MOON: Multi-Objective Optimization-Driven Object-Goal Navigation Using a Variable-Horizon Set-Orienteering Planner

TL;DR

This paper introduces MOON, a multi-objective optimization framework for object-goal navigation in complex indoor environments, combining landmark encoding, scalable planning, and a neural planner for efficient, strategic exploration and exploitation.

Contribution

It formulates object-goal navigation as a multi-objective optimization problem with a variable-horizon set-orienteering approach, integrating landmark encoding, scalable planning, and a neural planner.

Findings

Reduces decision latency by nearly 10 times with a neural planner.

Balances exploration and exploitation effectively in large-scale environments.

Provides a theoretical foundation for scalable, budget-constrained planning.

Abstract

This paper proposes MOON (Multi-Objective Optimization-driven Object-goal Navigation), a novel framework designed for efficient navigation in large-scale, complex indoor environments. While existing methods often rely on local heuristics, they frequently fail to address the strategic trade-offs between competing objectives in vast areas. To overcome this, we formulate the task as a multi-objective optimization problem (MOO) that balances frontier-based exploration with the exploitation of observed landmarks. Our prototype integrates three key pillars: (1) QOM [IROS05] for discriminative landmark encoding; (2) StructNav [RSS23] to enhance the navigation pipeline; and (3) a variable-horizon Set Orienteering Problem (SOP) formulation for globally coherent planning. To further support the framework's scalability, we provide a detailed theoretical foundation for the budget-constrained SOP formulation and the data-driven mode-switching strategy that enables long-horizon resource allocation. Additionally, we introduce a high-speed neural planner that distills the expert solver into a transformer-based model, reducing decision latency by a factor of nearly 10 while maintaining high planning quality.