WEpod DriverLess Car is the first self-driving shuttle that takes the public roads to commute between the towns of Wageningen and Ede in the central Dutch province of Gelderland. WEpods are the first vehicles in the world without a steering wheel to be given license plates.
To everyone’s surprise this six-passenger WEpod driverless car does not travel on special lanes, and they’re not guided by rails, magnets or wires. Instead, they’re steered through traffic by a complex set of systems which is powered by several NVIDIA GPUs.
Contents
Deep Learning is the technology behind WEpod Driverless car:
Deep Learning is the new kind of technology that lets computer systems teach themselves about the world through a training process that is adopted widely for vision-based systems and that is what powers this WEpod Driverless car to drive on a public road filled with traffic. NVIDIA GPUs are the core to drive the Deep Learning technology for these kinda vision-based systems.
Deep learning has already given computers the ability to surpass human capabilities on a number of tasks. And it’s critical for autonomous vehicles, where it’s just not possible to hand-code for every possible situation a self-driving car might encounter. Especially with regards to interpreting the objects surrounding the vehicle.
The WEpod team at the Delft University of Technology, along with auto manufacturers such Audi, BMW, Ford and Mercedes have turned to deep learning on NVIDIA GPUs.
Every WEpod DriverLess self-driving Car is Data Driven and GPU powered
The vehicle can reach to its destinations independently and no route adjustments needed explicitly. It can stop on sensing obstacles with the use of Laser Scanners on the road and can move when the obstacles are cleared. For example: A football comes in front of the vehicle and the vehicle stops by itself (you can see the demo in the video).
The WEpod contains all the 3D maps and has GPS to monitor the precise location of the vehicle. In addition to that the vehicle has Laser Scanners, Radar and 360 degree cameras which enables the vehicle to reach its destination safely. Further more the WEpod neither have a steering wheel nor brake pedals.
Deep Learning on NVIDIA GPUs have enabled the WEpod DriverLess Car to build a complete picture of the environment around it as it travels through traffic. Each WEpod continuously assesses its environment and options at high rates (thanks to the NVIDIA GPUs), resulting in a dynamic system able to deal with real-world situations of mixed traffic quickly, reliably and safely.
“This is a massive computing challenge,”
said Dimitrios Kotiadis, senior researcher from TU Delft.
The parallel architecture coupled with NVIDIA software tools make GPUs ideal for many kinds of deep learning tasks. And it was key to accelerating the training and deployment of WEPod’s autonomous vehicles.
Kotiadis has the following remark on NVIDIA GPUs they have used on their WEpod DriverLess self-driving cars:
“NVIDIA technology plays a crucial role in enabling us to meet our computational requirements,”
“Each WEpod is in many ways a supercomputer on wheels.”
WEpod DriverLess Car sets a new benchmark on Deep Learning, GPU computing, slef-driving car technology. It is also clearly visible that this has the potential to revolutionize the commute system in a city.
“Autonomous, on-demand transit systems like WEpod have the potential to revolutionize our cities,”
said WEpod Project Manager Jan Willem van der Wiel.