Robotics: Science and Systems XI

DeepMPC: Learning Deep Latent Features for Model Predictive Control

Ian Lenz, Ross Knepper, Ashutosh Saxena

Abstract:

Designing robotic controllers for tasks with complex non-linear dynamics is extremely challenging, time-consuming, and in many cases, infeasible. This difficulty is exacerbated in tasks such as robotic food-cutting, in which dynamics might vary both with environmental properties, such as material and tool class, and with time while acting. In this work, we present DeepMPC, an online real-time model-predictive control approach designed to handle such difficult tasks. Rather than hand-design a dynamics model for the task, our approach uses a novel deep architecture and learning algorithm, learning controllers for complex tasks directly from data. We validate our method in experiments on a large-scale dataset of 1488 material cuts for 20 diverse classes, and in 450 real-world robotic experiments, demonstrating significant improvement over several other approaches.

Download:

Bibtex:

  
@INPROCEEDINGS{Lenz-RSS-15, 
    AUTHOR    = {Ian Lenz AND Ross Knepper AND Ashutosh Saxena}, 
    TITLE     = {DeepMPC: Learning Deep Latent Features for Model Predictive Control}, 
    BOOKTITLE = {Proceedings of Robotics: Science and Systems}, 
    YEAR      = {2015}, 
    ADDRESS   = {Rome, Italy}, 
    MONTH     = {July},
    DOI       = {10.15607/RSS.2015.XI.012} 
}