Picking up and dropping off passengers on real map data from OpenStreetMap. The code and data mentioned here can be found in my Github repository.

An image from the Rideshare Simulator, using Downtown Kansas City as the map. Videos are included further below.

I recently built a rideshare simulator in C++, capable of taking in OpenStreetMap data and a related image, and showing vehicles driving around, picking up passengers, and taking them to their destinations.

I built this project as my Capstone project for the C++ Nanodegree (ND) program at Udacity. …

Things were moving quickly in early and mid-March due to the spread of COVID-19, and especially with the news of NBA players testing positive for the virus, the NCAA made the extraordinary move to cancel the 2020 NCAA Tournament for both Men’s and Women’s basketball.

Being one of my favorite times of the year, as well as with my alma mater Kansas being a favorite to win their first title since 2008, I was certainly disappointed by the news, even if the cancellation came as inevitable.

With no tournament to look forward to, I thought back to being a kid…

One of the interesting news stories in tech and transportation over the past few months has been the widespread emergence of dockless bikes and scooters. Depending on your city, they’ve been either a blessing or a curse — they are fantastic to some, while being a plague to others, so much so that they are sometimes temporarily banned.

Piles of Dockless Bikes [Source: The Guardian]

While the Bay Area with its heavy traffic (and plenty of VC money) got out in front on the roll-out of these, even Kansas City, where I grew up, is getting in on the fun.

The scooters are pretty enjoyable and easy…

Running code on a real car, and graduation!

This is it.

This is the end.

Nine months after beginning Udacity’s Self-Driving Car Engineer Nanodegree program, I was finally to the final project — running my (team’s) code on a real self-driving car.

Just one function was needed this entire time!

I actually began the program back in December 2016, diving into the world of self-driving cars. During the end of the first term, and into the middle of the second term, I was also working on finishing up my Capstone project for the Machine Learning Nanodegree program, where I combined skills from the two programs to build a Deep Learning model for Lane Detection. Soon after…

Electives for the SDCND

This is the second part of my reflections from the final term of the Self-Driving Car Engineer Nanodegree program — you can see Part 1 on the Path Planning project here!

The second project of Term 3 of the SDCND program is actually more than one project, as it’s an elective! Currently, there are two options: Functional Safety or Advanced Deep Learning.

Not the smoothest detection, but it’s found both roads present fairly well.

The Functional Safety content is done in concert with Elektrobit, and is actually quite a bit different than the other projects in the Nanodegree, as this one is not programming based. Instead, the project focuses on documenting the…

Path Planning

Having been slow on writing Medium posts the last few months, I’m finally getting the chance to write about the final term of the Udacity Self-Driving Car Engineer Nanodegree. It’s been an absolutely phenomenal experience between all three terms, and I hope to reflect more on the sum total of the program in the final part of this post. For now, I want to cover the first of the three projects of the final term, Path Planning.

I also want to put a quick disclaimer to start the article, as I recently started a position with Udacity as a Student…

To readers of The Sporting News, he was known as “The Answer Man”, but to me he was simply Uncle John. He passed away earlier this week.

Growing up, my great uncle helped further my love of sports, especially when it came to the underlying stats every sport has in plenty. He sent my dad and I the Baseball Register (which he was long instrumental in putting together as an editor), an annual ode to the mountain of statistics any baseball fan could follow down the rabbit hole. He sent me a plethora of team media packages, and even let…

I just got back from a work trip to Scotland, and thought it would be interesting to cover some of the differences that autonomous vehicles will have to account for between different countries. There is the very obvious first difference going from the United States to the United Kingdom — the cars drive on the other side of the road! But there are a lot of other important differences as well.

In the US, if you came to the below road, you’d likely believe it was one-way.

All white lines in the US would indicate one-way…

But you’d be wrong.

The second term of Udacity’s self-driving car Nanodegree program introduces Sensor Fusion, Localization, and Control. Even just past the subject matters themselves, this term has a lot of other key changes. First off, where Term 1 often focuses on algorithms you can import from already created libraries (in the case of using deep learning for traffic sign classification and behavioral cloning for driving, and Support Vector Machines for vehicle detection), Term 2 requires more specific programming — you have to learn the exact mathematical equations required to implement the various techniques presented. …

This is part two of my deep learning solution for lane detection, which covers the actual models I created in finding my final approach to the problem, as well as some potential improvements. Be sure to read Part One for the limitations of my previous approaches as well as the preliminary data used prior to the changes I made below. The code and data mentioned here and in the earlier post can be found in my Github repo.

With a decent dataset created, I was ready to make my first model for using deep learning to detect lane lines.

The Perspective Transformed Model


Michael Virgo

Udacity Self-Driving Car and Machine Learning Nanodegree Graduate

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