ARM is looking to establish itself in the burgeoning autonomous car market with a new chip design that is aimed at addressing the high safety standards needed for not only driverless vehicles but also other areas such as industrial and medical robots.
Company officials on Sept. 20 unveiled the Cortex-R52, a system-on-a-chip (SoC) design built on the company’s ARMv8-R architecture that is designed to comply with a range of safety standards—such as ISO 26262 ASIL D and IEC 61508 SIL 3—that apply to situations in the growing internet of things (IoT), such as autonomous cars and robots in health care settings, where safety and security is paramount in the interaction between humans and machines.
The includes with robots that assist doctors in surgery to self-driving cars that need to understand the environment around them and immediately react to ensure the safety of the drivers and the people around the cars. In addition, the systems need to be highly secure to protect them against hackers.
“We are helping partners to meet particular market opportunities, especially in fully autonomous vehicles and robotics systems where specific functionality is required for safety-critical tasks,” James McNiven, general manager for CPU and media processing groups at ARM, said in a statement.
Like other chip companies, ARM—which is being bought by Softbank for $32.2 billion—is working to branch out beyond its core markets to gain traction in a broad range of emerging growth areas being fueled by the rapid proliferation of connected devices, systems and sensors that make up the growing IoT. ARM designs SoCs and licenses those designs to a wide variety of chip manufacturers, such as Qualcomm, Samsung and Applied Micro. Most smartphones and tablets run on ARM-designed processors, but now company officials are looking to extend the reach of the architecture into other areas, from the data center to the IoT.
A growing number of ARM chip partners—including Qualcomm and Broadcom—are rolling out new products for the autonomous vehicle space. ARM also has been building up its capabilities in the IoT, including with the acquisition last year of Offspark, a company that specialized in security software for connected devices and sensors.
In a post on the company blog, James Scobie, a product manager at ARM, wrote about the growing demand for safety and security in IoT systems.
“Across multiple markets, electronic systems are becoming more complex—including automotive, industrial control and healthcare,” Scobie wrote. “Vehicles are beginning to drive themselves, industrial robots are becoming increasingly collaborative, and medical systems are automated to assist with surgery or deliver medication. More of these systems are demanding functionally safe operation and requiring that functional safety be provided at a higher safety level than previous generations of systems demanded.”
The Cortex-R52 architecture was created to address those functional safety needs, not only in self-driving cars, but also in increasingly automated factories that include autonomous robots that use machine learning and vision systems to enable them to work with less human control, he wrote.
“Outside the factory, robotics will be used in environments too harsh for humans, such as the nuclear industry, where there is a need to maintain precise and assured operation,” Scobie wrote. “They can also be used in the medical operating theaters with remote surgery. In both areas, functionally safe operation is critical.”
A key point in the Cortex-R52 is that there is what officials called hardware-enforced separation of various software tasks to make sure the code that is critical for safety is isolated. The hardware is managed by a software hypervisor. Not only does this ensure the protection of the code, but also lessens the amount of code that must be safety-certified, which makes software integration, maintenance and validation easier and development faster, they said.
“The Cortex-R52’s ability to compartmentalize software provides our users with the best solution for safety without loss of determinism,” Fabio Marchiò, vice president of STMicroelectronics’ Automotive and Discrete Group and general manager of its Automotive Digital Division, said in a statement. “Its virtualization support simplifies the consolidation of applications and functions into a single processor, delivering a shorter integration time.”