2019
AI
self-driving model
SHOW HN2019
144points
58comments
#304of 2,195 in 2019
Top 14%of 2019 by points
How HN took it
CuriousMostly questions and neutral comments
9 positive, 16 neutral or asking, 1 mixed, 5 critical, out of 31 comments about the project. Thread score +0.05.
Design: 0 for, 2 againstExecution: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Impressive work for a young developer
From 3 comments
> At the current state of my model the model basically just clones the human driver as good as possible. That means the the amount of brake is higher in curves I read in another…
pathsjs on HNGreat job! This is amazing. Love how I’m you used off-the-shelf components. Congrats and keep going!!
nikodunk on HNHoly crap. First: you're awesome. Keep it up. Second: anyone else think this is a great example of how autonomous driving is a last-mile problem?
rpmisms on HN
Objections
Neural network alone is unsafe for safety-critical driving
From 2 comments
Seems really scary to exclusively use a neural network for safety-critical tasks like this, without having an explicit method guaranteeing safety. You can't prove that a trained…
devit on HNThe risk is extremely high.
littlemtman on HN
Braking before curves is not how most drivers behave
From 2 comments
> At the current state of my model the model basically just clones the human driver as good as possible. That means the the amount of brake is higher in curves I read in another…
pathsjs on HNYou are conflating effective driving habits with actual driving habits. I'd say less than 5% of drivers in the states properly brake before curves and accelerate through. Hell,…
hugey010 on HN
Requests
Add temporal context from previous frames
From 1 comment
good start op. a good next step is add in temporal context (previous frame information) so model may resolve ambiguous cases. see e.g. breakdown of comma.ai openpilot model here…
czr on HN
Lead with demos and failure cases
From 1 comment
good start op. a good next step is add in temporal context (previous frame information) so model may resolve ambiguous cases. see e.g. breakdown of comma.ai openpilot model here…
czr on HN
Questions
How is overfitting handled given held-out test data
From 1 comment
How big of a risk is overfitting for these kinds of models? I think common practice is to hold back some of the data for testing.
billsmithaustin on HN
Why ELU activation works better than ReLU
From 2 comments
You do something similar in Udacity's SDC nanodegree but you use their simulator rather than a new car. Interestingly through trial and error on my project, ELU activation…
syntaxing on HNThanks for the answer! I also used Relu with no luck either. I figured Relu would work better than ELU but it didn't work for this application. Would you happen to know why ELU…
syntaxing on HN
Alternatives named
comma.ai openpilot
From 1 comment
good start op. a good next step is add in temporal context (previous frame information) so model may resolve ambiguous cases. see e.g. breakdown of comma.ai openpilot model here…
czr on HN
Tesla Autopilot
From 1 comment
>A few days ago @karpathy presented their workflow with PyTorch and also said some numbers, to train the Autopilot system with all it neural networks you would have to spend…
daenz on HN