Making autonomous vehicles excellent defensive drivers

If you live in a bustling metropolis with aggressive drivers battling rush hour traffic during normal times, defensive driving may be your default auto-pilot mode behind the steering wheel. But as the automotive industry gears up for autonomous driving, how will self-driving cars will fare versus the human driver? 

Autonomous vehicles (AVs) will depend on a host of advanced driver assistance systems (ADAS) and vehicle-to-everything (V2X) communication technologies to steer their way safely forward, because when it comes to pushing the cause for self-driving cars, too much is at stake for car makers, and neither human nor computing error can be tolerated. 

AV makers’ efforts are yielding results. In their latest annual AV testing data released in February this year, the California Department of Vehicles (DMV) data revealed that the number of disengagements dropped by a significant 60 per cent.

The DMV defines disengagement as “how often their vehicles disengaged from autonomous mode during tests – whether because of technical failure or situations requiring the test driver/operator to take manual control of the vehicle to operate safely.”

While the DMV’s data is a good indicator that the AV industry is progressing, the road towards totally hands-off and eyes-off autonomous driving is still arduous, and much more so for level 5 autonomy – when the steering wheel will make way for a plush passenger seat.

The AV will be armed with an impressive array of sensors – radar, lidar, camera, working in tandem with V2X communication to drive itself. The objective is to create the ideal self-driving car that can defend its passengers against a multitude of scenarios – from errant fellow human drivers, to jaywalking pedestrians, bad weather, and more.

One of the noble objectives of autonomous driving technology is to someday achieve zero road accidents. A very tall order since 1.35 million people die on the roads every year. 

This is why developers of self-driving technology will need to thoroughly verify their designs by testing sensor response protocols against multiple traffic scenarios, and pre-empt all corner cases. 

Bringing automotive test from the road into the lab

AV makers and their test partners are investing in both hardware and software to develop and test ADAS applications. These will replace human eyes, ears, limbs and vital brainwork with a plethora of sensors and algorithms that will beat the average human reaction time of 1.6 seconds to slam on the brakes, to a mere 0.5 seconds.

To achieve these capabilities, AVs will employ a variety of sensor technologies, including camera, radar, lidar or ultrasound. Testing these systems for individual performance and interoperability presents a whole new world of challenges, as each AV will have distinct configurations and combinations that need flexible modelling in test systems.

Besides emulating a myriad of scenarios to test the responses of individual devices, systems and entire autonomous vehicles, AV makers must also ensure they keep up to speed with evolving industry and regulatory conformance standards.

For example, are the software and hardware platforms compliant to the latest 3GPP standards, including 5G New Radio (NR)? Can vendors quickly and accurately validate C-V2X and 5G chipsets and devices, or perhaps turn to third party test expertise to qualify their product development. These are some of the critical questions they need to ask before AVs could be fully embraced and safe enough for widespread adoption.