Latest figures for tech giant's self-driving test cars also show there were 272 failures across 424,331 miles between September and November 2015

New figures published by Google about its autonomous vehicle development reveal that test drivers had to re-take control of its cars a total of 13 times over two months in near-miss incidents.

Drivers were also handed back control thanks to 272 recorded technical issues, comprised of both software and hardware failures, illustrating how much work is still to be done before Google’s self-driving vehicles can reliably and safely operate unaided.

The figures were collected between 24 September and 30 November 2015, as ordered by the California’s Department of Motor Vehicles, and account for a total of 424,331 test miles covered by Google’s fleet, which is made up of modified versions of the Lexus RX450h and electrically-powered Google Koala test cars.

Of the recorded incidents, Google reports that 69 disengagements were due to concerns for safety, although only 56 of those account for real-life situations. The other 13 were ‘simulated contacts’, events that are digitally replayed versions of previous disengagements on Google’s online simulator. The simulator drives more than three million virtual miles each day and is said to be able to predict the reaction of human drivers, cyclists and pedestrians to determine whether a test driver’s intervention was necessary.

In quarter four of 2014, Google’s cars covered an average of about 600 miles per disengagement. That figure improved substantially to about 2900 miles a year later, although that increase is largely attributed to increased technical reliability. Safety-related disengagements actually increased in quarter three and four of 2015, with the average miles per incident dropping from about 9000 in Q2 2015 to 6000 in Q4.

Google insists these numbers aren't entirely representative of safety, saying "the 56 events would very likely not have resulted in a real-word contact if the test driver had not taken control".

Google also points out that disengagements are necessary in order for it to ensure all possible scenarios are accounted for. It suggests that increasing the number of miles its test cars cover, and therefore increasing the number of software fixes it introduces, will help to bring the number of safety-related disengagements down.

The results make it clear that a true self-driving car that can navigate through all driving scenarios is still a long way off. Aside from reliability and safety-related disengagements, Google’s test drivers still have to take control when unfamiliar road circumstances, such as road works, appear.

Google’s report appears to support the words of Renault-Nissan boss Carlos Ghosn, who recently argued that we won’t see ‘true’ self-driving cars before the year 2025. His comments came in response to Tesla’s Elon Musk, who proclaimed that his brand would be the first to produce an autonomous car.

Our Verdict

Lexus RX 2009-2015
The RX model has been around for just over half Lexus's life

The Lexus RX has headline-grabbing emissions, but do they stand up to scrutiny?

Join the debate

Comments
11

13 January 2016

drop this totally "autonomous" nightmare and spend the R&D on EV's

 

Hydrogen cars just went POP

13 January 2016

If the distance between re-engagement of the driver is short then the driver must always be concentrating on the road, ready to re-engage any moment. If the distance is long then the driver will be ignoring everything until suddenly the car says "help!". Who knows what the driver would do at that point? He/she might be asleep, reading, texting, anything that demonstrates (ultimately misplaced) trust in the technology. Which is safer?

13 January 2016

424,000 miles and only 13 near misses? I would say that's pretty good, especially when considering that many of those near misses are caused by other road users not the Google car.

13 January 2016

I wonder how much would have been spent on r&d by then, before a single car has been sold. And yet no journalist has asked the question of approximately this extra will add to the price of a focus

 

Hydrogen cars just went POP

13 January 2016

Those cars need a 100% fail safe speed-signs recognition system. Some Volvos have those fitted but it is just not working well enough at the moment which is going to be a problem they'll have to overcome before launching their own self-driving models.

13 January 2016

Nothing to worry about here. I'm sure similar things happened before planes were allowed to fly hundreds of people around and land them in bad weather. You test and test and test until the problems become insignificant. It amazes me we've got this far this soon.

14 January 2016

I totally agree. It wasn't that long ago that a car being steered remotely was news. If all cars were self driving the roads would be even safer.

14 January 2016
Beebrave wrote:

I totally agree. It wasn't that long ago that a car being steered remotely was news. If all cars were self driving the roads would be even safer.

You may well be right old son but for 99.9% of the world driving is part of your life style, pleasure and fun. The other 1% covers those idiots who shouldnt be driving anyway

what's life without imagination

14 January 2016
5wheels wrote:
Beebrave wrote:

I totally agree. It wasn't that long ago that a car being steered remotely was news. If all cars were self driving the roads would be even safer.

You may well be right old son but for 99.9% of the world driving is part of your life style, pleasure and fun. The other 1% covers those idiots who shouldnt be driving anyway

The point I was trying to make is that if all of the cars during the trial had been self-driving, then there would have been fewer accidents. PS. 99.9 plus 1 = 100.9. Old son.

14 January 2016

Don't know about you, but 99.9% of my driving certainly isn't fun. I would happily let the car drive me on certain regular journeys while I tooka nap, did some work or made phone calls. But I would certainly not be watching the road, and probably not able to retake control at a moment's notice. It would need to be fail safe.

Pages

Add your comment

Log in or register to post comments

Find an Autocar car review

Driven this week

  • Citroen C11.2 Puretech 82 Furio
    First Drive
    29 September 2016
    Citroën's city car gets a new sporty-looking trim level, adding visual adornments, but no premium for the 1.2-litre Puretech triple we're driving
  • Mercedes C350e Sport
    First Drive
    28 September 2016
    Petrol-electric C-Class is a surprisingly well-priced alternative to a diesel but not the greatest example of the new ‘PHEV’ breed
  • Car review
    23 September 2016
    Aston kicks off its ‘second century plan’ with an all-new turbo V12 grand tourer
  • Ford Ka+ 1.2 Ti-VCT 85
    First Drive
    22 September 2016
    A rounded, refined and well-sorted bargain supermini – once you’re used to the confusing role redefinition imposed on the once-cheeky Ka
  •  Maserati Ghibli Diesel
    First Drive
    22 September 2016
    Maserati releases another range of updates for its range best seller, the Ghibli. We've driven the diesel version, but there's little improvement on before