Bright Box using gaming and neural networks for its self-driving car platform
Picture credit: Bright Box
Bright Box, a Switzerland-based connected vehicle applications provider, has announced the launch of a self-driving car product with a neural network which learns driving through gaming.
The product, Remoto Pilot, is a self-driving car retrofit kit with a neural network trained through computer games as well as real-life examples featuring safe, reliable road/lane following as well as real-time detection and avoidance of various obstacles such as cars and pedestrians.
By using stereo vision – a pair of video cameras mounted on a car – combined with advanced computer-vision algorithms based on convolutional neural networks (СNN) with deep learning, the solution allows highly efficient autonomous driving capability. It also uses Global Navigation Satellite System (GNSS) and high-definition (HD) maps.
Using stereo cameras is an alternative to the use of Lidar, a laser scanner which is usually installed on a car’s rooftop to measure distances to surrounding objects. Bright Box is planning to eliminate the need of Lidars with the use of advanced computer vision techniques.
At present, the company’s main product is Remoto, a turnkey connected car platform that helps car owners to start the engine, open and close doors, and track their car, as well as provide large amounts of data to automotive and insurance companies.
Alexander Dimchenko, Bright Box CTO, said: “We’ve got successful experience in connected-car solutions for remote car control and more than 250,000 cars connected. Today we work with a broad customer base among OEMs around the world (Europe, Middle East, Asia). The company is already negotiating solution supplies with OEMs and their partners, and hopes to increase the number of the company’s partners in the future. We also offer subscription based business model without significant R&D costs for OEMs.”