Electric Vehicles

3191 readers

1244 users here now

A community for the sharing of links, news, and discussion related to Electric Vehicles.

Rules

No bigotry - including racism, sexism, ableism, homophobia, transphobia, or xenophobia.
Be respectful, especially when disagreeing. Everyone should feel welcome here.
No self-promotion
No irrelevant content. All posts must be relevant and related to plug-in electric vehicles — BEVs or PHEVs.
No trolling
Policy, not politics. Submissions and comments about effective policymaking are allowed and encouraged in the community, however conversations and submissions about parties, politicians, and those devolving into general tribalism will be removed.

founded 1 year ago

MODERATORS

Tesla Bet On 'Pure Vision' For Self-Driving. That's Why It's In Hot Water (insideevs.com)

submitted 1 day ago by [email protected] to c/evs

31 comments fedilink hide all child comments

A fan of Tesla might think that the automaker just can't catch a break when it comes to its autonomous driving tech. It’s already subject to several federal investigations over its marketing and deployment of technologies like Autopilot and Full Self-Driving (FSD), and as of last week, we can add another to the list involving around 2.4 million Tesla vehicles. This time, regulators are assessing the cars' performance in low-visibility conditions after four documented accidents, one of which resulted in a fatality.

The National Highway Traffic Safety Administration (NHTSA) says this new probe is looking at instances when FSD was engaged when it was foggy or a lot of dust was in the air, or even when glare from the sun blinded the car’s cameras and this caused a problem.

What the car can "see" is the big issue here. It's also what Tesla bet its future on.

you are viewing a single comment's thread
view the rest of the comments

[–] Bell 0 points 1 day ago (1 children)

The problem was the different sensors could sometimes disagree. Like, vision sees an obstacle but radar isn't picking it up...which one does the software believe?

And if you think vision has problems with things like rain and fog, try radar or lidar!

Not mentioning the downsides of the other sensors always makes me suspicious of an article.

The key point of going vision-only is that: its what humans do every day. Articles that leave that out also disappoint me.

[–] bladerunnerspider 1 points 16 hours ago

It's called consensus. Have three sensors and each get a vote. Typically these sensors are the same and thus can detect a failure or incorrect reading of one. This idea is used in IT around data backups and RAID configurations as well as aviation. And .. I personally would just favor the radar. If vision says go and radar says stop... stop and avoid hitting that firetruck parked on the highway. Or that motorcyclist. Or any other bizarre vision-only, fatal crashes that this system has wrought.

Also humans can hear things. So, not just vision.