Less than the scene, still see the driest academic report!
Hi, everybody. Here is the column of academic report, the core reading small edition is selected from time to time and personally run to dedicate the best academic report in the field of science and technology for everyone, record the report for the students, and try every means to get a hand of PPT and live video – enough dry, enough fresh! Without more words, I hope that these excellent young scholars and experts jieqing’s academic reports can make your knowledge reading in your spare time more valuable.
Artificial intelligence forum is now a vast sea, there are hard goods, there are dry goods of the lecture but one in a hundred. “AI, to the future youth academic BBS” lecture series hosted by the university of Chinese Academy of Sciences, the organiser for university students of the Chinese Academy of Sciences, the co-organizer for the calculation of the Chinese Academy of Sciences graduate students will graduate, artificial intelligence, network center college student union, chemical engineering college student union, school of public policy and management, the student union, microelectronics college student union, Baidu is the supporting unit, while Corereading and PaperWeekly are cooperative we-media. The 7th session of “Future OF AI · Youth Academic Forum” was held in Chinese Academy of Sciences on the afternoon of July 22, 2019. Zhu Fan of Baidu brings you the report “Autonomous Driving in the Open Era – Baidu Apollo Plan”.
Zhu Fan, senior R&D engineer of Baidu Intelligent driving Business Group. He received his B.S. degree from Fudan University in 2008, m.S. degree and Ph.D. degree from The University of Edinburgh in 2009 and 2012, respectively. From 2013 to 2015, he worked as a postdoctoral fellow at the University of Michigan. In 2015, he joined Baidu’s SILICON Valley R&D center.
What the report says: The era of autonomous driving has arrived. Apollo is a software platform launched by Baidu named Apollo for the automotive industry and partners in the autonomous driving field. It aims to provide an open, complete and safe software platform for partners in the automotive industry and autonomous driving field, helping them combine vehicles and hardware systems to quickly build a complete autonomous driving system of their own. This report will introduce the latest progress of Baidu Apollo in automatic driving, and reveal the black technology behind Baidu’s automatic driving.
Autonomous driving in the Open era – Baidu Apollo project
Dr. Zhu fan started with a video introduction of Baidu autonomous driving, vividly showing some of the latest progress made by Baidu autonomous driving. Then, with the introduction of automatic driving classification standards, different levels of L0-L5 automatic driving standards are introduced respectively, which leads to Baidu automatic driving, and shows Apollo open circuit map of automatic driving. SAE (Society of Automotive Engineers, American Society of Automotive Engineers) J3016 document proposed the level 5 automatic driving classification scheme is currently widely accepted standards, which can be divided into: No automation (L0), Driving support (L1), Partial automation (L2), conditional automation (L3), High automation (L4), and full automation (L5). Currently, most autonomous driving companies are at the L3-L4 level of research, but L5 level of autonomous driving, where no human intervention is required in any situation, is truly autonomous.
Baidu has worked in the field of autonomous driving for many years, following two principles: “continue to lead, safety first” and “down to earth, scale test”. The former refers to baidu automatic driving in a continuous leading state, and adhere to safety in the first place. According to “Beijing automatic vehicle road test 2018 annual work report statistics, baidu is automated driving road test mileage most, test plates, zero accidents and the only one company cover all test scenarios, including T4 levels of the complex urban road scene, the scene of the highest standard, is also the most difficult test. “Scale test” is reflected in some data: The test mileage of Baidu urban road has exceeded 2 million kilometers, with more than 300 test vehicles and more than 13 test cities, and 438 new patents, ranking first in China. These achievements cannot be achieved without baidu’s steady development of autonomous driving, from the initial release of Apollo to the current version 5.0 of Apollo, Apollo 1.0, Apollo 1.5, Apollo 2.0, Apollo 2.5, Apollo 3.0 and Apollo 3.5.
Then introduces the Apollo open platform into the 5.0 era, and then leads to some application products of Baidu autonomous driving, at the same time, combined with the application scenario analysis of the advantages of Baidu Apollo autonomous driving. Apollo open platform consists of cloud service platform, software open platform, hardware development platform and vehicle certification platform. It enables the auto factory to integrate the hardware equipment such as relevant sensors required for automatic driving with the original vehicle process before installation. After the vehicle is off the assembly line, the auto factory will directly accept the vehicle through various safety tests. The improvement advantage for the safety and stability of the vehicle is that the rear installation process can not achieve. At the same time, Baidu automatic driving provides virtual simulation. Through massive scenes, built-in HIGH-DEFINITION maps, intelligent professional measurement system and 3D visualization execution of algorithms, it can realize big data simulation of vehicles traveling millions of kilometers per day.
Baidu’s automatic driving has accumulated a large number of scenarios, such as Minibus, which has realized the process from commercialization to mass production and then to batch operation. Robotaxi realizes the process from forward design to pre-assembly production line and then to vehicle test, saying goodbye to the trouble of refit; ApolloGo, which brings “city-level” intelligent upgrades, will carry out manned autonomous driving tests in Changsha this year. Baidu autonomous driving has the advantages of covering diversified operation scenarios, such as processing a large number of road scenarios, full-process and all-weather autonomous driving capability, safety design based on passengers’ feelings, and safe driving capability comparable to human drivers. Baidu’s autonomous driving is based on sensors with comprehensive coverage and strong deep learning AI technology, which greatly improves the driving technology of the system and can achieve a system response speed of millisecond faster than that of human drivers.
Finally, it introduces some cooperation of Baidu autonomous driving, including cooperation with developers, Oems and car-road cooperation companies. The cooperation with developers has resulted in products such as Apolong Golden Dragon Bus, Wu Xiaobai Smart Sanitation vehicle, Neolithic unmanned retail vehicle, Jinriqi Smart Rover and Tortec Apolox agricultural vehicle. The cooperation with OEM covers the whole process of product definition, r&d, mass production and operation. Since Baidu adheres to the principle of “opening capacity, sharing resources, accelerating innovation and sustainable win-win” in cooperation, Baidu has further expanded its partnership with automatic driving.
At the end of the presentation, Dr. Zhu showed Apollo’s slogan: “We choose to go to the moon in this decade and do the other things, not because they are easy, But because they arehard. “Apollo is committed to bringing a more robust platform and technology to you. For more exciting content, please follow the video sharing.
Leave a comment like follow
We share the dry goods of AI learning and development
Welcome to “core reading” of AI vertical we-media of the whole platform
(Add wechat: DXSXBB, join readers’ circle and discuss the freshest artificial intelligence technology.)