New Straits Times

COMPUTER CHAUFFEUR GETTING CLOSER

AI is quietly making driving safer, and features like speechreco­gnition and other safety applicatio­ns are now found in new cars, writes

- NORMAN MAYERSOHN

COMPUTERS may one day be trustworth­y replacemen­ts for drivers. The secret sauce of those computers’ becoming our chauffeurs is the ubiquitous force of artificial intelligen­ce, which is already active in virtual personal assistants and a bank’s customerse­rvice chat bot.

But it’s the automobile where AI could have a critical role for the greatest number of people.

Few AI applicatio­ns carry the responsibi­lity of automotive safety systems, where actions must be carried out in nanosecond­s and an ill-considered response may have costly consequenc­es.

Systems that marry microproce­ssors, sensors and software to make fully driverless cars possible are in the advanced stages of developmen­t, but experts say the leap from today’s computer-assisted driving to fully automated motoring that may render humans optional remains considerab­le.

Still, AI is already quietly making driving safer. Beyond the applicatio­ns now found in new cars, typically in convenienc­es like the speech-recognitio­n feature of infotainme­nt systems, are the subsystems that make up the packages of safety features common largely in luxury vehicles.

Enhancemen­ts like night vision, automatic emergency braking and lane keeping all depend on processors that use sensors and computer instructio­ns to warn drivers of danger or act to avoid collisions.

The term AI, coined in the 1950s, is something of an unfortunat­e choice, at least in terms of the automobile. The intelligen­ce within cars — their ability to learn and to apply that knowledge — is far from artificial; it is hard-earned. It comes down to capable electronic­s, sensors and, especially, extensive training.

“Training is like teaching our kids to drive, with rules, absolutes and best practices,” Glen De Vos, chief technology officer at Aptiv. “Some rules are embedded in the system — never out-drive the free space around the vehicle, obey road signs — but as you move up the spectrum toward accident avoidance, a predictive capacity is necessary.”

Aptiv, a spinoff from Delphi Automotive, an auto industry supplier, builds the data sets that a trained AI system depends on. Most of that data is accumulate­d on the road, acquired in videos to create the basic knowledge bank that computers draw on.

Data is also collected by radar, or lidar, its light-beam equivalent. A high degree of refinement of the data, covering every possible situation, is vital to assuring that the safety systems don’t issue excessive warnings, an annoyance that may lead a driver to ignore such signals.

The collecting of data to inform automotive AI systems will be greatly improved by a coming generation of connected cars — 50 million communicat­ing wirelessly with each other by 2020 — according to Sachin Lulla, IBM’s automotive leader.

Some of the tasks where AI takes an important role happen inside the car. Driver monitoring is a major component of advanced safety systems, with cameras mounted in the dashboard watching eye and head positions and even pulse rate through a steering-wheel sensor. The concept, IBM says, is to add context — the driver’s condition and degree of engagement — to complete the picture of the situation in the car and on the road.

One of AI’s strengths is simple object recognitio­n. But when a problem becomes more complex, like when an obstacle is detected in the road during a snowstorm, the advantage of using AI is its ability to solve problems that are otherwise too complex for existing systems. AI gets answers a lot faster.

The computing power it takes to operate a car with self-driving capability is staggering. A graphics processing unit to perform object recognitio­n works at a computer speed of a trillion floating-point operations per second. The main processor’s performanc­e is measured in millions of instructio­ns per second.

While automakers have embraced the goal of eliminatin­g all fatalities, deploying AI and autonomous vehicles can go only so far towards achieving that. A drunken driver of an older car could blow through a stop sign, and road conditions will be responsibl­e for some collisions.

NYT

 ??  ??
 ?? NYT PIC ?? A vehicle testing a new A.I. algorithm in Auburn Hills, Michigan, the US. When an obstacle is detected, a coloured box appears on the screen. A green box indicates pedestrian­s, while red boxes indicate cars and trucks. Blue indicates a clear path.
NYT PIC A vehicle testing a new A.I. algorithm in Auburn Hills, Michigan, the US. When an obstacle is detected, a coloured box appears on the screen. A green box indicates pedestrian­s, while red boxes indicate cars and trucks. Blue indicates a clear path.
 ??  ??

Newspapers in English

Newspapers from Malaysia