R. Rahmatizadeh, P. Abolghasemi, L. Bölöni, and S. Levine

Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration


Cite as:

R. Rahmatizadeh, P. Abolghasemi, L. Bölöni, and S. Levine. Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration. In Proc. of International Conference on Robotics and Automation (ICRA-2018), May 2018.

Download:

Download Video 

Abstract:

We propose a technique for multi-task learning from demonstration that trains the controller of a low-cost robotic arm to accomplish several complex picking and placing tasks, as well as non-prehensile manipulation. The controller is a recurrent neural network using raw images as input and generating robot arm trajectories, with the parameters shared across the tasks. The controller also combines VAE-GAN-based reconstruction with autoregressive multimodal action prediction. Our results demonstrate that it is possible to learn complex manipulation tasks, such as picking up a towel, wiping an object, and depositing the towel to its previous position, entirely from raw images with direct behavior cloning. We show that weight sharing and reconstruction-based regularization substantially improve generalization and robustness, and training on multiple tasks simultaneously increases the success rate on all tasks.

BibTeX:

@inproceedings{Rahmatizadeh-2018-InexpensiveRobot,
  author    = {R. Rahmatizadeh and
               P. Abolghasemi and
               L. B{\"o}l{\"o}ni and
               S. Levine},
  title     = {Vision-Based Multi-Task Manipulation for Inexpensive Robots Using
               End-To-End Learning from Demonstration},
  booktitle={Proc. of International Conference on Robotics and Automation (ICRA-2018)},
  location = "Brisbane, Australia",
  month = "May",
  year = "2018",
  abstract = {
  We propose a technique for multi-task learning from demonstration that trains the controller of a low-cost robotic arm to accomplish several complex picking and placing tasks, as well as non-prehensile manipulation. The controller is a recurrent neural network using raw images as input and generating robot arm trajectories, with the parameters shared across the tasks. The controller also combines VAE-GAN-based reconstruction with autoregressive multimodal action prediction. Our results demonstrate that it is possible to learn complex manipulation tasks, such as picking up a towel, wiping an object, and depositing the towel to its previous position, entirely from raw images with direct behavior cloning. We show that weight sharing and reconstruction-based regularization substantially improve generalization and robustness, and training on multiple tasks simultaneously increases the success rate on all tasks.
  }
}

Generated by bib2html.pl (written by Patrick Riley, Lotzi Boloni ) on Thu Aug 16, 2018 21:43:42