摘要
随着自动驾驶系统(Autonomous driving systems, ADS)在全球范围内的快速发展和广泛应用,大模型在自动驾驶技术中扮演着关键角色。这些模型通过整合多传感器数据,实现对复杂驾驶环境的快速准确理解和决策。然而,大模型面临超大规模参数、高计算成本和大存储需求等挑战,尤其在资源有限的车端设备上更为突出。有效压缩大模型成为当前研究的重要方向,可以降低大模型的计算和存储需求的同时保持性能。首先深入探讨了大模型技术的最新进展和应用实践,从而衍生出高效压缩技术。然后从剪枝、神经网络架构搜索、低秩分解、量化和知识蒸馏等角度出发,分析各种压缩技术的原理和性能特征。最后,基于现有研究,提出大模型高效压缩技术未来的挑战和发展方向,旨在为自动驾驶技术提供新思路和解决方案,推动系统向更高效、更智能、更安全的方向发展。
With the rapid development and widespread application of autonomous driving systems(ADS)globally,large models play a pivotal role in autonomous driving technology.These models integrate data from multiple sensors to achieve rapid and accurate understanding and decision-making in complex driving environments.However,large models face challenges such as massive parameter sizes,high computational costs,and large storage requirements,particularly accentuated in edge devices with limited resources.Efficiently compressing large models has become a significant research focus,enabling a reduction in computational and storage demands while maintaining performance.This study extensively explores the latest advancements and practical applications of large models technology,leading to the emergence of efficient compression techniques.It then analyzes various compression techniques,including pruning,neural network architecture search,low-rank decomposition,quantization,and knowledge distillation,in terms of their principles and performance characteristics.Finally,based on existing research,it outlines the future challenges and development directions of efficient compression techniques for large models,aiming to provide new insights and solutions for autonomous driving technology and drive the system towards higher efficiency,intelligence,and safety.
作者
褚文博
甘露
李国法
唐小林
李克强
CHU Wenbo;GAN Lu;LI Guofa;TANG Xiaolin;LI Keqiang(College of Mechanical and Vehicle Engineering,Chongqing University,Chongqing 400044;Western China Science City Innovation Center of Intelligent andConnected Vehicles(Chongqing)Co.,Ltd.,Chongqing 401329;Engineering Research Center of Mechanical Testing Technology and Equipment Ministry of Education,Chongqing University of Technology,Chongqing 400054;School of Vehicle and Mobility,Tsinghua University,Beijing 100084)
出处
《机械工程学报》
EI
CAS
CSCD
北大核心
2024年第22期224-240,共17页
Journal of Mechanical Engineering
基金
国家重点研发计划(2022YFB2503205)
国家自然科学基金(52372377,52272421,52222215,52072051)
工信部产业技术基础公共服务平台(2021-0176-1-1)
智能绿色车辆与交通全国重点实验室开放基金课题(KFZ2409)资助项目。
关键词
自动驾驶
大模型
综述
高效压缩技术
autonomous driving
large models
review
efficient compression technology
