Aligning Knowledge Graph with Visual Perception for Object-goal Navigation
This work improves object-goal navigation for AI agents by enhancing scene comprehension, though it is incremental as it builds on existing knowledge-graph methods.
The paper tackles object-goal navigation by addressing misalignment between knowledge graphs and visual perception, proposing AKGVP which uses continuous modeling and visual-language pre-training to achieve zero-shot navigation capability, with evaluation in the AI2-THOR simulator showing effectiveness.
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.