Reverse engineering controller sensitivity/aim for several games ie acceleration curves, deadzones, etc


A machine learning project I am working on requires me to interface with an Xbox controller connected to a PC. The implementation must do the following two things:

Record the joystick input from the controller into a file at regular intervals, along with an associated screenshot from a game. (ex: 60 times a second).

With this data I want to try to replicate/reverse engineer a few different FPS games sensitivity’s,dead zones, acceleration curves.

Does anyone have any idea as to how I'd go about doing this? I'm not sure where to start. If this question isn't appropriate for this sub, I’m where could I ask?

Austin Fenne

Posted 2019-08-04T10:33:19.023

Reputation: 31

In the AI literature the idea is called “game log recording”. A human operator plays a game, and during the task all the joystick inputs are recorded. If the data is visualized as a plot, a motion capture like diagram is the result which contains a time axis together with the measured values. The difficulty is to convert the raw numerical values into a linguistic description. – Manuel Rodriguez – 2019-08-04T11:53:34.143

No answers