When RoboTaxis with L4 intelligent driving capabilities began to run all over the streets, people began to look forward to the debut of L5 vehicles.
As we enter 2021, intelligent driving technology is being implemented at an accelerated pace.
Tesla FSD, NIO NOP, Xpeng NGP, and the long-awaited Ideal NOA, the L2-level assisted driving services developed by new car-making forces have been implemented in recent years. L4-level autonomous driving systems led by technology companies such as Baidu, Pony.ai, and WeRide have also been deployed in multiple key cities in the name of RoboTaxi for regional trial operations.
However, many people have questions: when and in what form will L5, which represents the highest level of autonomous driving, finally appear on the stage?
At the 2021 Baidu World Conference on August 18, CEO Robin Li announced the L5 autonomous driving platform called Auto Robot.
Baidu's understanding of L5: a robot in the form of a car
"Automobile robot" as a keyword was actually "preheated" a month and a half ago.
At the World Artificial Intelligence Conference in early July this year, Robin Li expressed his views on the future development trends of automobiles: cars in the future will be more like robots.
Just from the appearance at first glance, you can feel what Baidu wants to tell everyone urgently: although they both have four wheels, car robots are completely different from cars.
The biggest feature of the car robot that can be seen by the naked eye is that it has no windshield. All windows are located on both sides of the car body, and there is no observation window facing the front and rear of the car.
A multi-function LCD screen was installed at the front of the car where the windshield should have been. During the conference, the screen was always flashing with a status prompt: Car robot, in service.
Since there are no front and rear windshields, there will be no driver's seat, steering wheel, pedal system, and corresponding instrument panel, etc., and even if they are installed, they are purely for decoration. As a masked man who loves red uniforms said, "The foot (steering wheel) is just decoration, and the big guys above don't understand."
Since the control device is removed and there is no driver's seat, the car robot has a surprisingly spacious interior space. After opening the gull-wing doors on both sides through the mobile phone APP control, you can see two zero-gravity seats installed side by side in the back position, a large-size display screen in the front, and an interior space that is so spacious that it is strange. As the experience officer Ms. Jin Chen said, "You can even do a split (in the car)."
All in all, the design of this "car" seems to have exhausted all means to express one meaning: this is not a car driven by humans.
Since the passengers are no longer responsible for driving, they can do whatever they want during the ride, whether it is to use their mobile phones in the zero-gravity seat, watch a movie on the smart console and large curved screen, or even lay down the seat and adjust the lights to take a nap.
The driving job is completely entrusted to AI. After getting on the car, passengers only need to tell the car robot where they want to go and then wait.
Baidu promised the outside world that the car robot is safe. Through the video, we can see that the car robot perfectly completed the entire test route, whether it is unprotected left turns, which are considered the key bottleneck of autonomous driving, or giving way to pedestrians and avoiding other illegal vehicles. During the test ride, Baidu experience officer Jin Chen and CCTV host Wang Jianing even made an impromptu decision to adjust the destination of this trip using voice commands.
Baidu has high hopes for its automotive robots. Robin Li said that his automotive robots can serve people through three capabilities:
First of all, it has L5 autonomous driving capability, which not only does it not require human driving, but is also safer than human driving. Secondly, it has multi-modal interaction capabilities such as voice and face recognition, which can analyze users' potential needs and proactively provide services. In addition, the car robot also has the ability of self-learning and continuous upgrading, and is an intelligent body that can serve various scenarios.
The battle for the L5 track is starting
Looking at the entire industry at present, automotive robots do have their own unique features. Although this is not the first L5 vehicle.
If we only talk about L5 level "autonomous driving", there are quite a few "predecessors" of automotive robots.
Cruise's Origin, ZOOX's "driverless car", WeRide's Mini RoboBus, etc., were all released earlier. Even Baidu itself launched a RoboBus called Apollo driverless minibus in 2018, although its publicly announced autonomous driving level has always been "modestly" classified as L4.
▲The first generation of Apollo
Of course, car robots have their own uniqueness, because if classified by model and purpose, most of the above platforms will be classified as RoboBus. As for the driverless car, it is more like an enlarged special vehicle platform, which can be installed with 2 to 4 seats in a certain configuration and serve as a short-term parking for personnel.
Among all the RoboBus, Origin is the most powerful one.
Origin was developed by Cruise in collaboration with its parent company General Motors and with the introduction of some Honda technology over a three-year period of effort. However, the timing of the announcement of this car was too good to be true. In January 2020, when Cruise held a press conference in San Francisco to introduce Origin to the outside world, it was the eve of the outbreak of the COVID-19 pandemic.
In terms of basic structure, Origin is developed based on GM's pure electric platform and is positioned to have L5 autonomous driving capabilities from the beginning. Therefore, in terms of overall design, Origin is also completely different from traditional vehicles. There is no human-machine control device or vehicle control interface in the car, and there are only passenger seats and corresponding information systems in the car.
In terms of functional positioning, Cruise defines Origin as a public transportation platform. The most common application scenario is public transportation vehicles that run on fixed routes in the city. Origin can be equipped with 4 to 8 seats as needed, and a multi-function display screen for displaying arrival information is installed opposite the seats in the cabin. After the passengers get on the bus, take their seats and fasten their seat belts, they only need to press the orange button on the door, and Origin will automatically start to the next stop.
The reason why Origin is so powerful is that this RoboBus has won the first major smart bus order in history. In April this year, Cruise signed a contract with the UAE and plans to deploy Origin in Dubai in 2023.
Although the first batch of purchases is of an experimental nature, the contract stipulates that once the feedback from use is good, the UAE will increase purchases and expand the size of Dubai's driverless public transportation fleet to 4,000 vehicles by 2030 at the latest.
In order to realize the above ambitious plan, in June this year, General Motors' automotive finance department provided Cruise with a credit line of US$5 billion for small-scale trial production of Origin.
Compared with the high-profile Cruise Origin, Baidu has a rather low-key competitor - the "Apollo" self-driving minibus.
▲Interior of Apollon
The first generation of Apollo was first demonstrated at Create 2018 Baidu AI Developer Conference. Like Origin, Apollo also cancelled the onboard control device, and there were only passengers in the car. On the 5th of this month, Baidu launched the newly upgraded Apollo II.
Compared with the previous generation, Apollon II has made great improvements in hardware. The most typical example is the sensor system - from the original vision + millimeter wave radar system, two 40-line laser radars have been added to enhance the unprotected left turn function. In addition, in order to adapt to more powerful sensors, Apollon II not only adapts to new algorithms, but also increases the total system computing power to 372Tops.
These upgrades have enabled Apollo II to break through the closed areas of the previous generation and initially gain the ability to enter urban roads.
Of course, for safety reasons, Apollo II currently needs to be equipped with a safety officer when driving in cities. Through 5G and the proprietary cloud, the safety officer can remotely monitor the driving safety of the vehicle. If necessary, the vehicle can also be remotely controlled to avoid or emergency stop.
There is no doubt that whether it is Cruise Origin, Apollo II, or WeRide mini RoboBus, the L5 autonomous driving track is taking shape. The emergence of car robots shows Baidu's ambition to make a difference in both public transportation platforms and personal travel.
If we count from the first DARPA Grand Challenge held in 2004, the concept of intelligent driving in the modern sense has a history of 17 years.
▲A historic moment for intelligent driving, with the first DARPA Grand Challenge featuring some of the most bizarre vehicles
Over the past 17 years, from L0 to L5, the research and development routes of commercial intelligent driving technology have evolved into two general paths.
The first is the gradual evolution route. Traditional car companies use existing car platforms as a basis, continuously integrate new sensors, and rely on algorithm iteration to achieve breakthroughs in intelligent driving functions.
The new car-making forces that have emerged in the past decade have chosen to use the relatively high L2 level as their entry point, striving to provide users with usable high-performance assisted driving services as soon as possible.
As for the other path, it is the "revolutionary" route most favored by those technology companies that join the battle.
Previous article:Automotive chip supply cuts and chip companies' acquisitions in the midstream (Part 1)
Next article:SPAC fever for autonomous vehicles (AVs)
- Popular Resources
- Popular amplifiers
- Huawei's Strategic Department Director Gai Gang: The cumulative installed base of open source Euler operating system exceeds 10 million sets
- Analysis of the application of several common contact parts in high-voltage connectors of new energy vehicles
- Wiring harness durability test and contact voltage drop test method
- Sn-doped CuO nanostructure-based ethanol gas sensor for real-time drunk driving detection in vehicles
- Design considerations for automotive battery wiring harness
- Do you know all the various motors commonly used in automotive electronics?
- What are the functions of the Internet of Vehicles? What are the uses and benefits of the Internet of Vehicles?
- Power Inverter - A critical safety system for electric vehicles
- Analysis of the information security mechanism of AUTOSAR, the automotive embedded software framework
Professor at Beihang University, dedicated to promoting microcontrollers and embedded systems for over 20 years.
- Innolux's intelligent steer-by-wire solution makes cars smarter and safer
- 8051 MCU - Parity Check
- How to efficiently balance the sensitivity of tactile sensing interfaces
- What should I do if the servo motor shakes? What causes the servo motor to shake quickly?
- 【Brushless Motor】Analysis of three-phase BLDC motor and sharing of two popular development boards
- Midea Industrial Technology's subsidiaries Clou Electronics and Hekang New Energy jointly appeared at the Munich Battery Energy Storage Exhibition and Solar Energy Exhibition
- Guoxin Sichen | Application of ferroelectric memory PB85RS2MC in power battery management, with a capacity of 2M
- Analysis of common faults of frequency converter
- In a head-on competition with Qualcomm, what kind of cockpit products has Intel come up with?
- Dalian Rongke's all-vanadium liquid flow battery energy storage equipment industrialization project has entered the sprint stage before production
- Allegro MicroSystems Introduces Advanced Magnetic and Inductive Position Sensing Solutions at Electronica 2024
- Car key in the left hand, liveness detection radar in the right hand, UWB is imperative for cars!
- After a decade of rapid development, domestic CIS has entered the market
- Aegis Dagger Battery + Thor EM-i Super Hybrid, Geely New Energy has thrown out two "king bombs"
- A brief discussion on functional safety - fault, error, and failure
- In the smart car 2.0 cycle, these core industry chains are facing major opportunities!
- The United States and Japan are developing new batteries. CATL faces challenges? How should China's new energy battery industry respond?
- Murata launches high-precision 6-axis inertial sensor for automobiles
- Ford patents pre-charge alarm to help save costs and respond to emergencies
- New real-time microcontroller system from Texas Instruments enables smarter processing in automotive and industrial applications
- Questions about the PIOR register of Renesas MCU R7F0C004
- I have a LPV821 chip in my hand, and the teacher asked me to compare the package size
- Document Resources | Upgrade again - i.MX6Q development board manual update
- Share: [G-Non-contact object size and shape measurement] G-Fuzhou University-Non-contact object shape measurement
- Research on FFT Implementation Using FPGA
- The virtual machine Ubuntu system runs C language code and Python code
- ADC_DAC Basics
- [Help] How should I set the pull-up or pull-down resistor for ZYNQ's MIO?
- Show off the development board of ON Semiconductor's Internet of Things Innovation Design Competition!
- How to use Labview to perform secondary development on Ginkgo 2