NOTE: Sorry for taking so much time in posting next microblog. I’ve been busy for a few days, and the future looks bleak too
A little background: Self-driving cars are a thing now, not just a fantasy. Big companies are investing hundreds of thousands of dollars just to get in the market. The problem, as with every other technology, is to prove viability to the common masses. Industrial standards state that the accuracy ought to be greater than 99% to be useful as a product. To cope up, researchers along with industrial experts are working tirelessly to progress and to deliver efficient self-driving technologies.
Another dataset has recently been released, marking the era of ever increasing AI breakthroughs. Robotics Research Group at Oxford has recently released a humongous ~23TB driving data. (yeah you heard it right. Its TERABYTES!). Shared with a creative commons open-source license, it would definitely help in creating a fully autonomous self driving car.
According to their website:
Over the period of May 2014 to December 2015 we traversed a route through central Oxford twice a week on average using the Oxford RobotCar platform, an autonomous Nissan LEAF. This resulted in over 1000km of recorded driving with almost 20 million images collected from 6 cameras mounted to the vehicle, along with LIDAR, GPS and INS ground truth.
Data was collected in all weather conditions, including heavy rain, night, direct sunlight and snow. Road and building works over the period of a year significantly changed sections of the route from the beginning to the end of data collection.
An image depicting their self-driving car:
There are still many notable opensource contributions in autonomous driving recently, such udacity’s initiative to open-source their self-driving-car project and DeepDrive.io initiative ( which I’ve recently shared ). Advances like these will actually be changing our lives in future.