Published on December 4th, 2017 | by James Ayre0
GM (Cruise) Self-Driving Vehicle Test Drive In San Francisco Illustrates Differences Between Tech & Human Drivers Well
December 4th, 2017 by James Ayre
Last week, we published an article recounting a journalist’s demo drive of GM’s (Cruise Automation’s) self-driving vehicle tech. The drive was conducted in San Francisco and the most humorous bit seemed to be that a double-parked taco truck managed to stump the unit — for a minute or so, after which the backup driver took over instead of waiting around for a move from the self-driving tech.
While the taco truck incident certainly didn’t expose GM’s self-driving tech as being dangerous, it did illustrate how “cautious” the tech was — for the time being, at least — when dealing with novel situations. To put it another way, there are as of yet substantial differences to the way that some self-driving vehicle systems react to odd situations and the ways that humans react to them (of course, human reactions vary widely depending upon the driver as well).
To add to that earlier account (and illustration of that fact), I’m going by highlight another, separate demonstration of GM’s self-driving vehicle tech that was given the same day — this time to a journalist at Recode.
Here are the notes: “For example: We were not 20 seconds into the ride on Tuesday when a dog, still on a leash, went into the middle of the street in front of us and proceeded to go to the bathroom. That’s not something a self-driving car (or even a human) can plan for.
“While a human driver might have gone around the dog, GM’s self-driving car stopped even before the dog was fully in front of it. The dog did its business and then we moved on. For anyone who lives in a densely populated city, the experience was mercifully without a blaring car horn. …
“The Cruise car operated relatively smoothly on the busy streets of San Francisco. According to a readout by the car at the end of our trip, in 2.3 miles we encountered 94 people, 12 bikes and 107 cars. (The official readout did not include the dog.)
“Obstacles included a construction vehicle that pulled out in front of us quickly, and a large semi truck that turned down a narrow street, causing the car to brake and wait for it to pass. That experience in particular helped define the difference between a human driver and a robot.
“As the truck turned toward us, our car waited — it did not use its horn, back up, or move to the side. It just remained stopped as the truck passed within what looked like inches. A human driver could have taken it in any number of directions, but it was interesting to see how the car responded (or in this case didn’t) versus what I thought a human would have done.
“The biggest difference riding in a self-driving car is getting over those gaps in how you would react versus how the car reacts. This self-driving car was overly cautious, which GM warned in advance. It paused longer than you would think at stop signs. It had a few stops and starts during red lights. And waiting 5 to 10 seconds to find a way around something is longer than a human would need to avoid obstacles.”
It’s notable here that all of this was contrasted with a test drive the same writer was given in one of Waymo’s (Google’s) units a year back — which was reportedly far smoother, though was also conducted in a far calmer environment (Mountain View). That fact would seemingly confirm the idea that Waymo/Google is a fair bit ahead of everyone else in development, but the lack of a direct comparison means that implications will remain as conjecture for now (despite official stats supporting Waymo’s lead).
Something else interesting that was revealed in the coverage was that the car was reportedly outfitted with 14 cameras; 5 LiDARs; 3 articulating radars: 8 radars; and 10 ultra-short-range radars — quite an array, and no doubt expensive. You may recall that GM purchased the LiDAR startup Strobe not that long back, but that company’s tech apparently has yet to be integrated in the Cruise system.
As a reminder here, to cap things off, GM is officially aiming to launch self-driving vehicles to the market in 2019.
Have a tip for CleanTechnica? Send us an email: email@example.com