Towards Lifelong Self-Supervision: A Deep Learning Direction for Robotics
It addresses the challenge of building general intelligence in robots, but is incremental as it synthesizes existing ideas rather than introducing new methods.
The paper surveys deep learning applications in robotics, highlighting their limitations and proposing an integrated lifelong learning architecture that combines insights from cognitive development and classical control theory.
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.