An Open Source package that allows video game creators, AI researchers and hobbyists the opportunity to learn complex behaviors for their Non Player Characters or agents
Note: The exact features of the sensor and whether to implement it is yet to be determined, it's just an idea at this point.
The most basic functionality would include adding a relative position vector from an object to an object that is clipped at some distance and normalized.
Some possible additions to the basic idea (not all would necessarily be added):
Allowing multiple objects (an array of Node2D/3D) could be useful, and/or all objects that have a tag.
Including additional object properties such as linear velocity for objects that have it.
Similar to above, including custom properties that the user specifies.
Note: The exact features of the sensor and whether to implement it is yet to be determined, it's just an idea at this point.
The most basic functionality would include adding a relative position vector from an object to an object that is clipped at some distance and normalized.
Some possible additions to the basic idea (not all would necessarily be added):
The name for the state sensor is inspired by https://huggingface.co/docs/simulate/main/api/sensors#simulate.StateSensor, although I'm not familiar with the exact features or implementation of the sensor in Simulate.