集成电路与嵌入式系统2024，Vol.24Issue(11)：1-14,14.DOI:10.20193/j.ices2097-4191.2024.0027
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
摘要
Abstract
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 sur-roundings,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,mi-cro,and nano ones.Consequently,the design of specialized hardware accelerator chips to accelerate computation-intensive SLAM algo-rithms 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 algo-rithms.It then reviews the current research status and development trends from the perspectives of algorithms and dedicated chip de-sign,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/SLAMKey words
robots/simultaneous localization and mapping/specialized chips/hardware acceleration/SLAM分类
信息技术与安全科学引用本文复制引用
刘炳强,王超,孙立宁,沈梓煊,王继鹏,肖健,谭玉龙,何再生,许登科,王珂,瞿卫新..智能机器人同步定位与建图专用芯片研究综述[J].集成电路与嵌入式系统,2024,24(11):1-14,14.基金项目
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) （2019YFB1310000）
武汉市科技重大专项"卡脖子"技术攻关项目(2022010402020045) （2022010402020045）
华中科技大学交叉研究支持计划(2024JCYJ036) （2024JCYJ036）
华中科技大学未来技术太湖创新基金(HUST:2023-B-6). （HUST:2023-B-6）
