Autonomous Driving Algorithms and Its IC Design

With the rapid development of artificial intelligence and the emergence of various new sensors, autonomous driving has grown in popularity in recent years. The implementation of autonomous driving requires new sources of sensory data, such as cameras, radars, and lidars, and the algorithm processing requires a high degree of parallel computing. In this regard, traditional CPUs have insufficient computing power, while DSPs are good at image processing but lack sufficient performance for deep learning. Although GPUs are good at training, they are too "power-hungry," which can affect vehicle performance. Therefore, this book looks to the future, arguing that custom ASICs are bound to become mainstream. With the goal of ICs design for autonomous driving, this book discusses the theory and engineering practice of designing future-oriented autonomous driving SoC chips.

The content is divided into thirteen chapters, the first chapter mainly introduces readers to the current challenges and research directions in autonomous driving. Chapters 2-6 focus on algorithm design for perception and planning control. Chapters 7-10 address the optimization of deep learning models and the design of deep learning chips, while Chapters 11-12 cover automatic driving software architecture design. Chapter 13 discusses the 5G application on autonomous drving.

This book is suitable for all undergraduates, graduate students, and engineering technicians who are interested in autonomous driving.

隨著人工智慧的快速發展和各種新型感測器的出現，自動駕駛在近年來越來越受到歡迎。實現自動駕駛需要新的感測數據來源，例如攝像頭、雷達和激光雷達，而算法處理需要高度的並行計算。在這方面，傳統的中央處理器（CPU）計算能力不足，而數字信號處理器（DSP）擅長圖像處理，但對於深度學習缺乏足夠的性能。雖然圖形處理器（GPU）擅長訓練，但它們耗電量過大，可能影響車輛性能。因此，本書展望未來，認為定制的應用特定集成電路（ASIC）必將成為主流。本書以自動駕駛IC設計為目標，討論了設計面向未來的自動駕駛SoC芯片的理論和工程實踐。

本書內容分為十三章，第一章主要介紹了自動駕駛目前面臨的挑戰和研究方向。第2-6章著重於感知和規劃控制的算法設計。第7-10章涉及深度學習模型的優化和深度學習芯片的設計，而第11-12章則涵蓋了自動駕駛軟件架構設計。第13章討論了5G在自動駕駛上的應用。

本書適合所有對自動駕駛感興趣的本科生、研究生和工程技術人員閱讀。

Dr. Jianfeng Ren, currently working at Google Inc., received his PhD in Electrical Engineering from the University of Texas at Dallas in 2009. Previously, he worked for Qualcomm and Huawei HiSilicon for many years, and has published more than 40 papers and more than 30 US patents. His current research focus is on computational photograph/computer vision algorithms.

Dr. Dong xia, received the PhD degree in Communication and Information System in the National University of Defense Technology. He has long been engaged in research work in the field of artificial intelligence, chip algorithm design and automatic target recognition, and published more than 60 patents.

Dr. Jianfeng Ren（任建峰博士）目前在Google Inc.工作，於2009年從德州達拉斯大學獲得電機工程博士學位。在此之前，他曾在高通和華為海思工作多年，並發表了40多篇論文和30多項美國專利。他目前的研究重點是計算攝影/計算機視覺算法。

Dr. Dong Xia（夏東博士）在國防科技大學獲得通信與信息系統博士學位。他長期從事人工智能、芯片算法設計和自動目標識別等領域的研究工作，並發表了60多項專利。