Towards Lifelong Self-Supervision: A Deep Learning Direction for Robotics
arXiv:1611.00201
Abstract
Despite outstanding success in vision amongst other domains, many of the recent deep learning approaches have evident drawbacks for robots. This manuscript surveys recent work in the literature that pertain to applying deep learning systems to the robotics domain, either as means of estimation or as a tool to resolve motor commands directly from raw percepts. These recent advances are only a piece to the puzzle. We suggest that deep learning as a tool alone is insufficient in building a unified framework to acquire general intelligence. For this reason, we complement our survey with insights from cognitive development and refer to ideas from classical control theory, producing an integrated direction for a lifelong learning architecture.
References in corpus (12)
- Continuous control with deep reinforcement learning
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Intriguing properties of neural networks
- Playing Atari with Deep Reinforcement Learning
- DeepPose: Human Pose Estimation via Deep Neural Networks
- Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
- Learning Deconvolution Network for Semantic Segmentation
- Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images
- Learning to Poke by Poking: Experiential Learning of Intuitive Physics
- 3D Simulation for Robot Arm Control with Deep Q-Learning
- End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks
- Deep Learning a Grasp Function for Grasping under Gripper Pose Uncertainty