Question related to motion sensor LSM6DSOX

[Jasmine]

Hi, 

We need to use motion sensor LSM6DSOX for position tracking. 

We can not use GPS in the system, and the position accuracy we need to achieve is 1 m after moving 11 meters. 

So I have a question related to LSM6DSOX :

In the datasheet, the output is linear acceleration, the linear acceleration there means raw acceleration data or the acceleration without gravity components?

Does the machine learning core do sensor fusion, provide temperature compensation for accelerometer and gyroscope bias, and output orientation and linear acceleration (remove gravity)?

What algorithm is used for the sensor fusion in the machine learning core? KF (Madgwick algorithm), EKF or linear optimization algorithm? The reason I would like to know is that we do not need real-time process, so it’s possible for us to process data in a PC, we are thinking to use a more advanced algorithm to improve accuracy. If advance algorithm is already done in the machine learning core, then there is not much accuracy we can improve. 

Thank you very much for your time!

With best wishes

Jasmine

[Eleon BORLINI]

Hi @Jasmine​ , sorry for the (very) late answer... The MLC (machine learning core) is an embedded feature in the LSM6DSOX sensor and is not directly related to the sensor fusion algorithm. The MLC is a digital block that can be configured through a series of registers, accepts raw data as input and gives a label in output that is the result of the classification of the decision tree with which the MLC has been configured through the register. The most complete document on the use and the setup of the MLC feature is AN5259. On the other side, sensor fusion is an algorithm that has been developed on STM32 NUCLEO based reference designs for MEMS sensors, and is described (although not in every details) by the UM2220, and is basically a set of functions that get data from the accelerometer, gyroscope (6-axis fusion) and magnetometer (9-axis fusion) and provides real-time motion-sensor data fusion.

Btw, which is your target application?

Regards