- The brand new tyre strain monitoring system improves security and person experiences
- ST’s software program ecosystem software, STM32Cube.AI, accelerates the event of the sting AI perform working on the STM32 microcontroller
STMicroelectronics, a worldwide semiconductor chief serving prospects throughout the spectrum of electronics purposes, has introduced that Panasonic Cycle Expertise, Co. Ltd. (Panasonic) has adopted the STM32F3 microcontroller (MCU) and edge AI growth software, STM32Cube.AI, for his or her TiMO A e-assisted bike. ST’s edge AI options present a tyre strain monitoring system (TPMS) that leverages a sophisticated AI perform to enhance rider security and comfort.
Panasonic is a number one producer of e-assisted bikes in Japan and presents all kinds of merchandise for varied makes use of to the Japanese market. Their electric-assist bicycle for college commuting, TiMO A, runs an AI utility on the STM32F3 MCU to deduce the tyre air pressures with out utilizing strain sensors. Primarily based on data from the motor and the bicycle velocity sensor, the system generates a warning to inflate the tyres if vital. ST’s edge AI growth software, STM32Cube.AI, enabled Panasonic to implement this edge AI perform whereas becoming into STM32F3 embedded reminiscence house. This new perform simplifies tyre air-pressure upkeep, which boosts rider security and prolongs the lifetime of tyres and different cycle parts. It additionally helps to cut back the price and design work, as there is no such thing as a want for added {hardware} equivalent to an air strain sensor.
“We develop and manufacture e-assisted bikes with the mission of delivering environmentally pleasant, secure, and comfy transportation, accessible to all,” stated Mr. Hiroyuki KAMO, Supervisor, Software program Improvement Part, Improvement Division of Panasonic Cycle Expertise. “ST’s STM32F3 MCU gives value competitiveness and optimum features and efficiency for e-assisted bikes. By combining the STM32F3 MCU with STM32Cube.AI, we have been in a position to implement the progressive AI perform with out the necessity to change {hardware}. We’ll proceed to extend the vary of fashions with AI features and attempt to fulfil our mission by leveraging ST’s edge AI options.”
“ST has been actively engaged on the worldwide proliferation of edge AI in each {hardware} and software program, offering edge AI options to a variety of merchandise together with industrial and shopper tools,” stated Marc Dupaquier, Managing Director of Synthetic Intelligence Options, STMicroelectronics. “This collaboration marks a key step in our efforts, and we’re delighted to have contributed to the primary implementation of this AI perform in Panasonic’s e-assisted bike. We’ll proceed to suggest AI use circumstances and options for numerous markets, anyplace we might help to enhance our life.”
ST will showcase edge AI options, together with the STM32 MCU and a wide range of AI growth instruments, on the AI Expo at Tokyo Massive Sight (Could 22-24, 2024). The e-assisted bike and the motor unit (cutaway pattern) from Panasonic Cycle Expertise, which options the STM32F3 MCU and STM32Cube.AI, are additionally scheduled to be displayed at this expo.
The way it works
The STM32F3 MCU adopted for the TIMO A is predicated on the Arm Cortex-M4 (with a most working frequency of 72 MHz) and contains a 128KB Flash, together with varied high-performance analog and digital peripherals optimum for motor management. Along with the brand new inflation warning perform, the MCU determines the electrical help degree and controls the motor.
It leverages STM32Cube.AI to cut back the scale of the neural community (NN) mannequin and optimize reminiscence allocation all through the event of this AI perform. STM32Cube.AI is ST’s free edge AI growth software that converts NN fashions discovered by normal AI frameworks into code for the STM32 MCU and optimizes these fashions. The software optimized the NN mannequin developed by Panasonic Cycle Expertise for the STM32F3 MCU shortly and simply and applied it within the flash reminiscence, which has restricted capability.
ST presents a complete edge AI ecosystem for spreading edge AI to units utilized in a variety of situations. The ecosystem consists of STM32Cube.AI and likewise the NanoEdge AI Studio autoML software. Each instruments are a part of the soon-to-be-available ST Edge AI Suite. All of them can be found freed from cost.
