Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks.
Michelle A. LeeYuke ZhuKrishnan SrinivasanParth ShahSilvio SavareseLi Fei-FeiAnimesh GargJeannette BohgPublished in: ICRA (2019)
Keyphrases
- real time
- learning algorithm
- data sets
- multiple tasks
- supervised learning
- multi task learning
- learning systems
- multi modal
- learning process
- multi task
- inductive learning
- background knowledge
- real world
- neural network
- learning environment
- reinforcement learning
- computer vision
- machine learning
- external representations