Skip to yearly menu bar Skip to main content


Poster

Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation

Zihan Wang · Xiangyang Li · Jiahao Yang · Yeqi Liu · Junjie Hu · Ming Jiang · Shuqiang Jiang

Arch 4A-E Poster #397
Highlight Highlight
[ ] [ Project Page ]
[ Poster
Thu 20 Jun 10:30 a.m. PDT — noon PDT

Abstract:

Vision-and-language navigation (VLN) enables the agent to navigate to a remote location following the natural language instruction in 3D environments. At each navigation step, the agent selects from possible candidate locations and then makes the move. For better navigation planning, the lookahead exploration strategy aims to effectively evaluate the agent's next action by accurately anticipating the future environment of candidate locations. To this end, some existing works predict RGB images for future environments, while this strategy suffers from image distortion and high computational cost. To address these issues, we propose the pre-trained hierarchical neural radiance representation model (HNR) to produce multi-level semantic features for future environments, which are more descriptive and efficientthan pixel-wise RGB reconstruction. Furthermore, with the predicted future environmental representations, our lookahead VLN model is able to construct the navigable future path tree and select the optimal path branch via efficient parallel evaluation. Extensive experiments on the VLN-CE datasets confirm the effectiveness of our proposed method.

Chat is not available.