IEEE Consumer Electronics Magazine - September 2018 - 24

CHANGING ENVIRONMENTAL CONDITIONS

Modern vehicles are becoming
increasingly connected with
a lot of different systems,
such as Wi-Fi, near-field
communication, and V2X.
AUTONOMOUS VEHICLES
Next-generation ADASs using sensor fusion and V2X communication are paving the way for autonomous driving. The Society of Automotive Engineers (SAE) J3016 standard [28] defines
six different levels of driving automation for on-road vehicles
(see Table 1). A vehicle is categorized as level zero if there are
no ADASs assisting the driver in handling steering and acceleration/deceleration and everything is handled manually by the
driver. Level one vehicles consist of ADASs assisting the driver
in handling either steering or acceleration/deceleration under
certain cases with human driver input. ADASs in level two
vehicles handle both steering and acceleration/deceleration
under certain environments with human driver input. In general,
in lower-level vehicles (levels zero to two), the driver monitors
the driving environment. In contrast, ADAS monitors the driving environment in higher-level (levels three to five) vehicles.
Modern vehicles with the top-of-the-line ADASs, such as the
2016 Tesla model S, are level three, where multiple safety systems are handled by the system, but the driver intervenes when
needed. Level four vehicles handle multiple safety systems and
operate in a wider range of environments. Level five automation
is the end goal of autonomous driving, where all of the systems
in the car are operated by the ADAS, under all driving conditions (such as snow-covered roads and unmarked dirt roads)
and would not require any human intervention. This, however,
still requires significant advances in multiple areas, such as sensor technology, computing systems, and automotive networks.

CHALLENGES WITH ADASs
Despite significant advances in the field of ADASs, several
important challenges remain to be overcome.

Table 1. SAE J3016 levels of driving
automation [28].
Monitoring of
Driving Environment

SAE Level

Definition

Zero

No automation

One

Driver assistance

Two

Partial automation

Three

Conditional automation

Four

High automation

Five

Full automation

24 IEEE Consumer Electronics Magazine

One of the major problems with today's ADASs is that the performance of the system is significantly impacted by changing
environmental and weather conditions. For example, visionbased ADASs have issues with sensing during rainy and
extreme lighting conditions (too dark and/or too bright) [30].
One of the possible solutions to this problem includes sensor
fusion, by relying on other sensor data depending on the
weather conditions, e.g., relying on the camera and radar during low light conditions while using the camera and lidar during other times for accurate distance estimation. The inclusion
of V2I and developing cost-effective smart roads could help
mitigate this issue.

RESOURCE-CONSTRAINED SYSTEM
Embedded systems used in ADASs have a requirement for
low power consumption. This is because ADASs involve running several complex algorithms that result in high power
consumption and thermal dissipation. Due to the limited availability of energy in vehicles, it is essential to minimize the
power consumption of the embedded system used in ADASs.
Using more energy-efficient hardware than conventional general-purpose central processing units is important, which is
why emerging ADAS hardware must rely on graphics processing units, digital signal processors, image signal processors, etc., that are customized to reduce power consumption
for ADAS applications. Moreover, as the embedded systems
for ADAS operate in real time, they have strict timing constraints, which establishes a latency minimization requirement. Hence, optimized hardware and software that results in
minimal power consumption and greater performance (lower
latency) predictability are highly desired in an ADAS.

SECURITY
Modern vehicles are becoming increasingly connected with a
lot of different systems, such as Wi-Fi, near-field communication, and V2X. This enables the vehicle to sense and receive a
variety of information but also makes it more vulnerable to
attacks. Many vehicle hacks have been demonstrated, e.g.,
researchers in [7] used onboard diagnostics (OBD-II) to hack a
GM vehicle. In [29], the telematics system in a Jeep Cherokee
was hacked to accelerate, brake, and kill the engine. This problem is aggravated in ADASs and autonomous driving. Preventing hackers from gaining access to connected vehicles is
becoming increasingly important. This involves securing both
in-vehicle networks and external communication.

GEOSPATIAL CONSTRAINTS
Human driver

System

september 2018

Many of the modern ADAS solutions being developed are
tested within a geographic location or a group of locations
where they are sold. This limits the ADAS to one or a certain
group of geographical locations. This is because not all countries (or some states in a country) adhere to the same sign and
road conventions uniformly, which makes ADAS algorithms
that are often trained under one location hard to work
efficiently in other locations. There is a need to improve

Table of Contents for the Digital Edition of IEEE Consumer Electronics Magazine - September 2018