Integrating signal processing as well as AI algorithms into MEMS sensors allows local decision-making and significantly saves power and space.
STMicroelectronics (NYSE: STM), a global semiconductor leader serving customers across the spectrum of electronics applications and a top manufacturer of Micro-Electro-Mechanical Systems (MEMS), today announced the launch of the Intelligent Sensor Processing Unit (ISPU) that combines a Digital Signal Processor (DSP) suited to run AI algorithms and MEMS sensor on the same silicon.
Additionally, it reduces the size by a factor of 80% over systems-in-package devices, and cutting power by as much as 80percent, combining sensors and AI places electronic decision-making at the Edge. This is this Onlife Era where innovative products that are powered by smart sensors can perceive, process, and then take action that bring together technology and physical reality.
It is the Onlife Era acknowledges living with the constant support of connected technology, allowing for smooth, transparent interactions and seamless transitions with no distinction between offline and online. Through ISPU, ST is ISPU, ST is enabling this new era of technology by helping transfer intelligent processing to sensors that are able to support the fabric of our lives: no more in the Edge but instead in the Edge.
ST’s ISPU has significant benefits with respect to the four Ps of power consumption packaging, performance and cost. The exclusive ultra-low-power DSP is programmable in C which is a common language for many engineers. It also permits quantifying AI sensors to run high-precision, single-bit neural networks. This guarantees superior performance and accuracy for tasks like identification of anomalies and activity recognition through the analysis of inertial data.
“While technically challenging, integrating ST’s sensors on the same piece of silicon with our ISPU does improve sensor-based systems from an online experience to an Onlife one. It advances the sensor’s features to speed decision-making by reducing data transfers, enhancing privacy by keeping data local, while reducing size and power consumption, which cuts costs,” said Andrea Onetti, Executive Vice President, MEMS Sub-Group, STMicroelectronics. “Moreover, the ISPU is easily programmable with commercial AI models and can ultimately operate with all of the leading AI tools.”