# Grounding Complex Navigational Instructions Using Scene Graphs

arXiv: https://arxiv.org/abs/2106.01607 · HTML: https://mlsanity.com/paper/2106.01607/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 10 references that are in the map.
- First posted on arXiv 3 Jun 2021.

## Builds on (most cited first, 8 of 8)

- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [A Structured Self-attentive Sentence Embedding](https://mlsanity.com/paper/1703.03130/) (2017)
- [ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning](https://mlsanity.com/paper/1605.02097/) (2016)
- [Gated-Attention Architectures for Task-Oriented Language Grounding](https://mlsanity.com/paper/1706.07230/) (2017)
- [Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences](https://mlsanity.com/paper/1506.04089/) (2015)
- [Beating Atari with Natural Language Guided Reinforcement Learning](https://mlsanity.com/paper/1704.05539/) (2017)
- [Understanding Early Word Learning in Situated Artificial Agents](https://mlsanity.com/paper/1710.09867/) (2017)

## Abstract (arXiv)

Training a reinforcement learning agent to carry out natural language instructions is limited by the available supervision, i.e. knowing when the instruction has been carried out. We adapt the CLEVR visual question answering dataset to generate complex natural language navigation instructions and accompanying scene graphs, yielding an environment-agnostic supervised dataset. To demonstrate the use of this data set, we map the scenes to the VizDoom environment and use the architecture in citetgatedattention to train an agent to carry out these more complex language instructions.