sitzikbs/3dmfv-tutorial

This repository contains the python files from the blog post of 3DmFV tutorial

3dmfv-tutorial's Issues

Typo in visualization code

3DmFV-Tutorial/visualization.py

Line 57 in ef5d35c

derivatives = [r"\max{$g_{\alpha}}$",r"$\sum g_{\alpha}$",

I think the right code may be:

    derivatives = [r"$\max{g_{\alpha}}$",r"$\sum g_{\alpha}$",

Isn't it?

puzzle about np.power(batch_sig[:, :, :, 0], D)

Thanks for your quickly reply. Actually, I have read your paper released in IEEE ROBOTICS AND AUTOMATION LETTERS. However, I still don't understand the meaning of np.power(batch_sig[:, :, :, 0], D) after I read Equation 1 in section 3.1, it doesn't stand for sqrt(delta(sigma)) as only variance of the first variable in Gaussian is used in np.power(batch_sig[:, :, :, 0], D), could you give me more help?Thank you!

Compute probability per point

hi, I have read the code in utils.py, but I am puzzled about probability computation in line 295 to 296.
p_per_point = (1.0 / (np.power(2.0 * np.pi, D / 2.0) * np.power(batch_sig[:, :, :, 0], D))) * np.exp(
-0.5 * np.sum(np.square((batch_points - batch_mu) / batch_sig), axis=3))
Why the item-np.power(batch_sig[:, :, :, 0], D)- is multiplied? I don't know why the first axis and D are used, could you help me?