Closed iyildirim closed 3 years ago
Initial Proposal:
Composite objects move like the other singular objects (that is, they only have linear velocity and no angular momentum).
When two objects touch, with a low probability they stick together and start moving together.
A given composite object might break apart with a low probability at any of its joints on a given time point.
What is the most efficient way of going about implementing this? I am happy to give it a try if people are busy. Let me know.
We would like to model such clusters of beads using Chinese Restaurant Process. We will utilize Pakman & Paninski approach here too using their Neural Clustering Process. This will enable us with a data-driven smart proposal distribution to sample cluster assignments based on the velocities and positions.
I think the data generative procedure is rather elegant
k
objectsWe can play with clusters have N > 2.. I think it would be cool
Let me know if you guys can take a stab at this. I would think it shouldn't be too complicated.
Just registering here so that we think about it. This is when you have a bird of flocks but then half of the birds separate to their own way. Or when you have two rectangles moving together part ways halfway. etc. Fig. 5 in Balaban et al. 2019 is an example.