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

Po-Chen Ko, Hung-Ting Su, CY Chen, Jia-Fong Yeh, Min Sun, Winston H. Hsu

Abstract: Pre-explored Semantic Map, constructed through prior exploration using visual language models (VLMs), has proven effective as a foundational element 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. This work introduces 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 additional labels. We demonstrate the effectiveness of our proposed method using two modern map backbones, VLMaps and OpenMask3D, and show significant improvements in performance on object navigation tasks.