This article is the product of the NetEase Smart Studio (public account: smartman163), featuring the 29th episode of the "AI Hero" interview series. Focusing on AI and reading the next big era!
Author | Ding Guangsheng
I remember when my parents were younger, they would carry a thick Chinese atlas and constantly refer to maps to navigate their way to distant destinations. Later, our newly bought cars came equipped with sleek electronic navigation systems. But these systems were often frustrating due to their outdated maps and cumbersome interfaces, making navigation a challenge.
It wasn’t until the advent of mobile navigation that things changed. Its user-friendly interface and timely map updates gave us a seamless travel experience. You didn’t need to know north from south; just follow the instructions, and you’d reach your destination.
However, in the era of autonomous driving, maps are evolving into high-precision maps and high-precision positioning systems. This will further liberate humans, allowing them to simply sit back and let the self-driving car handle everything, without worrying about navigation or directions.
So, how exactly will autonomous driving achieve navigation?
Gao Dong, the Executive President of Wei Dong's Map, has a unique perspective. He told NetEase Intelligence, "High-precision maps and high-precision positioning are bound to become essential infrastructure for autonomous driving. Sensors, lidar, and other technologies will integrate with this infrastructure, but regardless of the approach, we must first build solid infrastructure. Gaode Map has two main focuses in the field of autonomous driving: first, leveraging big data and cloud computing capabilities to offer advanced navigation services; second, providing high-precision maps and positioning to enhance the capabilities of both companies and users."
Talking about building infrastructure for autonomous driving, Wei Dong candidly admitted, "This is a mission-driven task. We might not fully grasp the significance of this work until three or five years down the line." As a map service provider, Gaode's strengths lie in data accumulation and R&D capabilities, but it lacks the high-precision positioning capabilities necessary for infrastructure development.
A few days ago, Gaode Map partnered with Chihiro Positioning, a company known for its high-precision positioning services based on the Beidou satellite system. With over 1,450 ground-based reinforcement stations across the country, Chihiro provides accurate positioning services 7 days a week, 24 hours a day, complementing Gaode's offerings.
"Building a Car" or "Building a Road"? China's Auto Industry Cannot Repeat Its Mistake
In the debate over "car-making" versus "road-building," both traditional and new players in the automotive industry have their own preferences. Wei Dong pointed out that Gaode Map aims to be the "road builder." China's auto industry has already learned a lesson from this mistake.
Wei Dong noted that today's development of autonomous driving has entered a period of misunderstanding, somewhat akin to China's early entry into the automobile era. At that time, China's roads were poor and infrastructure lacking. The best-selling cars were Japanese models, particularly off-road vehicles. Many areas of China still prefer Japanese off-road vehicles today. Why? Because the poor infrastructure necessitated cars that could handle tough conditions.
Wei Dong told NetEase Intelligence that this mindset is similar to what many people think about autonomous driving today. They push hard for solutions like lidar and other sensors, attempting to create cars capable of precise positioning. However, Gaoding looks toward the future and focuses on infrastructure.
This naturally leads to the discussion of the path toward autonomous driving. Currently, there are roughly two approaches: one relies on machine learning vision schemes, while the other depends on traditional high-precision positioning and high-precision maps. Yang Wei, Vice President of Research and Development at Gaode Map, added, "These are two schools of thought. One is the self-sensing system, characterized by vehicle sensors detecting the environment through laser radar scanning. The onboard control computer acts like the human brain, deciding what actions are needed. Traditional car companies generally follow this route."
The other approach is the V2X model, designed for the future of transportation. It enables communication between vehicles, between vehicles and base stations, and among base stations, offering real-time traffic information such as road conditions, road details, and pedestrian information.
It is understood that with the evolution of the industry, there is now a trend of convergence between these two schools.
Ensuring Autonomous Driving Safety: High-Precision Maps + Positioning + Sensors
Security is a crucial issue in the field of transportation. In fact, autonomous driving has caused numerous traffic accidents worldwide. Google's driverless cars have been involved in over a dozen accidents, with some incidents being quite severe. For instance, in January 2016, a Lexus SUV test vehicle collided with a bus.
In addition, Tesla's first fatal accident involving autonomous driving occurred last year in China. A Tesla sedan crashed into a maintenance vehicle on the Beijing-Hong Kong-Macao Expressway, resulting in the driver's death. At the time, the owner had activated Tesla's autonomous driving mode.
Wei Dong stated that for autonomous driving, the technology can be categorized into two major parts: perception and control/decision-making. "The first part includes lidar, cameras, or millimeter-wave devices. These tools address flat surfaces rather than spatial issues. A car moving on a road is a spatial concept, so images alone cannot fully address spatial problems."
"We recently saw an incident involving Tesla's autonomous driving where the car was on the highway with strong sunlight. A pickup truck was parked on the side of the road, and the rear of the truck was white, so the image misidentified it as a cloud and hit it directly, causing casualties," said Yang Wei.
Regarding the safety of autonomous driving, Wei Dong believes that the realization of technology also deserves reflection. Sensor accuracy is continually improving, which is an inevitable trend in hardware development. "The issue is that at this stage, the best positioning and navigation model is under consideration, but many people opt for a more complex path, such as image recognition or lidar. While these methods can work, whether they represent the best solution is worth discussing," Wei Dong emphasized.
Wei Dong further stated that, of course, sensors have other functions. Besides locating and sensing the environment, they play a critical role in emergency situations, ensuring safety. Sensors will always be necessary, and the future will demand them to be even more precise and efficient. The question is whether the cost is justified at this stage, and whether the algorithm's efficiency and processing time meet the requirements. Even a few seconds could result in an accident.
"In the future, high-precision maps + high-precision positioning infrastructure and sensors, lidar, etc., will play complementary roles. The former solves the problem of absolute accuracy, while the latter addresses relative accuracy and safety measures," Wei Dong outlined the path to achieving autonomous driving and ensuring safety.
Next Step: Achieving Centimeter-Level Positioning – Cars Are Not Pedestrians
We’ve all experienced situations where inaccurate positioning and navigation errors leave us confused about north, south, east, or west. This can be incredibly frustrating.
This issue is gradually gaining attention and resolution as high-precision map positioning will be used in self-driving cars. Zhi Lei, Director of Smart Driving at Chihiro, noted that for driverless vehicles, positioning itself is a vital part of control. Accurate positioning determines decision-making endpoints, such as identifying uphill or downhill sections or even sharp turns. "If a car enters a high-speed curve at excessive speed, the autopilot system will automatically slow it down. This requires a combination of high-precision positioning and high-precision maps. In the long term, autonomous driving will require centimeter-level positioning."
In addition, Wei Dong told NetEase Smart that high-precision positioning technology will gradually be integrated into Gaode’s products, including car versions. Gaode Map's goal is to achieve centimeter-level coverage in China by 2018 and global meter-level services by 2019.
Currently, car brands such as Changan, Geely, Dongfeng Kai Chen, and BYD have pre-installed high-precision car map versions; in the aftermarket, Gaode is capturing more market share.
However, it is clear that the high-precision positioning function is temporarily unavailable on the general public's mobile phones. (End)
Follow NetEase Smart's public account (smartman163) to stay updated on the latest developments in the AI industry.
Click here to review the "AI Heroes" series, step by step!
1. Interview with Microsoft Hong Xiaowen: In the next decade, AI applications will become a battleground for soldiers.
2. Interview with Yu Kai, Horizon Robotics Technology: I am not alone in fearing the industry bubble!
3. Interview with Kewo Si Qian Dongqi: Artificial intelligence landing for a decade, you are cool does not mean that you can survive.
4. Interview with Yun Zhou from Technology Week: A Unique "Fighting Method" for the "National Team" Facing Face Recognition.
5. Exclusive interview with U Thant Technology Wu Gansha: Sharing an unmanned vehicle with L5 autopilot in 2021 is very difficult.
6. Interview with You Jian must choose Zhou Jian: The popularity of humanoid robots will take 10 years, and 90% of entrepreneurs will die.
7. Interview with Lenovo: You used to be an AI crook. Now I hope AI is only a "slow cow."
8. Interview with the Fourth Paradigm Dai Wenyuan: When did AI's Windows era arrive?
9. Interview with Intel Song Jiqiang: If robots replace your job, learn to be flexible and coexist with AI.
10. Interview with Tucson's Future Hou Xiaodi: Those who can't make profits but claim to want to change the world are either deceiving themselves or lying to others.
11. Interview with Gowild Qiong Nan: I hate hardware being given away for free, all payment should be respected, and low-cost robots will flood the market this year.
12. Interview with Codelong Technology Huang Dinglong: Artificial intelligence has been installed for more than 60 years, and now the core is to make money.
13. Interview with Microsoft Huang Xuedong: What is the technological outlook for voice interaction?
14. Interview with Daxie Huang Xiaoqing: When will the robot's 1G era come?
15. Interview with Li Zhifei: Artificial intelligence will become an extension of human intelligence.
16. Interview with ROOBO Liu Yingbo: How do I walk past those pitfalls in the robot market?
17. Interview with English fluently said that CEO Wang Hao: Why does Chinese learn English so effectively?
18. Interview with Baidu Ventures Liu Wei: Which AI companies will die in the bubble?
19. Dialogue with Hasabis: The story of AlphaGo's farewell to Go AI has just begun.
20. Interview with Jürgen: AI has long been aware of where the industry will go in the next decade.
21. Interview with Nico: How far is the use of brain-computer interface to download consciousness to achieve immortality?
22. Interview with Yang Qiang: Alpha Dog is God? It also has a fatal weakness.
23. Conversation Yuval: AI works irreversibly for humanity and wisdom will control the world
24, Interview Peng Jun: L3 is not suitable for commercial vehicles to consider the scene application
25, Dialogue Li Deyi: "Drive the brain" into the car traffic jam will become history
26. Dialogue View: DoerOS Do Android Play in the Voice Interactive Era?
27. Interview with Xie Dianxia: Do not just stare at the speaker speech interaction will refactor APP
28. Interview with Jian Renxian: How to Save the Mentally Retarded Robot with Emotional Interactions
Breaker Mcb,Mcb Circuit Breaker,32A Circuit Breaker,Miniature Circuit Breaker
ZHEJIANG QIANNA ELECTRIC CO.,LTD , https://www.traner-elec.com