• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE Aerospace Conference >FPGA architecture for deep learning and its application to planetary robotics
【24h】

FPGA architecture for deep learning and its application to planetary robotics

机译：深度学习的FPGA架构及其在行星机器人中的应用

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

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.
机译：行星漫游车和航天器上的自主控制系统得益于具有学习等认知能力，因此它们可以就地适应意外情况。 Q学习是强化学习的一种形式，它在解决某些类别的学习问题上非常有效。然而，由于该领域面临的限制，例如处理能力，芯片尺寸，收敛速度和辐射硬化所需的成本，行星漫游器和航天器上的嵌入式系统很少执行学习算法。这些挑战提出了对便携式，低功耗，面积高效的硬件加速器的迫切需求，以使学习算法在机载太空硬件上实用。本文介绍了使用人工神经网络（ANN）进行Q学习的FPGA实现。这种方法将神经网络软件固有的大规模并行性与FPGA硬件的细粒度并行性相匹配，从而大大减少了处理时间。火星科学实验室目前使用Xilinx-Space级Virtex FPGA器件进行图像处理，烟火操作控制和避障。我们在Xilinx Virtex 7 FPGA上对架构进行仿真和编程。已经证明了单个神经元Q学习和更复杂的多层感知（MLP）Q学习加速器的体系结构实现。结果表明，与传统的Intel i5 2.3 GHz CPU相比，Virtex 7 FPGA的速度提高了43倍。最后，我们使用Xilinx的Symphony模拟器和编译器对建议的体系结构进行仿真，并评估性能和功耗。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号