Name
Title | ||
|---|---|---|
Transfer And Online Reinforcement Learning In Stt-Mram Based Embedded Systems For Autonomous Drones |
Abstract | ||
|---|---|---|
In this paper we present an algorithm-hardware co design for camera-based autonomous flight in small drones. We show that the large write-latency and write-energy for nonvolatile memory (NVM) based embedded systems makes them unsuitable for real-time reinforcement learning (RL), We address this by performing transfer learning (TL) on meta environments and RL on the last few layers of a deep convolutional network. While the NVM stores the meta-model from TL, an on-die SRAM stores the weights of the last few layers. Thus all the real-time updates sia RL are carried out on the SRAM arrays. This provides us with a practical platform with comparable performance as end-to-end RL and 83.4% lower energy per image frame. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.23919/DATE.2019.8715066 | 2019 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE) |
DocType | Volume | ISSN |
Journal | abs/1905.06314 | 1530-1591 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Insik Yoon | 1 | 9 | 3.36 |
| Malik Aqeel Anwar | 2 | 1 | 1.37 |
| Titash Rakshit | 3 | 0 | 1.69 |
| Arijit Raychowdhury | 4 | 284 | 48.04 |