As promised previously in April 2017, Baidu Research has released their Autonomous Driving platform – Apollo. By making it Open Source, they declare Apollo as the “Android of Autonomous Driving Industry.” This is the first step in their goal of developing fully autonomous cars for open city roads by 2020.
Baidu Research has released its Open Source Autonomous Driving platform called Apollo. It believes that open sourcing poses a win-win situation; community development is faster for testing and deployment, therefore, pacing the project, forbye more participants implies more travel data. Armed with massive collaboration with other institutions, Apollo is ready to transform the Autonomous Driving Industry. Here is the official Github repo for the Apollo project.
Baidu Research affirms that its autonomous driving project is in similitude with the Apollo missions of NASA in the 1960s and 1970s. In fact, the readme in their Github repo starts with the famous quote by John. F. Kennedy:
“We choose to go to the moon in this decade and do the other things, not because they are easy, but because they are hard.”
Their goal of developing fully autonomous cars by 2020 is equally ambitious. However, it is not new. The dream for completely autonomous cars is decades old. To remind you, it has been ten years since DARPA unveiled the Urban Challenge in 2007. With a massive increase in computing power and AI capabilities, this goal is all the more realizable.
Baidu has already partnered with various top companies and institutions including Ford, Daimler, Delphi, Continental and top universities along with equipage companies like Microsoft, NVIDIA, and Intel.
Features of Apollo
Developers of Apollo have built a platform capable of supporting versatile tasks like intelligent control, precise sensing, and localization and cloud ecosystem in which the vehicle and the cloud are unified.
Apollo runs entirely on ROS (Robot Operating System) and supports C++ and Python; however, Python 3 support is currently unavailable. It provides localization and basic controls. As for the hardware, it supports GPS and IMUs (for locomotion and orientation).
The platform is clearly in its early days. The crucial elements of autonomous driving like perception and motion planning are still lacking. Furthermore, support for basic sensors like LiDAR, RADAR, Camera is still under development.
Apollo also aims to incorporate features like voice-based user-vehicle interaction and end-to-end security.
This is yet another commendable commitment to Open Source by the tech giant. With large-scale commercialization and fast paced development, the future of Apollo surely looks bright. With the burgeoning Open Source initiatives by almost all of the tech giants (cough Not you Apple cough), there is a sense that a better future is being built by the community as a whole.
So, what do you think about the Apollo project? I am eager to see how the moral dilemma in self-driving cars is resolved. Share your thoughts with us.