Mini-project Automotive, EV & Aerospace Case Studio

Self-driving crash rate comparison

Inspired by publicly reported work at Waymo

Compare crash rates of driverless cars with human drivers fairly, using the right benchmarks.

The brief

Waymo publishes crash rates for its driverless cars against human benchmarks for the same cities and roads, and explains why raw crash counts mislead. Rebuild the comparison from its public safety data, compute rates per million miles with confidence intervals, and write what the numbers can and cannot show. Good looks like: correct rates and intervals, a clear explanation of benchmark choice, and a one-page summary a journalist would get right.

Read the case first

What Waymo has said in public about this kind of work, on its own pages:

Make it your own

Ask what a fair comparison would need in India: use Indian road accident statistics (data.gov.in or MoRTH reports) and write which numbers are missing to judge a driverless car on Indian roads.

AITeky has no link with Waymo, which has not reviewed or endorsed this brief. The brief only draws on what the company has published, uses open data rather than its data, and is a learning exercise: don't present your project as Waymo's work or system.

What you will build

Download the public safety impact data
Compute crash rates per million miles with confidence intervals
Compare with human benchmarks by crash type and city
Explain how benchmark choice changes the result
Write a one-page plain-language summary

Free, open data to build it with

It takes a minute with your email. AiTeky Pass (₹999/month or ₹9,999/year) is free for your first 30 days.