Towards Navigation by Reasoning over Spatial Configurations

Abstract

We deal with the navigation problem where the agent follows natural language instructions while observing the environment. Focusing on language understanding, we show the importance of spatial semantics in grounding navigation instructions into visual perceptions. We propose a neural agent that uses the elements of spatial configurations and investigate their influence on the navigation agent's reasoning ability. Moreover, we model the sequential execution order and align visual objects with spatial configurations in the instruction. Our neural agent improves strong baselines on the seen environments and shows competitive performance on the unseen environments. Additionally, the experimental results demonstrate that explicit modeling of spatial semantic elements in the instructions can improve the grounding and spatial reasoning of the model.

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
• Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences
• Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents
• From Spatial Relations to Spatial Configurations
• Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following