- Autonomous driver assisted systems (ADAS) play a key role in the development of self-driving vehicles
- Implementation of Field-programmable gate arrays (FPGA) based control systems can improve the current decision-making parameters of autonomous vehicles
The development of the self-driving vehicles industry has gained a quick pace in the last five years. There is steady progress in the development of high-end processors and microcontrollers. These processors are considered as the ‘brain’ of the control systems used in autonomous vehicles.
The demand for system-on-chip(SOC) designs has rapidly increased in the vehicle industries. SOC design eliminates wire connections between different control peripherals in a vehicle. This helps in reducing faults occurring in the wire harness due to different wiring issues. Also, this design approach contributes to the development of a robust and rigid control system.
Xilinx has recently introduced a pair of automotive FPGAs. These two FPGA devices are developed to provide application-specific solutions. This article covers one of the two devices released by Xilinx.
The Zync Ultrascale+ is based on the development of ADAS and self-driving systems. This device features a 16-nanometre gate size for the field arrays. As stated by the company, this solution can increase the vehicle’s performance of up to three times as compared to previous automotive platforms.
The device features the integration of an application processing block with a real-time multicore microprocessor. It also uses a graphics processing unit. All these components are combined and integrated with a large FPGA fabric.
Can handle 4Kx2K video streams of up to 60 frames per second
The Zync Ultrascale device is based on enhancing the video processing features of current vehicle systems. The device features a video-codec unit. This unit helps in the encoding and decoding of h.264/h.265 codec based files. The company informed that the device can handle 4Kx2K video streams of up to 60 frames per second. The processing unit of the device includes quad-core Arm Cortex-A53 and a dual-core Arm Cortex-R5 processor.
Emre Onder, senior vice president of marketing for Xilinx Systems told about the device in a recent statement saying,
“The new additions to our automotive portfolio expand our proven offering to the market. Through customer-driven requests, we’ve broadened our XA product family to meet the complex levels of today’s ADAS and autonomous driving systems. With these additions to the Zynq UltraScale+ product line, Xilinx delivers unmatched processing flexibility and scalability vital for today’s rapidly changing requirements. Whether customers are developing for L1 or for L4 systems, we have a solution that meets their needs.”
The device also features low-power features. The device is certified to ASIL-C level in the low-power domain. This mini SOC design is qualified for MPSoC portfolio. This device also qualifies AEC-Q100 test specifications.
With a rugged processing system and optimised video encoder, the company claims that the new device can be a good replacement for the present processing system in autonomous vehicles.