POLYN Technology Announces Tapeout of Automotive Chip

Estimated reading time: 1 minute

POLYN Technology, a leader in neuromorphic technology with application-specific Neuromorphic Analog Signal Processing (NASP) products, has taped out a VibroSense™ engineering chip featuring an analog neuromorphic core for tire friction monitoring.

This is POLYN’s first chip, developed in cooperation with GlobalFoundries, using more advanced nodes for this and the next generation of products.

The milestone accelerates the adoption of intelligent, physics-aware sensing technologies for next-generation ADAS and autonomous driving platforms.

Following extensive real-world validation and data-driven development, POLYN’s advanced solution for tire-road friction estimation leverages neural networks to process high-frequency sensor data. The system is trained on diverse driving conditions to estimate the peak friction coefficient (PFC) in real time, enabling predictive insight into road grip before critical events such as braking occur.

Validation through controlled braking scenarios, along with correlation with industry benchmarks, demonstrates strong alignment with real-world friction behavior across standard surfaces, including asphalt, concrete, and aquaplaning conditions. The solution is engineered to maintain reliable performance under complex and non-ideal driving conditions, such as wet roads or uneven terrain, providing stable estimates with confidence-aware outputs.

VibroSense Tire Monitoring Solution is designed to operate in conjunction with a TPMS SoC, using accelerometer vibration signals to monitor tire–road grip.

“There is strong and growing interest in sensor data pre-processing implemented in silicon for automotive applications,” said Aleksandr Timofeev, CEO of POLYN. “This tapeout marks an important milestone in NASP chip development and furthers our mission to unlock new opportunities for advanced vehicle systems with VibroSense - an energy-efficient neuromorphic sensing solution.”

POLYN’s advanced neural network compiler and customized EDA flow generate the neural core layout for the VibroSense chip, incorporating thousands of neurons, weight matrices, and interconnections. NASP technology utilizes analog neurons for signal processing in a truly asynchronous mode, resulting in extremely low power consumption and low inference latency. This enables deployment of the VibroSense chip within the tire, making it an industry-first practical solution for direct road sensing.

Timofeev added that POLYN is actively collaborating with Tier 1 suppliers and automotive OEMs seeking to obtain real-time tire-road friction estimates directly from the tire. Indirect calculations and virtual sensors cannot provide the required accuracy under rapidly changing road conditions, particularly in autonomous driving scenarios.