From Seeing to Moving: A Survey on Learning for Visual Indoor Navigation (VIN)
arXiv:2002.11310
Abstract
Visual Indoor Navigation (VIN) task has drawn increasing attention from the data-driven machine learning communities especially with the recently reported success from learning-based methods. Due to the innate complexity of this task, researchers have tried approaching the problem from a variety of different angles, the full scope of which has not yet been captured within an overarching report. This survey first summarizes the representative work of learning-based approaches for the VIN task and then identifies and discusses lingering issues impeding the VIN performance, as well as motivates future research in these key areas worth exploring for the community.
References in corpus (18)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Learning to Navigate in Complex Environments
- AI2-THOR: An Interactive 3D Environment for Visual AI
- Building Generalizable Agents with a Realistic and Rich 3D Environment
- Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?
- Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
- ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects
- Assessing Generalization in Deep Reinforcement Learning
- Learning to Learn: Meta-Critic Networks for Sample Efficient Learning
- Unifying Map and Landmark Based Representations for Visual Navigation
- MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation
- Improving Target-driven Visual Navigation with Attention on 3D Spatial Relationships
- Language and Visual Entity Relationship Graph for Agent Navigation
- Situational Fusion of Visual Representation for Visual Navigation
- Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks
- What Should I Do Now? Marrying Reinforcement Learning and Symbolic Planning
- Graph Attention Memory for Visual Navigation
- NeoNav: Improving the Generalization of Visual Navigation via Generating Next Expected Observations