performance.

Findings

The proposed C2FAgent outperforms baseline methods.

Multi-object and preference considerations make MO-DDN more realistic.

Coarse-to-fine strategy enhances decision-making at different levels.

Abstract

The process of satisfying daily demands is a fundamental aspect of humans' daily lives. With the advancement of embodied AI, robots are increasingly capable of satisfying human demands. Demand-driven navigation (DDN) is a task in which an agent must locate an object to satisfy a specified demand instruction, such as ``I am thirsty.'' The previous study typically assumes that each demand instruction requires only one object to be fulfilled and does not consider individual preferences. However, the realistic human demand may involve multiple objects. In this paper, we introduce the Multi-object Demand-driven Navigation (MO-DDN) benchmark, which addresses these nuanced aspects, including multi-object search and personal preferences, thus making the MO-DDN task more reflective of real-life scenarios compared to DDN. Building upon previous work, we employ the concept of ``attribute'' to tackle this new task. However, instead of solely relying on attribute features in an end-to-end manner like DDN, we propose a modular method that involves constructing a coarse-to-fine attribute-based exploration agent (C2FAgent). Our experimental results illustrate that this coarse-to-fine exploration strategy capitalizes on the advantages of attributes at various decision-making levels, resulting in superior performance compared to baseline methods. Code and video can be found at https://sites.google.com/view/moddn.