Exploring the Reliability of Foundation Model-Based Frontier Selection in Zero-Shot Object Goal Navigation

TL;DR

This paper introduces a new multi-expert decision framework for reliable frontier selection in zero-shot object goal navigation, improving robotic indoor navigation by enhancing reasoning and decision accuracy.

Contribution

The paper proposes Diversified Expert Frontier Analysis and Consensus Decision Making to improve foundation model-based navigation decisions in zero-shot scenarios.

Findings

Achieves state-of-the-art results on RoboTHOR and HM3D datasets.

Outperforms baseline methods in navigating to untrained objects.

Demonstrates robustness and adaptability in dynamic environments.

Abstract

In this paper, we present a novel method for reliable frontier selection in Zero-Shot Object Goal Navigation (ZS-OGN), enhancing robotic navigation systems with foundation models to improve commonsense reasoning in indoor environments. Our approach introduces a multi-expert decision framework to address the nonsensical or irrelevant reasoning often seen in foundation model-based systems. The method comprises two key components: Diversified Expert Frontier Analysis (DEFA) and Consensus Decision Making (CDM). DEFA utilizes three expert models: furniture arrangement, room type analysis, and visual scene reasoning, while CDM aggregates their outputs, prioritizing unanimous or majority consensus for more reliable decisions. Demonstrating state-of-the-art performance on the RoboTHOR and HM3D datasets, our method excels at navigating towards untrained objects or goals and outperforms various baselines, showcasing its adaptability to dynamic real-world conditions and superior generalization capabilities.