SOC/FPGA: 4D full-range radar

Project background

SCS carried out the following subtasks for the implementation of the algorithm on the FPGA:

  • Guided development of an FPGA architecture for a specific algorithm
  • Development of FPGA-RTLPolylang
    placeholder do not modify
  • FPGA implementationPolylang
    placeholder do not modify
  • ISO26262 ASIL-B compliantPolylang
    placeholder do not modify
  • Embedded SWPolylang
    placeholder do not modify
  • CybersecurityPolylang
    placeholder do not modify
  • ASPICE-compliant documentationPolylang
    placeholder do not modify

ZF Radar background

The 4D full-range radar offers a resolution close to that of optical sensors, cameras or LiDAR. This at a competitive price, while at the same time offering the possibility of direct speed measurement and the ability to work in difficult conditions (snow, fog, dust). In combination with these technologies, high-resolution radar can help to ensure the necessary safety and reliability for partially to highly automated driving, including Level 4.

The imaging full-range radar offers high resolution in four dimensions: Distance, speed, horizontal angle and additionally the elevation angle (height). This means that the radar is also an imaging technology in 3D, with speed as an additional fourth measurement dimension. The high-resolution 4D detection of the traffic situation helps a vehicle on the motorway, for example, to detect the end of a traffic jam under a bridge at an early stage and to brake accordingly.

From 2022, our customer will supply its new 4D full-range radar to the first OEM for a series production electric SUV.
Additional information: https://press.zf.com/press/de/releases/release_25856.html

FPGA-based driver assistance systems

Project insights

The development of driver assistance systems, such as a lane departure warning system or traffic jam assistant, involves solving a wide range of problems. For example, the system must be taught to transform pixels into known objects (road surface, road markings, vehicles, pedestrians, etc.). The algorithms required for this are implemented as PC programmes by our customer’s technical experts for research purposes.

As the performance of modern processors and graphics cards was not sufficient at the time of the project to process the video image of an automotive camera in real time with the algorithm, the technical expert was unable to test the functionality of his algorithm in the moving test vehicle. Several such algorithms were implemented by SCS engineers in an FPGA and integrated on our suitable hardware platform. The resulting system enables real-time processing of the video images. In each case, the feasibility was first examined in a feasibility study in close cooperation with the customer’s technical experts and the realisation costs were determined.

SCS then carried out the implementation on FPGA. With the implementation on FPGA, the customer’s technical experts are able to execute their algorithms in the test vehicle in real time. They can combine them into a complete system and test them in real traffic situations. Project insight using the example of the Stixel algorithm: Processing video images on a pixel basis requires the algorithm to handle considerable amounts of data. The Stixel algorithm helps to reduce the amount of data: it summarises the pixels of an image column into “columns”, so-called stixels. It forms pixels from vertical surfaces (in vehicle rear ends, kerbs, …), flat surfaces (roadway, pavement, …) and background.

In addition to data reduction, an initial, rough grouping of the pixels into sub-objects is achieved. This algorithm is mathematically complex and correspondingly computationally intensive. As part of a feasibility study, SCS has succeeded in mapping the algorithm onto a streaming architecture for a low-cost FPGA. It was then implemented on the SCS FPGA box and integrated with other algorithms. Two automotive cameras can now be connected directly. The result, a Stixel image, is available via a network connection for display or further processing on a PC.

The FPGA box from SCS was one of the subsystems of the Mercedes-Benz S-Class INTELLIGENT DRIVE, which was the first car in the world to drive a 100km overland route completely autonomously in a pioneering achievement. The selected route leads from Mannheim through villages and small towns to Pforzheim and has historical significance: exactly 125 years earlier, Bertha Benz demonstrated the suitability of the patented Benz motorised carriage on the same route. The modern S-Class successfully mastered numerous difficult traffic situations.

Text and images provide an insight on the following website:
Pioneering achievement: Autonomous long-distance drive in rural and: Mercedes-Benz S-Class INTELLIGENT DRIVE drives autonomously in the tracks of Bertha Benz