A Reconfigurable Matrix Multiplication Coprocessor with High Area and Energy Efficiency for Visual Intelligent and Autonomous Mobile Robots

Wang，Jipeng1; Zhan，Yi1; Wang，Zhaoxu1; Peng，Zixuan1; Xu，Jiarui1; Liu，Bingqiang1; Yu，Guoyi1; An，Fengwei2; Wang，Chao1; Zou，Xuecheng1

10.1109/A-SSCC53895.2021.9634793

2021

17th IEEE Asian Solid-State Circuits Conference (A-SSCC) - Integrated Circuits and Systems for the Connection of Intelligent Things

978-1-6654-4351-7

Proceedings - A-SSCC 2021: IEEE Asian Solid-State Circuits Conference

1-3

NOV 07-10, 2021

null,Busan,SOUTH KOREA

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Matrix multiplication is an essential mathematical calculation in a wide range applications of signal processing, computer graphics and intelligent robots. The intelligent and autonomous robots involves various navigation algorithms (e.g. Extended Kalman Filter (EKF), reinforcement learning, A∗ and artificial potential field, etc.) [1]-[4] and deep neural network (DNN) algorithms (e.g. Darknet in YOLOv3), which all contain intensive matrix multiplications with different sizes and shapes. The emerging Intelligent and Autonomous Mobile Robots (I-AMRs) have put forward to a higher demand to efficient hardware acceleration of a comprehensive range of matrix multiplications as depicted in Fig. 1. Recent works have focused on the hardware acceleration of matrix multiplications optimized for a specified navigation or DNN algorithm [3]-[5], which cannot achieve high hardware utilization, high area and energy efficiency for the various matrix multiplications in I-AMRs.

Visualization Navigation Shape Signal processing algorithms Reinforcement learning Signal processing Energy efficiency

其他

英语

CPCI-S ; EI

National Key R&D Program of China[2019YFB1310001]

Engineering

Engineering, Electrical & Electronic

WOS:000768220800066

20220611593100

Computer graphics ; Computer hardware ; Coprocessor ; Deep neural networks ; Energy efficiency ; Intelligent robots ; Mobile robots ; Navigation ; Program processors ; Reinforcement learning

Ergonomics and Human Factors Engineering:461.4 ; Energy Conservation:525.2 ; Semiconductor Devices and Integrated Circuits:714.2 ; Computer Circuits:721.3 ; Computer Systems and Equipment:722 ; Artificial Intelligence:723.4 ; Computer Applications:723.5 ; Robotics:731.5 ; Robot Applications:731.6 ; Algebra:921.1

2-s2.0-85124012791

Scopus

1.Huazhong University of Science and Technology,Wuhan,China
2.Southern University of Science and Technology,Shenzhen,China

Wang，Jipeng,Zhan，Yi,Wang，Zhaoxu,et al. A Reconfigurable Matrix Multiplication Coprocessor with High Area and Energy Efficiency for Visual Intelligent and Autonomous Mobile Robots[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2021:1-3.