industry news
Subscribe Now

aiDrive2 Introduces a Modular Approach to Automated Driving

AImotive encourages cooperation in the self-driving industry by providing a modular solution to the challenges of autonomy

January 4, 2019 – AImotive, AImotive, the autonomous technology service provider, today announced the next generation of its AI-powered self-driving full-stack software, aiDrive™ 2. Through a highly modular design, aiDrive2 will serve as a platform for deeper collaboration in an industry dominated by proprietary ‘walled garden’ approaches.

aiDrive2’s modular design will open the door to a wide range of implementations reducing the time to market of automated driving solutions. Automotive OEMs, Tier1s and Robotaxi companies will have the ability to integrate only selected modules into a best-in-class solution or rely on aiDrive2 to deploy full automated driving solutions. Compatible with a wide range of different sensor types and hardware platforms, aiDrive2’s flexibility allows for a wide range of possible collaborations. The software stack offers a platform for both ADAS functionalities and L4 autonomy in an autonomous driving industry racing to reduce the time to market of automated driving solutions available to the public.

“AImotive has always supported industry collaboration and standardization. These will be vital in securing consumer trust in autonomous driving technologies,” said Laszlo Kishonti, AImotive CEO. “By creating aiDrive2 AImotive hopes to provide an easily accessible platform to support our partners in achieving their autonomous goals.”

The aiDrive software stack handles all tasks associated with self-driving from perception to control. The solution relies on advanced artificial intelligence in perception and motion planning to ensure a higher degree of safety in operation. To ensure safety AI is augmented with classical, verifiable planning algorithms. aiDrive is compatible with a wide range of sensor types to ensure redundancy and a deeper understanding of the vehicle’s environment. Building on these various input types aiDrive2 also utilizes high- and low-level sensor fusion for robust model space creation.

aiDrive2 offers the complete functionality of the previous generation of aiDrive but has been highly optimized for embedded automotive hardware platforms. These optimizations allow for the deployment of aiDrive-based self-driving systems in production vehicles, without compromising on the safety of the system.

AImotive is currently working on the advancement of autonomous vehicle technologies with partners such as Groupe PSA, Samsung and SAIC. aiDrive2 will be available for licensing from Q1 2019. Interested parties can see the system in action in AImotive’s booth at CES 2019: Tech East North Hall, #7538.

For more information please visit https://aimotive.com/technology/aidrive.jsp

About AImotive:
AImotive is one of the largest independent teams in the world working towards fully self-driving car technology. Our unique toolset is engineered to answer all the challenges of autonomous mobility, powered by advanced artificial intelligence, simulation technology, and supporting hardware architectures. This comprehensive approach to self-driving car technology allows our team to develop systems quickly in the safest possible way.

AImotive is at the forefront of open collaboration for autonomous driving, partnering with the Khronos Group to develop the Neural Network Exchange Format (NNEF), the first neural network data exchange standard to make communication easier and more reliable between AI toolsets and inference engines.

AImotive is a privately held company, headquartered in Budapest with offices in Mountain View, California, Helsinki, Finland, and Tokyo, Japan. The company was granted licenses to test their self-driving vehicle fleet in Hungary, Finland and the states of California and Nevada. Follow @AImotive on Twitter, like us on Facebook, or learn more at www.aimotive.com.

Leave a Reply

featured blogs
Jun 19, 2019
I want to believe. Not only could Eugene Victor Tooms hibernate for 30-year stints, but he could squeeze and elongate his body to pass through narrow openings. In the supernatural thriller The X-Files, Tooms managed to fit through elevator shafts, air vents, chimneys, and alm...
Jun 19, 2019
A lot of AI design is done in software and, while much of it will remain there, increasing numbers of designs are finding their way into hardware. There are multiple reasons for this including the... [[ Click on the title to access the full blog on the Cadence Community site...
Jun 17, 2019
eSilicon used the Tessent family of DFT solutions to solve their toughest challenges of testing a large 2.5D/3D deep learning device. Hear all about it in this 15 minute video. With over 300 tapeouts, there is no doubt that eSilicon has tons of experience getting designs don...
Jan 25, 2019
Let'€™s face it: We'€™re addicted to SRAM. It'€™s big, it'€™s power-hungry, but it'€™s fast. And no matter how much we complain about it, we still use it. Because we don'€™t have anything better in the mainstream yet. We'€™ve looked at attempts to improve conven...