Every day we come across many inspiring stories of our students succeeding in various fields. Some make us happy, some make us proud, and then there are some that are so remarkable they make us realize the profound impact our students can have on society.
We came across one such story recently of Mateusz Zatylny, a recipient of the Udacity Pytorch Scholarship and the Udacity Facebook Secure and Private AI Scholarship, who is now building an autonomous technology driven wheelchair along with a group of Udacians he met during the Pytorch Scholarship program. Mateusz is a patient of generalized Dystonia, a movement disorder that is not limited to a single part of the body. But that clearly didn’t deter him from achieving great things. He can’t control his wheelchair by himself, so he decided to build an autonomous technology driven wheelchair that could help him and many more to safely maneuver through daily life.
Robots use a surprisingly simple but powerful algorithm to find out where they are on a map, a problem called localization by engineers. The algorithm known as particle filtering looks amazingly cool. In this first article, we attempt to explain the intuition behind particle filters. In part 2 we will elucidate the mathematics needed to build your own particle filters.
Every robot that can move around, whether it is a vacuum cleaning robot like a Roomba or a self-driving car like Carla, has a lifelong problem to contend with. The problem is to find out its whereabouts on a map that every robot carries with itself. But why is finding the whereabouts so challenging? A robot can just ‘look’ at its surroundings and recall which area on the map looks like the current surroundings, not very different from how we humans find where we are in a city or inside the office when woken up from a post-lunch slumber.
The challenge is the utmost precision with which robots have to localize themselves, very unlike humans. If a Roomba thinks it is in front of a door, while it actually is slightly behind a wall, a few centimeters away from where it thinks it is, it may never be able to maneuver its way out from one room to another. A self-driving car, operating under a similar misconception, may scrape another car, veer off the road or climb a curb. The reason this does not happen is because robots are able to beat humans at one of their own games.
Humans try to address the imprecision in their beliefs by filling in missing clues using logic and reasoning but they do end up tripping sometimes. However humans move around rather slowly and have enough time to recover from a bad assumption. So, while we may miss a step on a staircase and stumble, in most cases, we do not tumble down the staircase into the abyss.
For the sake of everyone’s safety robots pack much more precision into their beliefs so that they do not have to trip and recover. How do robots synchronize their beliefs with reality so precisely? Let us find out, starting with something called priors.
At Udacity, our students are at the heart of everything we do. It’s the reason we’re here, and their success is our number one priority. That’s why we’re constantly finding new ways to innovate and make our programs stronger. In order to help our students master in-demand skills more effectively, we recently launched new support features for our Nanodegree programs. In our latest series, we’ve been highlighting students from all over the globe who have had this new experience.
In this week’s feature, we spoke with another student enrolled in one of our redesigned Nanodegree programs. Felix Palomares is a software engineer in the casino gaming industry who enrolled in the Robotics Software Engineer Nanodegree program to live out his childhood dream. He took some time out of his busy schedule to share his experience with us.
The Sensor Fusion Nanodegree program launched this week and we are thrilled to begin sharing this course with students. This program offers cutting-edge access to skills and projects that are integral to many industries, especially the autonomous vehicle industry.
To train the next generation of engineering talent in self-driving car technology, lifelong learning pioneer Udacity is further expanding its learning partnership with Mercedes-Benz Research & Development North America (MBRDNA). Today, we are excited to announce theSensor Fusion Engineer Nanodegree program, built in collaboration with Mercedes-Benz. Mercedes-Benz was the first automotive manufacturer to open a research and development center in Silicon Valley in 1995. In September 2014, MBRDNA became one of the first automotive manufacturers to be issued with an official license by the state of California for testing self-driving vehicles on public roads.
“Sensor fusion is a crucial component of autonomous vehicles at Mercedes-Benz,” said Michael Maile, Manager of the Sensor Fusion and Localization team at MBRDNA. “Our partnership with Udacity is offering a great way of teaching engineers how to work with lidar, radar, and camera sensors to perceive the driving environment.”
This week we launched new support features for our Nanodegree programs designed to help our students master the skills they’re learning. Before sharing these new features with the public, we invited current Udacity students to experience our new and improved learning programs. One of those students is Mohamed Barakat, a biomedical engineer, living in Munich, Germany and currently working as a software engineer in the healthcare sector. He is enrolled in the Robotics Software Engineer Nanodegree program. We had a chance to chat with him about his current Udacity experience and how this program is impacting his skillset.
Jupyter Notebooks are fantastic tools for learning any technical topic, from basic programming to data science all the way to advanced artificial intelligence. Like a web page, you can read and review learning content; and like a traditional programming environment, Notebooks can be “hands-on”. Notebooks invite you to experiment with the code and data cells alongside the equations and graphs.
But have you ever wished an instructor was sitting right next to you when you’re stuck on something, to “show you how she would solve it?”
Graffiti brings that instructor into the Notebook, and makes Udacity’s new C++ Nanodegree Program an amazing way for software engineers to learn the C++ programming language!
Jupyter Graffiti are recorded, interactive demonstrations that live inside your Notebooks.
Via Jupyter Graffiti, Udacity instructors show you exactly how to solve each problem. They walk you through the content, pointing, selecting, typing and executing code, adding and removing code cells, and more. As a student, you can play these recordings as many times as you want, or not at all, and pause and rewind them to see the instructor write and explain the code again.