`

Timezone: »

 
Poster
Language and Visual Entity Relationship Graph for Agent Navigation
Yicong Hong · Cristian Rodriguez · Yuankai Qi · Qi Wu · Stephen Gould

Mon Dec 07 09:00 PM -- 11:00 PM (PST) @ Poster Session 0 #111

Vision-and-Language Navigation (VLN) requires an agent to navigate in a real-world environment following natural language instructions. From both the textual and visual perspectives, we find that the relationships among the scene, its objects, and directional cues are essential for the agent to interpret complex instructions and correctly perceive the environment. To capture and utilize the relationships, we propose a novel Language and Visual Entity Relationship Graph for modelling the inter-modal relationships between text and vision, and the intra-modal relationships among visual entities. We propose a message passing algorithm for propagating information between language elements and visual entities in the graph, which we then combine to determine the next action to take. Experiments show that by taking advantage of the relationships we are able to improve over state-of-the-art. On the Room-to-Room (R2R) benchmark, our method achieves the new best performance on the test unseen split with success rate weighted by path length of 52%. On the Room-for-Room (R4R) dataset, our method significantly improves the previous best from 13% to 34% on the success weighted by normalized dynamic time warping.

Author Information

Yicong Hong (Australian National University)
Cristian Rodriguez (Australian National University)
Yuankai Qi (University of Adelaide )
Qi Wu (University of Adelaide)
Stephen Gould (ANU)

More from the Same Authors