LOViS: Learning Orientation and Visual Signals for Vision and Language Navigation
This addresses the challenge of improving navigation agents for following natural language instructions, though it is incremental as it builds on existing Transformer-based methods.
The paper tackled the problem of vision and language navigation by designing a neural agent with explicit orientation and vision modules to disentangle spatial and visual information, achieving state-of-the-art results on R2R and R4R datasets.
Understanding spatial and visual information is essential for a navigation agent who follows natural language instructions. The current Transformer-based VLN agents entangle the orientation and vision information, which limits the gain from the learning of each information source. In this paper, we design a neural agent with explicit Orientation and Vision modules. Those modules learn to ground spatial information and landmark mentions in the instructions to the visual environment more effectively. To strengthen the spatial reasoning and visual perception of the agent, we design specific pre-training tasks to feed and better utilize the corresponding modules in our final navigation model. We evaluate our approach on both Room2room (R2R) and Room4room (R4R) datasets and achieve the state of the art results on both benchmarks.