On-Policy Dataset Synthesis for Learning Robot Grasping Policies Using Fully Convolutional Deep Networks.
Vishal SatishJeffrey MahlerKen GoldbergPublished in: IEEE Robotics Autom. Lett. (2019)
Keyphrases
- deep learning
- learning process
- vision system
- unsupervised learning
- autonomous learning
- policy gradient methods
- mobile robot
- learning algorithm
- robotic systems
- unsupervised feature learning
- deep architectures
- connectionist networks
- human robot interaction
- multi robot
- path planning
- reinforcement learning
- social networks