Aligning Knowledge Graph with Visual Perception for Object-goal Navigation

TL;DR

This paper introduces AKGVP, a novel method that aligns knowledge graphs with visual perception to improve object-goal navigation, achieving better scene understanding and zero-shot capabilities in simulated environments.

Contribution

It proposes a continuous knowledge graph architecture combined with visual-language pre-training to address misalignment issues in scene representation for navigation.

Findings

Enhanced scene understanding through continuous knowledge graphs.

Improved zero-shot navigation performance.

Effective in AI2-THOR simulation environment.

Abstract

Object-goal navigation is a challenging task that requires guiding an agent to specific objects based on first-person visual observations. The ability of agent to comprehend its surroundings plays a crucial role in achieving successful object finding. However, existing knowledge-graph-based navigators often rely on discrete categorical one-hot vectors and vote counting strategy to construct graph representation of the scenes, which results in misalignment with visual images. To provide more accurate and coherent scene descriptions and address this misalignment issue, we propose the Aligning Knowledge Graph with Visual Perception (AKGVP) method for object-goal navigation. Technically, our approach introduces continuous modeling of the hierarchical scene architecture and leverages visual-language pre-training to align natural language description with visual perception. The integration of a continuous knowledge graph architecture and multimodal feature alignment empowers the navigator with a remarkable zero-shot navigation capability. We extensively evaluate our method using the AI2-THOR simulator and conduct a series of experiments to demonstrate the effectiveness and efficiency of our navigator. Code available: https://github.com/nuoxu/AKGVP.