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.- Anthology ID:
- 2021.splurobonlp-1.5
- Volume:
- Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Malihe Alikhani, Valts Blukis, Parisa Kordjamshidi, Aishwarya Padmakumar, Hao Tan
- Venue:
- splurobonlp
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 42–52
- Language:
- URL:
- https://aclanthology.org/2021.splurobonlp-1.5
- DOI:
- 10.18653/v1/2021.splurobonlp-1.5
- Cite (ACL):
- Yue Zhang, Quan Guo, and Parisa Kordjamshidi. 2021. Towards Navigation by Reasoning over Spatial Configurations. In Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics, pages 42–52, Online. Association for Computational Linguistics.
- Cite (Informal):
- Towards Navigation by Reasoning over Spatial Configurations (Zhang et al., splurobonlp 2021)
- PDF:
- https://preview.aclanthology.org/landing_page/2021.splurobonlp-1.5.pdf