Wettersteinstraße 18
82024 Taufkirchen
- InoNet Computer GmbH
As part of the AD Bavaria project, the Technical University of Munich (TUM) is using the autonomous vehicle EDGAR (Excellence Driving GARching), for example as an autonomous Wiesn shuttle at the Oktoberfest. This application places the highest demands on the technology and requires a solution that overcomes several complex technical challenges.
A key challenge is processing the large volumes of data generated while driving with the help of artificial intelligence (AI), which requires a large number of suitable interfaces for the seamless integration of sensors such as cameras, radar and lidar.
In addition, the data must be stored and transferred to an external hardware-in-the-loop (HiL) evaluation station for later analysis. The data already processed during the journey is used to visualise the detected objects – such as other vehicles, pedestrians, cyclists or traffic signs – on screens inside the vehicle. At the same time, the processed information must be transmitted to the Engine Control Unit (ECU) to enable the autonomous vehicle to be controlled.
These requirements demand a hardware solution that is not only powerful and flexible, but also works reliably under the demanding operating conditions in the vehicle.
In order to meet the high demands of the AD Bavaria project, the Technical University of Munich (TUM) relies on the powerful InoNet Mayflower®-B17-LiQuid-vX in combination with the QuickTray®-v3, which is integrated into the vehicle’s trunk. This liquid-cooled hardware platform is designed for demanding applications such as data acquisition and logging in Advanced Driver Assistance Systems (ADAS) test environments.
The Mayflower®-B17-LiQuid-vX offers a combination of a high-performance CPU and the NVIDIA® RTX A6000 GPU, which enables the processing of large amounts of data thanks to its computing power. The efficient water cooling ensures reliable heat dissipation, even under demanding conditions. By integrating network cards, frame grabbers and BUS measurement cards, the platform provides extensive connectivity and enables precise processing and analysis of sensor data. It also allows this data to be visualised directly on screens via its many interfaces.
The QuickTray®-v3 complements the system as a high-performance storage module with a capacity of up to 120 TB and write rates of up to 26 GByte/s*, enabling continuous recording and encrypted logging of vehicle data. Thanks to hot-plugging, the QuickTray®-v3 can be replaced quickly and easily if required, ensuring a high degree of flexibility and ease of use.
*depending on the SSD type and manufacturer used, real measured with Iometer in continuous write mode
InoNet’s solution offers significant benefits to the customer by covering all requirements with a single PC, saving the cost of additional systems. Processing data on the move means that only relevant information is stored, reducing the amount of data to be stored and allowing longer recording times. The high storage capacity of the QuickTray®-v3 allows for more efficient recording, helping to make the most of test drives.
Thanks to the hot-plugging function, the QuickTray®-v3 can be seamlessly replaced, so that the data can be easily transferred to an external evaluation station for HiL simulations. In addition, the QuickTray®-v3’s built-in data encryption ensures maximum protection of sensitive information from unauthorised access.
The ability to visualise the data during the journey offers the customer a further advantage: errors can be detected immediately and any necessary intervention can be made directly if the system has not recorded important objects correctly. This supports the driver and contributes to greater safety and efficiency during testing.
Liquid-cooled in-vehicle server for AI/GPU and sensor fusion applications
High-speed hot-plug & encryption-capable storage insert for data exchange