- US - English
- China - 简体中文
- India - English
- Japan - 日本語
- Malaysia - English
- Singapore - English
- Taiwan – 繁體中文
Invalid input. Special characters are not supported.
Update: This article was originally published earlier in the evolution of autonomous vehicle technology. Since then, the industry, and our thinking, has continued to move forward. For the most up-to-date perspective on what’s changed, check out our latest insights on autonomous drive.
Autonomous cars are evolving from a futuristic dream to a modern reality, and as the technology matures, personal and public transportation will be forever transformed.
Eventually, driverless cars will take human motorists out of the equation entirely, banishing dangerous drowsy, impaired, and distracted drivers from roadways. Nearly 40,000 people in the United States died on the roads in 2017, and according to the National Highway Traffic Safety Administration1 (NHTSA), about 90 percent of those accidents were due to human error2.
But what’s behind the technology of autonomous driving, how exactly is a driverless car safer, and what will it take to get us from A to B without needing to watch the road?
Artificial intelligence drives autonomous vehicles
For a car to be autonomous, it needs to be continuously aware of its surroundings — first, by perceiving (identifying and classifying information) and then acting on the information through the autonomous/computer control of the vehicle. Autonomous vehicles require safe, secure, and highly responsive solutions which need to be able to make split-second decisions based on a detailed understanding of the driving environment.
Understanding the driving environment requires an enormous amount of data to be captured by myriad different sensors across the car, which is then processed by the vehicle’s autonomous driving computer system.
But how does all of this happen alongside every other function a car performs to keep it running? That’s where AI comes in.
For the vehicle to be truly capable of driving without user control, an extensive amount of training must be initially undertaken for the Artificial Intelligence (AI) network. The network is trained to understand how to see the road and its surroundings, understand what it’s seeing, and make the right decisions in any imaginable traffic situation.
Today, what’s under the hood of a self-driving car is just as powerful as some of the highest performing supercomputers from just a few years ago.
The autonomous vehicle is projected to contain more lines of code than any other software platform that has been created to date.
In today’s landscape, the average high-end autonomous vehicle is expected to run on 300 million to 1 billion lines of code, nearly 1,000 times more than the Apollo 11 moon landing. To handle this, premium autonomous platforms will require roughly 2 TB of storage and memory bandwidth exceeding 1 TB per second (utilizing technologies like GDDR6 or HBM) to support the real-time compute performance necessary for Level 3 (conditionally automated) and Level 4 (highly automated) driving.
A self-driving car’s AI system requires a continuous, uninterrupted stream of data and instructions in order to make real-time decisions based on complex data sets. Successful self-driving vehicles exist on the road today.
However, the success of many of these early vehicles is the result of repeatedly driving the same route consistently over many days. This method allowed the network to learn every detail of the route and generate high-resolution maps that were then used as a key part of the self-navigation system. This teaches the driverless car where to go, but what about traffic, pedestrians and the other potential real-time hazards?
This generally restricted range of operation is referred to as geo-fencing, and reflects the approach that early self-driving vehicles are embracing in deploying vehicles that are truly driverless. While geo-fencing can lead to a solution that can work over a limited route, an autonomous vehicle with heavy reliance on geo-fencing in one part of the world may not function as well in another.
Are driverless cars Safer?
Memory and storage, the unsung heroes in autonomous driving
Whether it’s the memory subsystem associated with sensor fusion processing, path planning, or the storage subsystem utilized by the black-box data recorder, these components all play a key role. The wide range of memory and storage devices all work together to get us closer to a future where autonomous driving is not only a possibility, but the norm, including:
- Solid-state Drives (SSDs)
- NAND flash
- NOR flash through low-power DRAM
- GDDR6
According to Robert Bielby, Micron’s Senior Director of Automotive System Architecture, high performance AI computers employ deep neural network algorithms, which enable autonomous cars to drive better than human-driven cars4.
“You’ve got a host of different sensors that work together to see the entire environment in 360 degrees, 24/7, at a greater distance and with a higher accuracy, than humans can,” Bielby stated. “Combined with the extreme compute performance that today can be deployed in a car, and you have a situation where it is possible for cars to do a far better job of driving down the road with greater safety than we can.”
Imagine a scenario where a car slams on its brakes while on a busy freeway. Through the introduction of Vehicle to Vehicle and Vehicle to Infrastructure (collectively called V2X) communication, this single event could be wirelessly transmitted to all cars following the lead vehicle. This would allow them to understand the situation at hand and proactively slow down and brake to avoid an accident.
5 stages of automation
High-Speed memory is an essential component of autonomous driving
Remember the statistics that about 90 percent of U.S. fatal vehicle accidents being due to human error? Humans are distracted easily, but can make snap decisions when faced with unexpected hazards. Computers, on the other hand, don’t get distracted by the things that pull humans' attention away from the road, like a flashy billboard or a favourite song on the radio. More so, computers reaction times are faster and more consistent than human drivers.
Understandably, safety is of utmost concern when it comes to autonomous vehicles. The attention to safety goes well beyond backup hardware systems to minimize mistakes, self driving cars also include an infrastructure to enable vehicles to communicate with each other and their surroundings. This connected system of sensors and backups is governed by laws that require higher safety standards as vehicles become more autonomous.
What are the levels of autonomous vehicles?
The NHSTA has established clear guidance relating to the development and deployment of autonomous driving technologies, via a series of levels.
These levels identify the level of control a person has over the vehicle, compared to a computer:
- Level 0: No automation (a standard car)
- Level 1: Driver assistance (single function support such as steering or braking)
- Level 2: Partial automation (the driver must keep a hand on the wheel
- Level 3: Conditional automation (the driver may be required to take over at any time)
- Level 4: High automation
- Level 5: Full automation
Currently, the majority of Advance Driver Assistance Systems (ADAS) are Level 2 capable and are based on computer hardware using memory devices that are relatively mature and low bandwidth.
As driverless cars reach increasing levels of autonomy, the importance of memory technologies, both from a safety and performance perspective, moves from the back to the front seat of the car.
Where historically the personal computer was recognized as the driver of the sector, it’s now recognized that the automotive industry is going to be the leading driver of future memory technologies. Today, some of the leading autonomous platforms are already illustrating this point.
Nvidia’s recently announced state-of-the-art Pegasus computing platform3, developed specifically for autonomous driving, is based on the industry’s highest performance, leading-edge DRAM technologies. Altogether, the Pegasus platform delivers more than 1 TB per second of memory bandwidth in order to deliver Level 5 performance.
Data is the fuel of autonomous vehicles
The importance of GDDR6 in the future of autonomous driving, and how Micron plays a part
Micron is an industry leader in both automotive memory solutions, and graphics memory solutions GDDR5x and GDDR6. The bandwidth associated with GDDR6 memories enables higher levels of autonomy to be realized in a practical footprint that is viable for deployment in the automobile. An autonomous compute platform that’s rich in memory bandwidth will have the ability to allow for continued evolution and refinement of autonomous driving algorithms.
Robert Bielby commented: “What you’ll see is that there will be improvements in algorithms that will occur over time,”. “But those will be deployed as software upgrades, similar to the way your smart phone receives a regular update to an application or operating system.”
The continued evolution of autonomous vehicles involves many iterations of varying capabilities over the next decade. This requires careful management of human-machine engagement, ensuring that drivers clearly understand what level of autonomy is available at any particular time and what the responsibilities are for “hands-on” and “eyes-on” operation.
GDDR6 is a fundamental technology that provides the essential memory bandwidth that fuels artificial intelligence compute engines. It underpins the capability of autonomous vehicles to act responsibly and enhance safety in accordance with the industry safety standards as governed by NHSTA.
GDDR6 is a high-performance memory technology that is qualified to operate in the high temperatures and harsh conditions that can be associated with driving.
AI is a critical technology required to realize autonomous driving. To handle human-like decision-making, AI-driven cars need massive computing power supported by innovative memory and storage systems.
As self driving vehicles drive more need for speed from memory, Micron’s more than 25-year commitment to driving the automotive industry forward will, deliver the right level of performance needed to win the race.
Sources and References:
1. National Highway Traffic Safety Administration. “NCSA Publications & Data Requests.” 2017, crashstats.nhtsa.dot.gov/#/.
2. National Safety Council. “Distracted Driving.” Injury Facts, 2018, injuryfacts.nsc.org/motor-vehicle/motor-vehicle-safety-issues/distracted-driving/.
3. Nvidia. “NVIDIA Announces World's First AI Computer to Make Robotaxis a Reality.” NVIDIA Newsroom Newsroom, 10 Oct. 2017, nvidianews.nvidia.com/news/nvidia-announces-world-s-first-ai-computer-to-make-robotaxis-a-reality
4. Bielby, R (2018, February 28). Personal Interview
