Why it doesn't just calculate moon's position given current date, time of day and coordinates?
Tesla auto-pilot keeps confusing moon with traffic light then slowing down
31–40 of 93 posts
Re: Tesla auto-pilot keeps confusing moon with traffic light then slowing down
#32I only have two cameras and have never confused the moon with traffic lights.
If your head was in a vice and your eyeballs were superglued into the straight-ahead position you might have more trouble.
Re: Tesla auto-pilot keeps confusing moon with traffic light then slowing down
#33I can't understand why instead of using all the possible senses: vision, auditory, radar, lidar they want to only use vision as if there's some sense of "purity" in doing that.
Which of the above would solve this problem?
That said, the computer vision is still far from human level. It lacks a common sense around how the world works.
Re: Tesla auto-pilot keeps confusing moon with traffic light then slowing down
#34I can't understand why instead of using all the possible senses: vision, auditory, radar, lidar they want to only use vision as if there's some sense of "purity" in doing that.
Which of the above would solve this problem?
You'd be able to tell there's no object anywhere near the car and disregard the light.
Re: Tesla auto-pilot keeps confusing moon with traffic light then slowing down
#35I can't understand why instead of using all the possible senses: vision, auditory, radar, lidar they want to only use vision as if there's some sense of "purity" in doing that.
Which of the above would solve this problem?
Re: Tesla auto-pilot keeps confusing moon with traffic light then slowing down
#36I can't understand why instead of using all the possible senses: vision, auditory, radar, lidar they want to only use vision as if there's some sense of "purity" in doing that.
Which of the above would solve this problem?
Re: Tesla auto-pilot keeps confusing moon with traffic light then slowing down
#37I can't understand why instead of using all the possible senses: vision, auditory, radar, lidar they want to only use vision as if there's some sense of "purity" in doing that.
Re: Tesla auto-pilot keeps confusing moon with traffic light then slowing down
#38Why it doesn't just calculate moon's position given current date, time of day and coordinates?
Re: Tesla auto-pilot keeps confusing moon with traffic light then slowing down
#39This is a problem with learning the appropriate context. In the case of a yellow traffic light, there should be a traffic light fixture and two other (unlit) lights. Without this context, it becomes apparent the yellow pixels in a circular shape (representation to the network) are not a traffic light at all. Tesla’s vision/ml systems are amazing. I would love to learn more about how unit testing for this type of erro…
> Tesla’s vision/ml systems are amazing More importantly, they're the only ones accessible to the average consumer. Waymo/Zoox/Daimler all have equally if not more impressive systems. A real issue with tesla is that they want to be vision-only, which is going to make getting to level 5 first almost impossible. BTW - knowing where the moon is happens to be an extremely solved problem.
It's true... but I don't think that's how Tesla would solve it. Their goal is to create a neural network "driver" which can drive in any place even if it has never seen it before. They'd rather teach their neural network that the moon and stoplights are not to be confused visually. Thought I suppose in searching for training examples they could use the known position of the moon for approximate labeling.
Re: Tesla auto-pilot keeps confusing moon with traffic light then slowing down
#40This is a problem with learning the appropriate context. In the case of a yellow traffic light, there should be a traffic light fixture and two other (unlit) lights. Without this context, it becomes apparent the yellow pixels in a circular shape (representation to the network) are not a traffic light at all. Tesla’s vision/ml systems are amazing. I would love to learn more about how unit testing for this type of erro…