The process you need to go through is actually similar to the camera calibration procedure in OpenCV or other software. The chessboard is replaced by your robot, and you can skip the intrinsic estimation step. I would actually recommend you take a look https://github.com/hengli/camodocal a multi rig camera calibrator.
Anyways a high level overview.
The two ...
Short answer: At first, a motion capture recording of the robot is created. Secondly, the recording is converted into a task model.
Long answer: A human operator is the natural source for providing high quality control signals. A well trained operator is able to let the robot solve difficult situations. The only problem is, that the actions of a human ...
In general, you want to build a 3D map of the environment, or more likely an approximation of a 3D map. Typically such maps are grid-based across the horizontal plane, and each cell contains some additional information like height (see '2D occupancy maps', 'digital elevation models' and '2.5D grid maps' for more information). They often focus on geometric ...
from my experience, you can do it on the 2D image together with the disparity information.
tracking based on image has been well developed in recent years, there should be many advanced algorithms you can use directly(may based on NN
you can project the detection result from the 2D image to your disparity to get a distance of the object, which ...
I am missing something?
Indeed, the context is standard stereo and (all) pixel comparisons ($w\times h$).
In a rectified image, the epipolar line can be typically be about the width of the image. Thus the search range would be $D\times w$.
Thus total number of comparisons = $D\times w \times wh$.