English

End-to-End Learning of Semantic Grasping

Robotics 2017-11-10 v3 Machine Learning Machine Learning

Abstract

We consider the task of semantic robotic grasping, in which a robot picks up an object of a user-specified class using only monocular images. Inspired by the two-stream hypothesis of visual reasoning, we present a semantic grasping framework that learns object detection, classification, and grasp planning in an end-to-end fashion. A "ventral stream" recognizes object class while a "dorsal stream" simultaneously interprets the geometric relationships necessary to execute successful grasps. We leverage the autonomous data collection capabilities of robots to obtain a large self-supervised dataset for training the dorsal stream, and use semi-supervised label propagation to train the ventral stream with only a modest amount of human supervision. We experimentally show that our approach improves upon grasping systems whose components are not learned end-to-end, including a baseline method that uses bounding box detection. Furthermore, we show that jointly training our model with auxiliary data consisting of non-semantic grasping data, as well as semantically labeled images without grasp actions, has the potential to substantially improve semantic grasping performance.

Keywords

Cite

@article{arxiv.1707.01932,
  title  = {End-to-End Learning of Semantic Grasping},
  author = {Eric Jang and Sudheendra Vijayanarasimhan and Peter Pastor and Julian Ibarz and Sergey Levine},
  journal= {arXiv preprint arXiv:1707.01932},
  year   = {2017}
}

Comments

14 pages

R2 v1 2026-06-22T20:40:03.391Z