papers AI Learner
The Github is limit! Click to go to the new site.

Differentiable Algorithm Networks for Composable Robot Learning

2019-05-28
Peter Karkus, Xiao Ma, David Hsu, Leslie Pack Kaelbling, Wee Sun Lee, Tomas Lozano-Perez

Abstract

This paper introduces the Differentiable Algorithm Network (DAN), a composable architecture for robot learning systems. A DAN is composed of neural network modules, each encoding a differentiable robot algorithm and an associated model; and it is trained end-to-end from data. DAN combines the strengths of model-driven modular system design and data-driven end-to-end learning. The algorithms and models act as structural assumptions to reduce the data requirements for learning; end-to-end learning allows the modules to adapt to one another and compensate for imperfect models and algorithms, in order to achieve the best overall system performance. We illustrate the DAN methodology through a case study on a simulated robot system, which learns to navigate in complex 3-D environments with only local visual observations and an image of a partially correct 2-D floor map.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1905.11602

PDF

https://arxiv.org/pdf/1905.11602


Comments

Content