Xilinx & Continental Create the Auto Industry's First Production-Ready 4D Imaging Radar for Autonomous Vehicles
【Summary】Silicon Valley chipmaker Xilinx Inc. and automotive supplier Continental have teamed up to create the first production ready 4D radar for autonomous vehicles, the companies announced. The new advanced radar sensor (ARS) from Continental is called the “ASR540” and it was built on the Xilinx Zynq UltraScale multiprocessor system on a chip (MPSoC).
Silicon Valley chipmaker Xilinx Inc. and automotive supplier Continental have teamed up to create the first production ready 4D radar for autonomous vehicles, the companies announced. The new advanced radar sensor (ARS) from Continental is called the "ASR540" and it was built on the Xilinx Zynq UltraScale multiprocessor system on a chip (MPSoC).
The ARS540 is a compact, long-range 4D imaging radar with a 300-meter range, as well as high resolution. It offers a wide, 60° field-of-view enabling multi-hypothesis tracking for more precise prediction while driving. This helps a self-driving vehicle's software better manage complex driving scenarios, such as the detection of a traffic jam that's under a bridge.
The companies said the new ASR540 is the auto industry's first production-ready 4D imaging radar, which can support today's SAE Level 2 autonomous driving functions and all the way to Level 4 and 5 self-driving capability, which requires little or no human intervention.
Xilinx says its Zynq UltraScale family of MPSoCs are the world's highest performance adaptive devices to support advanced driver assist systems (ADAS) and autonomous driving applications.
"We are extremely pleased to be powering the industry's first production-ready 4D imaging radar. The sophisticated features in Continental's ARS540 accelerate the wider adoption of autonomous driving by bringing this advanced technology into passenger-owned vehicles. The combination of Continental's heritage in radar and Xilinx's legacy in adaptable silicon make this a very powerful offering," said Willard Tu, senior director of automotive at Xilinx.
The ARS540 4D radar.
The ARS540 4D imaging radar is capable of determining an object's elevation and range, whereas 2D radar only measures speed and azimuth, which is the horizontal angle of an object. 4D radar can be used to measure the height of bridges and highway overpasses.
4D radar also offers a longer range, which is critical for use in autonomous vehicles, as objects that can be identified and tracked from further away provide an extra layer of safety for the perception systems used in autonomous vehicles or those equipped with advanced driver assist systems (ADAS).
The ARS540 radar housing measures 137 x 90 x 39 mm, so it can be seamlessly integrated in the front bumper of most vehicles during production.
In addition, the ARS540 system's high horizontal and vertical resolution enables detection of hazardous objects on the road that are lower in height that conventional radar might otherwise miss due to having a narrower field of view.
"The Xilinx Zynq UltraScale+ MPSoC platform delivers the high performance and advanced DSP capabilities we needed to realize the ARS540, combined with adaptability and a market-leading selection of network interfaces capable of handling the wide array of antenna data at extremely high aggregate transfer rates," said Norbert Hammerschmidt, head of program management radar at Continental. "We are very proud to continue our long-standing partnership with Xilinx and to now provide the market with a technology that has the potential to save lives."
Xilinx is recognized for inventing the field programmable gate array (FPGA), which serves as a blank slate for hardware developers because it is programmable. In comparison, the popular Intel Core i7 SoC powering many laptops runs a specific set of instructions or programming logic that cannot be altered, as it is set in silicon during manufacturing.
The Xilinx Automotive Zynq UltraScale MPSoC however is fully programmable by the customer, so its serves as a versatile platform that allows Continental's ARS540 4D imaging radar to be used in multiple sensor-platform configurations. With its programmability, it's adaptable to each automaker's unique specifications when used for ADAS. It also supports parallel processing.
FPGAs are ideal for digital signal processing (DSP) applications, since they can support custom, parallel algorithms. The Parallel processing abilities of the Zynq UltraScale MPSoC's programmable logic delivers higher performance to support the ARS540's robust 4D sensing capabilities.
The Zynq UltraScale includes many digital signal processing (DSP) slices to enable hardware acceleration of real-time radar sensor inputs. It's also scalable for widespread use for ADAS for the auto industry.
ADAS features such as radar are becoming standard in many new vehicles. With the widespread adoption of these systems, the use of 4D radars by automakers will likely increase as well.
As vehicles become high-tech computers on wheels, the world's automakers are increasingly turning to hardware suppliers like Xilinx and Continental to supply the components that will be necessary to support partial and fully autonomous driving capabilities. The market for ADAS hardware is expected to rapidly grow over the next decade.
"We expect 4D imaging radar to take place in luxury cars and Robotaxis at first, leading to over US$550 million, a rise at a compound annual growth rate (CAGR) of 124% between 2020 and 2025. Xilinx and Continental, two innovative market leaders have an excellent opportunity by teaming up to develop this new sensing modality." said Cédric Malaquin, technology & market analyst, RF Devices & Technology at Yole Développement (Yole).
The new 4D radar from Continental will be used by a major automaker, extending Xilinx's reach into the automotive space as a hardware supplier with its SoC's. The automaker and other details will be announced soon.
Originally hailing from New Jersey, Eric is a automotive & technology reporter covering the high-tech industry here in Silicon Valley. He has over 15 years of automotive experience and a bachelors degree in computer science. These skills, combined with technical writing and news reporting, allows him to fully understand and identify new and innovative technologies in the auto industry and beyond. He has worked at Uber on self-driving cars and as a technical writer, helping people to understand and work with technology.
Ford is Testing a New Robotic Charging Station to Assist Drivers of EVs With Disabilities
Ford Raises the Prices of the F-150 Lightning Electric Pickup Due to Rising Raw Material Costs
The BMW 7-Series to Feature HD Live Maps From HERE Technologies for Hands-Free Highway Driving in North America at Speeds up to 80 MPH
AutoX to Use the 'Eyeonic Vision Sensor' from California-based SiLC Technologies for its Robotaxi Fleet in China
LG Develops ‘Invisible’ Speaker Sound Technology That Could Revolutionize In-Vehicle Audio
Researchers at South Korea’s Chung-Ang University Develop a ‘Meta-Reinforcement’ Machine Learning Algorithm for Traffic Lights to Improve Vehicle Throughput
Zeekr’s New 009 Electric Passenger Van is the World’s First EV to Feature CATL’s Advanced ‘Qilin’ Battery With a Range of 510 Miles
Redwood Materials is Building an Electric Vehicle Battery Recycling Facility in South Carolina
- China’s New Intelligent EV company JIDU Launches its Limited-Edition Robocar Called the ‘ROBO-01 Lunar Edition’
- Solid State Battery Startup Solid Power Completes its EV Cell Pilot Production Line
- New Premium Electric Vehicle Brand Zeekr Is Exploring IPO Options in the U.S. or Hong Kong, According to Sources
- SiLC Technologies Launches its Eyeonic Vision System, a LiDAR Sensor That Can Identify Objects up to 1 Kilometer Away
- Mercedes-Benz Begins Production of the Highly Anticipated EQS Electric SUV in Alabama
- California’s Electric Vehicle Sales for Q1-Q3 2022 Show That Tesla is Facing Growing Competition
- Volkswagen Breaks Ground on the First of Six European Battery Cell Factories as Part of a $20 Billion Investment
- Consumer Reports Survey Finds Roughly 28% of Respondents Don't Want to Buy an EV
- Researchers at South Korea’s Chung-Ang University Develop a ‘Meta-Reinforcement’ Machine Learning Algorithm for Traffic Lights to Improve Vehicle Throughput
- Automaker BYD is Emerging as One of Tesla’s Biggest Competitors in China, Latest Vehicle Registration Data Shows