Building a real, self-driving car!


The TLDR; of how I built this

System architecture

Source: Udacity

Traffic Detection

Waypoint Updater


Breaking all of this down


  1. Perform depthwise convolutions with 1x1 convolutions (this is also known as a pointwise convolution) vs. a vanilla convolution.
  2. From there, use a “width multiplier” which allows the size of input + output channels to be thresholded between 0 and 1.
  3. We’d also then use a “resolution multiplier” to reduce the original input size and threshold to 0 and 1.


The green path is our trajectory with those spheres being the waypoints



Planning for the future

Connect with me




Building Self-Driving Cars as a 15yo.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Interviewing For a Software Engineering Internship at Amazon

How to Update Dependency Version in Multiple GitHub Repositories

Sheet.Best is Awesome

Announce Closing WL minting process

My Second Project in Hacktoberfest

Development framework to cut down debugging time by Half.

Deliver Continuously

QA: An Agile Method for an Agile World

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Sri Anumakonda

Sri Anumakonda

Building Self-Driving Cars as a 15yo.

More from Medium

On The Reproducibility Problem of Deep Learning Research Papers

Does your autonomous vehicle know when to stop?

How many books are there in a law library?

The Math behind Match Making