Obstacle sensors, radars and eventually, self-driving cars: The road to Advanced Driver Assistance Systems

Honda Cars India too now offers these ADAS features on the higher-spec variants of its mid-segment sedan, the City, while Tata Motors offers these in the top variants of the Harrier and the Safari Red Dark Edition. These tools have traditionally been offered with cars having a substantially higher price sticker, including Hyundai’s premium SUV Tucson and sedans and utility vehicles sold by German luxury car makers such as Mercedes-Benz and the Volkswagen Group’s Audi.

What’s behind the increasing offerings of ADAS tech?

While this progressive trend of moving down the price bracket is being driven by several factors, including the increasing demand for safer vehicles among Indian consumers and the government’s push for increased road safety, the availability of more affordable ADAS technology is also accelerating this trend.

With the adoption of ADAS technology, car manufacturers say they are helping to improve the overall safety of Indian roads and reduce the number of accidents and fatalities. But ADAS level 2 is where the self driving goal of most carmakers seems to have maxed out, at least for now, despite lofty promises over the years.

Every single year since 2014, Tesla Inc. CEO Elon Musk has promised that the Austin-based carmaker will get its self-driving technology road-ready, with a definitive time-frame for this upshift in passenger car technology. And each of these last eight years, what is evident is that self-driving continues to be as elusive for Tesla as it is for a bunch of other carmakers in the fray that aim to put passenger cars on the roads without anyone behind the wheels.

Not to be undone, Musk, in keeping with the trend, repeated his claim in August last year, with a freshly updated target to boot: that he would get the electric auto maker’s self-driving technology ready “by year-end”. That, predictably, is still an elusive target.

So what exactly is autonomous-driving?

There are five levels in the evolution of autonomous driving: each level describing the extent to which a car takes over the responsibilities from the driver, and how the two interface. So, the levels range from 0 to 5, progressively defining their relative extent of automation. Level 0, “No Automation”, is where the driver controls the car without any support from a driver assistance system – the case for most cars on the road currently.

The driver assistance systems of level 1, like adaptive lane assist or parking assist, are already being offered in a number of top-end cars, while level 2 is a further upgrade that was available only across some models of premium car makers such as steering and lane-keeping assist and remote-controlled parking – examples include Tesla’s ‘Autopilot’ or BMW’s ‘Personal CoPilot’. This is what Hyundai is now offering with its new Verna and Honda with the new City.

Level 3 is where it starts to get tough for carmakers – who have to offer an even greater array of “automated driving” tools where the driver can partly take his eyes of the road, while level 4 stands for “Fully Automated Driving”, where the driver can take his hands off the steering wheel for most of the drive. Level 5 is “Full Automation”, where the car can drive without any human input whatsoever. All of these are still in the testing phase and that’s where the projections made by Musk and other self-driving proponents have to do more of the walking-the-talk.

Why is the self-driving objective still elusive?

When Musk first made his claim over a decade ago, Tesla had been working on its driver assisted technology, which they have branded as autopilot, for about 12 months or so. Success has been patchy ever since.

Problems ranged from jumping red lights, not recognising pedestrians to situational problems like identifying a cyclist who briefly disappears behind a parked vehicle. Ultimately, Tesla began beta testing its full self-driving system only in 2020. But there’s a catch with Tesla’s beta testing: it is doing the testing with regular people driving their Tesla cars on public roads, with each of these drivers having forked out an amount of $12,000 for the privilege of doing so.

Google’s Waymo and Cruise owned by General Motors are among companies that predicted they’d have full self-driving cars by 2020, with only limited success: that too limited to ring fenced, geotagged areas. But none of them are anywhere close to reaching level 5. And there are perils of unleashing less-than-optimally tested tech: In June last year, for instance, 13 Cruise Robo taxis stopped simultaneously on a major arterial street in San Francisco, bringing traffic to a standstill.

Clearly, developing full self-driving cars is way harder than carmakers initially thought. Also, there is the continuing debate on the technology of choice: cameras vs a combination of technologies that include lidar, radar, sensors and camera. While Tesla is relying primarily on cameras, most other car models depend on multiple sensors to feed information into onboard computers, which expends huge amounts of processing power to map what’s going on and forecast what might happen next.

While it is easy for humans to do this kind of prediction based on situational awareness, this can present a complex problem for computers, such as when someone at the side of the road steps off the pavement and disappears behind a parked van for a minute or distinguishing between a red signage on a wall versus an actual stop sign. In the first instance, a human driver might anticipate that the person behind the van could emerge from the other side and step out onto the road.

But for a computer, this predictive capacity is still work in progress. For self driving to work in a country like India, where traffic is extremely haphazard, it will be an even tougher task.

What’s next in terms of the milestones for self-driving?

In 2022, eight years after his first prediction, Musk highlighted the real scale of the problem – that to solve full self-driving, the issue of a mastery over real world AI is a must, which is still a work-in-progress. The rapid advances being made in large language models is a somewhat positive sign, going forward. But all the information the car will need to drive properly has to be aggregated by sensors or cameras and then fed into the computer for it to learn from it, which is possible only with increased autonomous driving miles.

As a result of these gaps, both car hiring majors Uber and Lyft are offloading their self driving divisions. Tesla was sued for failing to deliver on Musk’s long standing promise to develop a fully self-driving car. Also, there is the danger of miscommunication by companies. Drivers using advanced driver assistance systems like Tesla’s Autopilot or General Motors Super Cruise often treat their vehicles as fully self-driving despite warnings.

The Insurance Institute for Highway Safety, a US-based industry funded group that prods automakers to make safer vehicles, released the findings of a survey in October than reported that regular users of Super Cruise, Nissan/Infiniti’s ProPILOT Assist and Tesla’s Autopilot “said they were more likely to perform non-driving-related activities like eating or texting while using their partial automation systems than while driving unassisted.”