In December, two Waymo robotaxies in Phoenix collided with the same pickup truck that was in the midst of being towed, which prompted the Alphabet subsidiary to issue a recall on its vehicles' software.

Last year, two Waymo robotaxis in Phoenix “made contact” with the same pickup truck that was in the midst of being towed, which prompted the Alphabet subsidiary to issue a recall on its vehicles’ software. A “recall” in this case meant rolling out a software update after investigating the issue and determining its root cause.

In a blog post, Waymo has revealed that on December 11, 2023, one of its robotaxis collided with a backwards-facing pickup truck being towed ahead of it. The company says the truck was being towed improperly and was angled across a center turn lane and a traffic lane. Apparently, the tow truck didn’t pull over after the incident, and another Waymo vehicle came into contact with the pickup truck a few minutes later. Waymo didn’t elaborate on what it meant by saying that its robotaxis “made contact” with the pickup truck, but it did say that the incidents resulted in no injuries and only minor vehicle damage. The self-driving vehicles involved in the collisions weren’t carrying any passenger.

After an investigation, Waymo found that its software had incorrectly predicted the future movements of the pickup truck due to “persistent orientation mismatch” between the towed vehicle and the one towing it. The company developed and validated a fix for its software to prevent similar incidents in the future and started deploying the update to its fleet on December 20.

  • Chozo@kbin.social
    0·
    5 months ago

    After an investigation, Waymo found that its software had incorrectly predicted the future movements of the pickup truck due to “persistent orientation mismatch” between the towed vehicle and the one towing it.

    Having worked at Waymo for a year troubleshooting daily builds of the software, this sounds to me like they may be trying to test riskier, “human” behaviors. Normally, the cars won’t accelerate at all if the lidar detects an object in front of it, no matter what it thinks the object is or what direction it’s moving in. So the fact that this failsafe was overridden somehow makes me think they’re trying to add more “What would a human driver do in this situation?” options to the car’s decision-making process. I’m guessing somebody added something along the lines of “assume the object will have started moving by the time you’re closer to that position” and forgot to set a backup safety mechanism for the event that the object doesn’t start moving.

    I’m pretty sure the dev team also has safety checklists that they go through before pushing out any build, to make sure that every failsafe is accounted for, so that’s a pretty major fuckup to have slipped through the cracks (if my theory is even close to accurate). But luckily, a very easily-fixed fuckup. They’re lucky this situation was just “comically stupid” instead of “harrowing tragedy”.