Browse > Article
http://dx.doi.org/10.22895/jse.2021.0001

Energy-Efficient DNN Processor on Embedded Systems for Spontaneous Human-Robot Interaction  

Kim, Changhyeon (School of Electrical Engineering, KAIST)
Yoo, Hoi-Jun (School of Electrical Engineering, KAIST)
Publication Information
Journal of Semiconductor Engineering / v.2, no.2, 2021 , pp. 130-135 More about this Journal
Abstract
Recently, deep neural networks (DNNs) are actively used for action control so that an autonomous system, such as the robot, can perform human-like behaviors and operations. Unlike recognition tasks, the real-time operation is essential in action control, and it is too slow to use remote learning on a server communicating through a network. New learning techniques, such as reinforcement learning (RL), are needed to determine and select the correct robot behavior locally. In this paper, we propose an energy-efficient DNN processor with a LUT-based processing engine and near-zero skipper. A CNN-based facial emotion recognition and an RNN-based emotional dialogue generation model is integrated for natural HRI system and tested with the proposed processor. It supports 1b to 16b variable weight bit precision with and 57.6% and 28.5% lower energy consumption than conventional MAC arithmetic units for 1b and 16b weight precision. Also, the near-zero skipper reduces 36% of MAC operation and consumes 28% lower energy consumption for facial emotion recognition tasks. Implemented in 65nm CMOS process, the proposed processor occupies 1784×1784 um2 areas and dissipates 0.28 mW and 34.4 mW at 1fps and 30fps facial emotion recognition tasks.
Keywords
Deep learning; deep learning ASIC; deep neural network; mobile deep learning; reinforcement learning;
Citations & Related Records
연도 인용수 순위
  • Reference
1 J. Lee, C. Kim, S. Kang, D. Shin, S. Kim, and H.-J. Yoo, "UNPU: A 50.6 TOPS/W unified deep neural network accelerator with 1b-to-16b fully-variable weight bit-precision," in 2018 IEEE International Solid-State Circuits Conference-(ISSCC), 2018: IEEE, pp. 218-220.
2 V. Mnih et al., "Human-level control through deep reinforcement learning," in Nature, vol. 518, no. 7540, p. 529, 2015.   DOI
3 J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. J. a. p. a. Klimov, "Proximal policy optimization algorithms," 2017.
4 K. Ueyoshi et al., "QUEST: A 7.49 TOPS multi-purpose logquantized DNN inference engine stacked on 96MB 3D SRAM using inductive-coupling technology in 40nm CMOS," in 2018 IEEE International Solid-State Circuits Conference-(ISSCC), 2018: IEEE, pp. 216-218.
5 V. Mnih et al., "Playing atari with deep reinforcement learning," arXiv preprint arXiv:1312.5602, 2013.
6 Z. Yuan et al., "STICKER: A 0.41-62.1 TOPS/W 8bit Neural Network Processor with Multi-Sparsity Compatible Convolution Arrays and Online Tuning Acceleration for Fully Connected Layers," in 2018 IEEE Symposium on VLSI Circuits, 2018: IEEE, pp. 33-34.