Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World

Abstract

Bridging the 'reality gap' that separates simulated robotics from experiments on hardware could accelerate robotic research through improved data availability. This paper explores domain randomization, a simple technique for training models on simulated images that transfer to real images by randomizing rendering in the simulator. With enough variability in the simulator, the real world may appear to the model as just another variation. We focus on the task of object localization, which is a stepping stone to general robotic manipulation skills. We find that it is possible to train a real-world object detector that is accurate to $1.5$cm and robust to distractors and partial occlusions using only data from a simulator with non-realistic random textures. To demonstrate the capabilities of our detectors, we show they can be used to perform grasping in a cluttered environment. To our knowledge, this is the first successful transfer of a deep neural network trained only on simulated RGB images (without pre-training on real images) to the real world for the purpose of robotic control.

8 pages, 7 figures. Submitted to 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017)

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Domain Confusion: Maximizing for Domain Invariance
• Unsupervised Cross-Domain Image Generation
• Playing for Data: Ground Truth from Computer Games
• EPOpt: Learning Robust Neural Network Policies Using Model Ensembles
• Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
• 3D Simulation for Robot Arm Control with Deep Q-Learning
• Reinforcement Learning for Pivoting Task
• Deep Predictive Policy Training using Reinforcement Learning

Cited by in corpus (9)

• A Berkeley View of Systems Challenges for AI
• Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task
• HoME: a Household Multimodal Environment
• Active Neural Localization
• Sim-to-Real Transfer of Accurate Grasping with Eye-In-Hand Observations and Continuous Control
• Mutual Alignment Transfer Learning
• Transferring Autonomous Driving Knowledge on Simulated and Real Intersections
• Map-based Multi-Policy Reinforcement Learning: Enhancing Adaptability of Robots by Deep Reinforcement Learning
• Transferring Agent Behaviors from Videos via Motion GANs