Domain randomization for transferring deep neural networks from simulation to the real world
Explore this paper's citation graph
- Type
- article
- Published
- 2017-03-20
- Cited by
- 4,028
- References
- 64
- Access
- Open access
- OpenAlex
- https://openalex.org/W2605102758
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:2413610
Keywords
Computer science, Artificial intelligence, Rendering (computer graphics), Robotics, Artificial neural network
References
- Model learning for robot control: a survey
- The YCB object and Model set: Towards common benchmarks for manipulation research
- Efficient Learning of Domain-invariant Image Representations
- Deep Domain Confusion: Maximizing for Domain Invariance
- Learning omnidirectional path following using dimensionality reduction
- Efficient reinforcement learning for robots using informative simulated priors
- Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
- Domain Adaptation: Learning Bounds and Algorithms
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Robots that can adapt like animals
- Evolutionary Robotics and the Radical Envelope-of-Noise Hypothesis
- The Transferability Approach: Crossing the Reality Gap in Evolutionary Robotics
- Cross-domain video concept detection using adaptive svms
- Efficient multi-view object recognition and full pose estimation
- Superhuman performance of surgical tasks by robots using iterative learning from human-guided demonstrations
- Reinforcement learning with multi-fidelity simulators
- Describing Textures in the Wild
- The MOPED framework: Object recognition and pose estimation for manipulation
- Artificial neural networks for spatial perception: Towards visual object localisation in humanoid robots
- From Virtual to Reality: Fast Adaptation of Virtual Object Detectors to Real Domains
Cited by
- Learning Manipulation Trajectories Using Recurrent Neural Networks
- Towards Generalization and Simplicity in Continuous Control
- Cross-Domain Perceptual Reward Functions
- Grounding Symbols in Multi-Modal Instructions
- Object Detection Using Deep CNNs Trained on Synthetic Images
- Reverse Curriculum Generation for Reinforcement Learning
- ADAPT: Zero-Shot Adaptive Policy Transfer for Stochastic Dynamical Systems
- Autonomous robots: potential, advances and future direction
- Unsupervised state representation learning with robotic priors: a robustness benchmark
- Autonomous Quadrotor Landing using Deep Reinforcement Learning
- Sim-to-real Transfer of Visuo-motor Policies for Reaching in Clutter: Domain Randomization and Adaptation with Modular Networks
- How to Train a CAT: Learning Canonical Appearance Transformations for Direct Visual Localization Under Illumination Change
- Reasoning About Spatial Patterns of Human Behavior During Group Conversations with Robots
- Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping
- Avoidance of Manual Labeling in Robotic Autonomous Navigation Through Multi-Sensory Semi-Supervised Learning
- GeneSIS-Rt: Generating Synthetic Images for Training Secondary Real-World Tasks
- Map-based Multi-Policy Reinforcement Learning: Enhancing Adaptability of Robots by Deep Reinforcement Learning
- Domain Randomization and Generative Models for Robotic Grasping
- Asymmetric Actor Critic for Image-Based Robot Learning
- Automated Production Technologies and Measurement Systems for Ferrite Magnetized Linear Generators
Related papers
- Some considerations of bridging stresses for fiber-reinforced ceramics
- Bridging the gap to working in Canada: experience of internationally educated physiotherapists with an innovative multicomponent, blended format bridging program
- Testable design of RMC networks with universal tests for detecting stuck-at and bridging faults
- Using Dummy Bridging Faults to Define Reduced Sets of Target Faults
- OS1322-394 Fracture mechanism of intralaminar crack propagation under mode II loading for CFRP laminates
- BRIDGING THE GAP - The author leads her learners from language acquisition to language use
- OA: bridging the language gap
- ChemInform Abstract: REARRANGEMENT OF BRIDGING ALKYLIDYNEIRON COMPLEXES TO BRIDGING ALKENYLIRON COMPLEXES