Fusing sensor data for autonomous driving

Autonomous systems

The challenge

The road to completely operational self-driving cars is still long because of the complexities of the requirements. In particular, the correct perception of complex traffic situations remains a challenge and is prone to errors. Multi-layered scenarios with changing road users, confusing crossings/intersections and changing visibility and surrounding conditions make it impossible for autonomous cars to act correctly on their own.

How we will help

In cooperation with the project partners, XITASO creates a robust sensor system which takes external influences effectively into consideration and thereby increases the safety of autonomous vehicles in challenging traffic situations. For this purpose, sensor data from the vehicle is merged with sensor data from the infrastructure to create an innovative overall sensor system via fast, secure, and reliable V2X communication (vehicle-to-everything).

Technologies

Computer Vision Sensor Fusion Deep Learning V2X GAIA-X

Innovative sensor technology for safe autonomous driving at intersections

To ensure the success of the project VALISENS (valid innovative overall sensor systems for cooperative automated driving), the combination of infra-red cameras and their data with other sensors like classical RGB cameras, LiDAR, and radars is researched – for the development of a reliable and trustworthy sensor system for autonomous vehicles in intersection traffic.

The focus is on the development of AI based multi-perspective and multimodal fusion processes as well as object recognition, and their transfer to driving scenarios. Particular attention is paid to the robustness under various external conditions in the merging of the IR pictures with classic camera pictures.

GAIA-X for progressive data management

Furthermore, XITASO is researching the application of GAIA-X as a platform for data storage and data management for sensor and fused data. XITASO’s expertise in software architecture for hybrid edge/cloud data management will be brought into the project to develop innovative solutions and to drive the potential of autonomous mobility forward.

Data fusion for automated driving: Efficient overall situation analysis in test fields

Using new methods of data fusion and processing, the comprehensive overall situation is detected, analyzed, and evaluated. This approach creates the foundations for realizing the automated driving functions level 3+ and enables the application of extensive customized test and validation processes for cooperative automated driving. The efficiency of the complete sensor system will be presented within the public test fields in Dresden and Ingolstadt.

Project participants and funding

Project partners

LiangDao GmbH
LiangDao is a global leading system provider of LiDAR sensors, providing their industry customers with a comprehensive range.

Fraunhofer IVI
The Fraunhofer-Institut für Verkehrs- und Infrastruktursysteme IVI works on traffic related research on vehicle and drive technology, layout, logistics, digital business processes and intelligent traffic systems.

NXP Semiconductors N.V.
NXP is a global semiconductor company, developing solutions which enable secure connections for a more intelligent world.

s.m.s – smart microwave sensors GmbH
smartmicro designs, develops and produces radar solutions for traffic management as well as for applications in the automotive and aerospace industries.

Project sponsor

BMWK_Logo_EN

Funding program

New vehicle and system technologies

Project management

TÜV Rheinland Consulting GmbH

Interested in helping with our research projects?

With research and innovation projects, we explore the potential of tomorrow’s technologies. For this purpose, we are always looking for committed colleagues who would like to continue and shape the XITASO path with us.

Further projects

Are you interested in a project, a service or do you have any other question?

Dr. Andreas Angerer

Tel. +49 821 885882-94
andreas.angerer@xitaso.com