I saw the Tesla Robotaxi:
- Drive into oncoming traffic, getting honked at in the process.
- Signal a turn and then go straight at a stop sign with turn signal on.
- Park in a fire lane to drop off the passenger.
And that was in a single 22 minute ride. Not great performance at all.
Tbh it’s not as bad as I was expecting. Those clips could definitely have resulted in an accident, but the system seems to actually work most of the time. I wonder if it couldn’t be augmented with lidar at this point to make it more reliable? A live stress test is ridiculously irresponsible and will definitely kill people, but at least it’s only Texans at risk (for now).
I was skeptical of the idea of robotaxis, but this kind of sold me on it. If they’re cheaper than human drivers, I might even be able to get rid of my car some day. It doesn’t change the fact that I’ll never get into one because the CEO is a nazi though.
Keep in mind this is a system with millions of miles under it’s belt and it still doesn’t understand what to do with a forced left turn lane in a very short trip in a fairly controlled environment with supremely good visual, road, and traffic conditions. LIDAR wouldn’t have helped the car here, there was no “whoops, confusining visibility”, it just completely screwed up and ignored the road markings.
It’s been in this state for years now, of being surprisingly capable, yet horrible screw ups being noted frequently. They seem to be like 95% of the way there and stuck, with no progress in reality just some willfull denial convincing them to move forward anyway.