Interesting coding experiments, progress reports, and explorations found here.
Knowing how to work with lidar sensors and the algorithms that utilize them can be a highly sought after skill in robotics, but is also hard to get started with. Lidar sensors (and depth mapping cameras) can be prohibitively expensive and a pain to set up, delaying and distracting developers from what they are actually interested in — coding something cool that makes use of the data. Compare that to computer vision, where all you have to do to get started is connect to a cheap webcam, or load up a video from the internet, and you are ready to get coding. For people studying computer vision, you can go from having nothing to making an face tracking program in a couple of hours or less.
There is nothing like that for lidar. No easy way to get some data and start working with it out of the box.
With the goal of making it simple and easy for developers to start working with lidar data, I went looking for datasets to work with and develop into some future guide. After a quick Twitter conversation with David Silver (head of the Udacity SDC program) and Oliver Cameron (CEO of Voyage), I decided to begin by investigating Udacity’s 3.5 hour driving dataset.
In this post I’ll be walking you through my exploration of the Udacity dataset and some of the troubleshooting needed to get it running. Ultimately, I was not able to get the point cloud data playing back with full accuracy, but I hope that with this work log and a bit of help from the community, we can get the data clean enough to start running algorithms and use as a teaching tool.