Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation
arXiv:2007.05655
Abstract
The ability to perform effective planning is crucial for building an instruction-following agent. When navigating through a new environment, an agent is challenged with (1) connecting the natural language instructions with its progressively growing knowledge of the world; and (2) performing long-range planning and decision making in the form of effective exploration and error correction. Current methods are still limited on both fronts despite extensive efforts. In this paper, we introduce the Evolving Graphical Planner (EGP), a model that performs global planning for navigation based on raw sensory input. The model dynamically constructs a graphical representation, generalizes the action space to allow for more flexible decision making, and performs efficient planning on a proxy graph representation. We evaluate our model on a challenging Vision-and-Language Navigation (VLN) task with photorealistic images and achieve superior performance compared to previous navigation architectures. For instance, we achieve a 53% success rate on the test split of the Room-to-Room navigation task through pure imitation learning, outperforming previous navigation architectures by up to 5%.
References in corpus (9)
- Deep Convolutional Networks on Graph-Structured Data
- Matterport3D: Learning from RGB-D Data in Indoor Environments
- Professor Forcing: A New Algorithm for Training Recurrent Networks
- Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
- Neural Map: Structured Memory for Deep Reinforcement Learning
- From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following
- Neural Graph Evolution: Towards Efficient Automatic Robot Design
- Hallucinative Topological Memory for Zero-Shot Visual Planning
- RMM: A Recursive Mental Model for Dialog Navigation