News

Tensor and Arm Partner on Compute Platform for Autonomous Robocar

• By John K. Waters
• March 12, 2026

Tensor and Arm have announced a multi-year collaboration to develop the computing architecture for Tensor’s planned autonomous Robocar.

Under the partnership, Tensor will use Arm’s compute platform to power artificial intelligence workloads across the vehicle as it prepares to commercialize its Robocar fleet in 2026. The companies said each vehicle will integrate more than 400 ARM-based processor cores to support autonomous driving functions.

The collaboration centers on what Tensor calls an AI-defined vehicle architecture for Level 4 autonomy. Level 4 systems are capable of operating without human intervention under defined conditions.

According to the companies, each vehicle will incorporate 433 Arm based cores across multiple processor families, including Neoverse AE for high throughput AI processing, Cortex X processors for system control and in cabin AI features, Cortex A cores for vehicle functions such as drive by wire and lidar processing, Cortex R cores for safety critical systems and Cortex M cores for low power subsystems.

The compute platform distributes processing tasks across the vehicle, from onboard computing systems to sensors and other subsystems, while meeting automotive safety and power requirements. The system also operates alongside NVIDIA accelerated AI processing used in Tensor’s autonomy stack.

Tensor said its Robocar platform includes a sensor suite designed to support autonomous navigation. According to the company, the vehicle incorporates 37 cameras, five lidars, 11 radars, 22 microphones, 10 ultrasonic sensors, three inertial measurement units, satellite positioning capability, collision detection sensors, and other monitoring systems.

Drew Henry, executive vice president of Arm’s Physical AI Business Unit, said autonomous vehicles require high-performance computing systems that can operate reliably in physical environments.

“Autonomous vehicles are a leading example of how AI is shifting to the physical world, requiring world-class, high-performance, safe, and power-efficient compute foundations to transform the future of mobility in meaningful and tangible ways,” Henry said.

Dr. Jewel Li, chief operating officer of Tensor, said the partnership is intended to support the engineering requirements needed to deploy autonomous vehicles at scale.

“Delivering personal autonomous vehicles at scale requires more than breakthrough AI and autonomy; it demands advanced engineering for safety, redundancy, reliability, and power efficiency,” Li said.

Tensor said it is working with a number of automotive and technology partners on the Robocar platform, including Autoliv, ZF, Continental, NVIDIA, AMD, Qualcomm, Samsung, and Oracle.

The company said the Tensor Robocar is expected to be introduced in the United States, the European Union, and the Middle East markets in 2026.