NavigationNet: A Large-scale Interactive Indoor Navigation Dataset
arXiv:1808.08374
Abstract
Indoor navigation aims at performing navigation within buildings. In scenes like home and factory, most intelligent mobile devices require an functionality of routing to guide itself precisely through indoor scenes to complete various tasks in order to serve human. In most scenarios, we expected an intelligent device capable of navigating itself in unseen environment. Although several solutions have been proposed to deal with this issue, they usually require pre-installed beacons or a map pre-built with SLAM, which means that they are not capable of working in novel environments. To address this, we proposed NavigationNet, a computer vision dataset and benchmark to allow the utilization of deep reinforcement learning on scene-understanding-based indoor navigation. We also proposed and formalized several typical indoor routing problems that are suitable for deep reinforcement learning.
References in corpus (20)
- Continuous control with deep reinforcement learning
- Playing Atari with Deep Reinforcement Learning
- Deep Residual Learning for Image Recognition
- Densely Connected Convolutional Networks
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Benchmarking Deep Reinforcement Learning for Continuous Control
- Visual-Inertial Monocular SLAM with Map Reuse
- Emergence of Locomotion Behaviours in Rich Environments
- Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
- Matterport3D: Learning from RGB-D Data in Indoor Environments
- AI2-THOR: An Interactive 3D Environment for Visual AI
- End-to-End Learning of Geometry and Context for Deep Stereo Regression
- TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games
- Deep Learning Driven Visual Path Prediction from a Single Image
- Learning to Perform Physics Experiments via Deep Reinforcement Learning
- Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching
- End-to-End Learning of Semantic Grasping
- Dual Path Networks
- Visual Semantic Planning using Deep Successor Representations
- Improved Stereo Matching with Constant Highway Networks and Reflective Confidence Learning