Product overview
Description
The AEKD-AICAR1 is a versatile system based on a long-short term memory (LSTM) recurrent neural network (RNN), which can provide a car state classification: car parked, car driving on normal road conditions, car driving on a bumpy road, car skidding or swerving.
The innovative idea in the AEKD-AICAR1 is to define an ECU detection node with an embedded artificial intelligence processing.
The AEKD-AICAR1 houses an SPC58EC chorus 4Mbytes microcontroller, which can acquire discrete acceleration variations on a three-axis reference system.
The AEKD-AICAR1 system represents a reference for the automotive AI on the edge processing.
It is possible to replace easily the sensor with another one that belongs to the ST MEMS family. It is also possible to modify the neural network and/or retrain the neural network. The new neural network is converted into a library executable by the MCU using SPC5-STUDIO-AI.
-
All features
- The AEKD-AICAR1 is a hardware kit that consists of the following boards:
AEK-MCU-C4MLIT1–SPC58EC Chorus 4 Mbytes MCU board AEK-LCD-DT028V1–SPI-based TFT LCD display AEK-CON-SENSOR1–MEMS sensor connector for SPC5 MCU STEVAL-MKI206V1–Adapter board with AIS2DW12 digital motion sensor - Pretrained neural network code flashed in the MCU
- Classification of four vehicle states: parking, normal road, bumpy, and skidding
- Real-time data collection and processing of MEMS sensor data
- LCD display for vehicle state
- On MEMS disconnection, the system performs classification based on the internal datalog in the MCU flash memory
- 28x18x7 cm
- Supplied by 12 V or by eight AA batteries (not provided in the package)
- The AEKD-AICAR1 is a hardware kit that consists of the following boards: