基于STT-MRAM的无人机嵌入式系统迁移与在线强化学习
Transfer and Online Reinforcement Learning in STT-MRAM Based Embedded Systems for Autonomous Drones
摘要:
在本文中,我们提出了一种算法硬件协同设计的摄像机为基础的自主飞行的小型无人机。我们表明,大的写延迟和写能量的非易失性存储器(NVM)为基础的嵌入式系统,使他们不适合实时强化学习(RL)。我们通过在元环境上执行迁移学习(TL)和在深度卷积网络的最后几层上执行RL来解决这个问题。当NVM存储来自TL的元模型时,管芯上SRAM存储最后几层的权重。因此,所有通过RL的实时更新都在SRAM阵列上执行。这为我们提供了一个实用的平台,其性能与端到端RL相当,每帧图像的能耗降低了83.4
英文摘要:
In this paper we present an algorithm-hardware codesign 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 metaenvironments 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 via 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
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。