Automotive ADAS Enable Autonomous Vehicles
As the automotive industry pushes forward to the distant reality of fully autonomous vehicles, demand for Advanced Driver Assistance Systems (ADAS) is growing rapidly. The integration of automotive ADAS technology into an increasing number of new vehicles has helped make partially automated driving (Level 2 autonomy) a reality for a growing number of drivers. Continued improvements in the technologies that comprise ADAS have helped reduce cost, allowing some features to migrate from high-end vehicles to more mass-produced vehicles.
ADAS is already one of the fastest-growing segments in automotive electronics as it can be considered to serve as the bridge from non-autonomous to fully autonomous vehicles. The closer we get to Level 5, fully autonomous driving, the more robust and comprehensive automotive ADAS will become.
Components Powering Automotive ADAS are Advancing
ADAS is commonly understood to include five key components:
- Sensors: Commonly used in some of today's connected devices, some sensors have become significantly lower in cost thanks to innovative manufacturing techniques and the growing volume of usage. When connected to networks or the cloud, sensors yield real-time, actionable data that can power ADAS. However, most of these devices have limited range and bandwidth and must be improved and fused with other sensor data to power a Level 5 Autonomous Driving Experience.
- Processors: With the increasing requirements for processing speed in ADAS applications, processors are used for everything from building a real-time 3D spatial model of a car's surroundings to calculating proximity and threat levels based on the environment. However, due to the length of qualification processes in the automotive industry, the adoption of advanced manufacturing technologies are approximately six years slower than the average smartphone processor.
- Software: Automotive companies increasingly rely on software. After all, the software makes the hardware work. The hardware can be significantly simplified with software, especially when machine learning and artificial intelligence can be implemented to manage different situations. The development effort behind software is huge in the industry.
- Mapping: The ADAS mapping function stores and updates geographical and infrastructure information gathered via vehicle sensors to determine its exact location. This function maintains the information and communicates it to system control even if GPS coverage fails. Since automotive OEMs and other players search for lower-cost options, third-party applications generally meet this demand.
- Actuators: The electrification of the actuator system has been a major enabler of ADAS because it has facilitated interaction with other electrical components in the vehicle. With processors to analyze data from vehicle sensors, the ADAS system can make decisions executable by actuators. This system allows everything from electric power steering to autonomous acceleration and braking.
A Compelling Use Case: Driver Monitoring
Driver and passenger safety is always first in the automotive sectors. With all the major components we discussed earlier, new vehicle interface features have been enabled for automotive ADAS. One example of this is around the next generation in-car sensing technology work eyeSight Technologies is doing regarding driver monitoring, in partnership with Jabil.
Driver distraction and drowsiness are two of the major contributors to accidents and fatalities. With all the enhanced features and entertainment content entering the vehicle, the driver must still focus on driving. These in-car sensing technologies help do that by monitoring whether the driver is distracted or sleepy.
The technology uses machine learning computer vision software to monitor several parameters around the driver’s head and face such as:
- Head pose
- Eyelid position and movements
- Iris and gaze direction
The system can also recognize driver’s faces and estimate their gender and age.
In one use case, if the driver is experiencing a high PERCLOS (the percentage of time the eyelids are closed), the system can take other parameters into account to determine the driver's state of drowsiness. Then, car manufacturers have an opportunity to further personalize a response system that may include rattling the seat or sounding an audible alarm to keep the driver alert and reduce the risk of an accident.
Driver Monitoring is also an indispensable feature as we move through the implementation of ever-increasing levels of automation and autonomy. These automatic systems will need to assure themselves that an awake and attentive driver is at the wheel in order to transfer control back to the driver.
Connectivity is a Critical Element in the Future of Automotive
In a 2018 survey sponsored by Jabil, Automotive Product Development and Launch Cycles, 53 percent of respondents indicated that better connectivity was the primary driver of innovation.
Subscribe to the Jabil Blog
Sign up for weekly updates on the latest trends, research and insight in tech, IoT and the supply chain.
Automotive connectivity is a critical element for the future of automotive because it will help pave the way for the autonomous vehicle. One key aspect is for vehicles to talk to each other (V2V) and to talk to the infrastructure (V2I). There is a strong push to get connectivity features in every new vehicle to enable elements like entertainment content and streaming, but more importantly an autonomous world.
4G technology is limited in its bandwidth and ability to cope with copious amounts of data. For example, in high-density areas with a high density of connected vehicles all demanding the same bandwidth from the network at the same time, 4G would not be able to support all the data. Therefore, mobile technology progress is needed to enable full high bandwidth connectivity for densely populated areas. In addition, 4G coverage doesn't even extend to all rural areas.
5G may be the answer, however the standards for the technology aren't defined yet. 5G is recognized as a high-bandwidth, next-generation technology that will be a significant evolution over 4G, but even a split-second latency would remain a concern for the automotive industry. 5G could potentially enable new autonomy features, but it certainly won't be able to cover everything.
The Average Age of Vehicles on the Road Matters
In addition to the required upgrades necessary in wireless connectivity and infrastructure, there are concerns around vehicles that are currently on the road. Today's car owners are keeping their vehicles for much longer than in the past, averaging a record 11.6 years in the U.S. alone. When we examine these trends in Europe, we see the average age of cars on the road lasting from 7.7 years in the U.K. to a high of 13.5 years in Greece.
With more than 1 billion cars on the road around the world, these numbers create a fairly risky situation for the autonomous vehicle. In a future filled with autonomous driving, all vehicles must have the ability to talk to each other and the environment around them. These cars will need to be "retired" to allow a safe driving environment. Regardless, this is another reason implementation of level five autonomous vehicles are going to take at least a couple of decades.
In Automotive, Safety is One Thing, Cybersecurity is Another
In a September 2017 episode of the podcast Hackable, the host Geoff Siskind pairs up with the author of "The Car Hacker's Handbook" to showcase how to hack a car. With the use of a black toolbox, the hacker is successfully able to control features of the car through its diagnostic port. Hackers could utilize tiny devices that grant access to the car from anywhere in the world, via cellular capabilities.
A 2018 survey by Morning Consult shows that 67 percent of Americans are somewhat or very concerned about cyber threats to driverless cars. The ask is clear: automotive companies must prioritize cybersecurity the way consumer electronics do. I think we will see a lot more manufacturers focusing on this aspect to provide a safe automotive ADAS experience.
Consumer Technology Companies Enter the Arena
The growth of automotive ADAS and increased R&D spending on autonomous driving has attracted many high-tech companies that have not traditionally participated in the industry. For companies that have historically participated in the automotive industry, these companies present an opportunity to expand ADAS capabilities via partnership and/or acquisition.
Seventy-six percent of the 2018 Automotive Product Development and Launch Cycles survey respondents believe that the new players in the industry have shortened go-to-market. But more importantly, 99 percent see these high-tech companies creating more opportunities for the automotive market, whether that be in delivering a different customer experience or becoming more data-driven.
While Level 5 autonomous vehicles are still a distant reality, ADAS is progressively shortening the distance. In the meantime, we must focus on our capabilities around infrastructure and connectivity to enable a world where all of this is possible.
Download the Automotive Product Development Trends Survey Report
Insights from over 200 automotive OE and Tier 1 decision-makers on technology adoption, opportunities and challenges.