FPGA architecture for deep learning and its application to planetary robotics

Pranay Reddy Gankidi, Jekan Thangavelautham

Research output: Chapter in Book/Report/Conference proceedingConference contribution

20 Scopus citations

Abstract

Autonomous control systems onboard planetary rovers and spacecraft benefit from having cognitive capabilities like learning so that they can adapt to unexpected situations in-situ. Q-learning is a form of reinforcement learning and it has been efficient in solving certain class of learning problems. However, embedded systems onboard planetary rovers and spacecraft rarely implement learning algorithms due to the constraints faced in the field, like processing power, chip size, convergence rate and costs due to the need for radiation hardening. These challenges present a compelling need for a portable, low-power, area efficient hardware accelerator to make learning algorithms practical onboard space hardware. This paper presents a FPGA implementation of Q-learning with Artificial Neural Networks (ANN). This method matches the massive parallelism inherent in neural network software with the fine-grain parallelism of an FPGA hardware thereby dramatically reducing processing time. Mars Science Laboratory currently uses Xilinx-Space-grade Virtex FPGA devices for image processing, pyrotechnic operation control and obstacle avoidance. We simulate and program our architecture on a Xilinx Virtex 7 FPGA. The architectural implementation for a single neuron Q-learning and a more complex Multilayer Perception (MLP) Q-learning accelerator has been demonstrated. The results show up to a 43-fold speed up by Virtex 7 FPGAs compared to a conventional Intel i5 2.3 GHz CPU. Finally, we simulate the proposed architecture using the Symphony simulator and compiler from Xilinx, and evaluate the performance and power consumption.

Original languageEnglish (US)
Title of host publication2017 IEEE Aerospace Conference
PublisherIEEE Computer Society
ISBN (Electronic)9781509016136
DOIs
StatePublished - Jun 7 2017
Externally publishedYes
Event2017 IEEE Aerospace Conference, AERO 2017 - Big Sky, United States
Duration: Mar 4 2017Mar 11 2017

Publication series

NameIEEE Aerospace Conference Proceedings
ISSN (Print)1095-323X

Other

Other2017 IEEE Aerospace Conference, AERO 2017
Country/TerritoryUnited States
CityBig Sky
Period3/4/173/11/17

ASJC Scopus subject areas

  • Aerospace Engineering
  • Space and Planetary Science

Fingerprint

Dive into the research topics of 'FPGA architecture for deep learning and its application to planetary robotics'. Together they form a unique fingerprint.

Cite this