Context-Aware Replanning with Pre-explored Semantic Map for Object Navigation

TL;DR

This paper introduces CARe, a method that improves object navigation by estimating map uncertainty and revising decisions without extra labels, enhancing performance with existing mapping backbones.

Contribution

The paper presents CARe, a novel approach for map uncertainty estimation and decision revision in semantic mapping, applicable to training-free robotic navigation.

Findings

Significant performance improvements in object navigation tasks.

Effective map uncertainty estimation through confidence scores and multi-view consistency.

Compatibility with VLMaps and OpenMask3D backbones.

Abstract

Pre-explored Semantic Maps, constructed through prior exploration using visual language models (VLMs), have proven effective as foundational elements for training-free robotic applications. However, existing approaches assume the map's accuracy and do not provide effective mechanisms for revising decisions based on incorrect maps. To address this, we introduce Context-Aware Replanning (CARe), which estimates map uncertainty through confidence scores and multi-view consistency, enabling the agent to revise erroneous decisions stemming from inaccurate maps without requiring additional labels. We demonstrate the effectiveness of our proposed method by integrating it with two modern mapping backbones, VLMaps and OpenMask3D, and observe significant performance improvements in object navigation tasks. More details can be found on the project page: https://care-maps.github.io/