智能机器人同步定位与建图专用芯片研究综述  

Overview of development and challenges of dedicated chips for simultaneous localization and mapping in intelligent robotics

作　　者：刘炳强 沈梓煊 王继鹏 肖健[2] 谭玉龙 何再生 许登科 王珂[4] 瞿卫新 王超[1,2] 孙立宁[4,5,6] LIU Bingqiang;SHEN Zixuan;WANG Jipeng;XIAO Jian;TAN Yulong;HE Zaisheng;XU Dengke;WANG Ke;QU Weixin;WANG Chao;SUN Lining(School of Optical and Electronic Information,Huazhong University of Science and Technology,Wuhan 430074,China;College of Future Technology,Huazhong University of Science and Technology,Wuhan 430074,China;Zhuhai Yiwei Semiconductor Co.,Ltd.,Zhuhai 519000,China;State Key Laboratory of Robotics and Systems,Harbin Institute of Technology,Harbin 150001,China;School of Mechanical and Electrical Engineering,Soochow University,Suzhou 215006,China;Xiangcheng Research Institute of Robotics and Intelligent Equipment,Soochow University,Suzhou 215131,China)

机构地区：[1]华中科技大学光学与电子信息学院,武汉430074 [2]华中科技大学未来技术学院,武汉430074 [3]珠海一微半导体股份有限公司,珠海519000 [4]哈尔滨工业大学机器人技术与系统国家重点实验室,哈尔滨150001 [5]苏州大学机电工程学院,苏州215006 [6]苏州大学相城机器人与智能装备研究院,苏州215131

出　　处：《集成电路与嵌入式系统》2024年第11期1-14,共14页Integrated Circuits and Embedded Systems

基　　金：国家重点研发计划机器人环境建模与导航定位专用芯片及软硬件模组(2019YFB1310000);武汉市科技重大专项“卡脖子”技术攻关项目(2022010402020045);华中科技大学交叉研究支持计划(2024JCYJ036);华中科技大学未来技术太湖创新基金(HUST:2023B6)。

摘　　要：机器人是新质生产力的革命性引擎,正在重塑人类的生活和工作。同步定位与建图技术(Simultaneous Localization And Mapping,SLAM)能够使机器人在未知环境中自主导航并构建周围环境的地图,是自主移动机器人实现智能化的基石。然而,SLAM算法复杂且运算量大,基于通用芯片方案实现存在延时长、功耗高的问题,不能满足自主移动机器人,尤其是小型、微型、纳型机器人的实时性、体积和功耗需求。因此,设计专用芯片加速计算密集的SLAM算法在近年来受到学术界和产业界的高度关注。本文首先从SLAM技术的基本概念和应用场景出发介绍了SLAM算法需要硬件加速的必要性,接着从算法和专用芯片设计两个角度出发梳理了SLAM技术的研究现状与发展趋势,接着重点讨论了SLAM专用芯片研究的技术挑战与解决方案,对未来发展给出了建议。Robots represent a revolutionary engine of new productive forces,reshaping human life and work.Simultaneous Localization And Mapping(SLAM)technology enables robots to navigate autonomously in unknown environments and construct maps of their surroundings,serving as the cornerstone for the intelligence of autonomous mobile robots.However,given that SLAM algorithms are complex and computationally intensive,implementations based on general-purpose CPU chips suffer from long delays and high power consumption,which fails to meet the real-time and power consumption requirements of autonomous mobile robots,especially small,micro,and nano ones.Consequently,the design of specialized hardware accelerator chips to accelerate computation-intensive SLAM algorithms has received considerable attention from both the academic and industrial communities in recent years.This article starts with the basic concepts and application scenarios of SLAM technology,and highlights the necessity of hardware acceleration for SLAM algorithms.It then reviews the current research status and development trends from the perspectives of algorithms and dedicated chip design,and discusses the technical challenges and solutions related to SLAM dedicated chips,providing recommendions for future development.

关 键 词：机器人 同步定位与建图 专用芯片 硬件加速 SLAM 

分 类 号：TN47[电子电信—微电子学与固体电子学]