Read for example: http://homotopytypetheory.org/2013/03/08/homotopy-theory-in-...
So HoTT might solve a problem for constructivists working with Coq. Problems you can entirely avoid by not working constructively (or with Coq, for that matter). Therefore, at this point, there is no evidence at all that HoTT might improve the state of the art in interactive theorem proving.
That does not mean that this evidence might not come up at some point.
How can I be sure in my judgement? Well, I don't have to understand string theory to be sure at this point that it is not relevant to interactive theorem proving. I would change my mind if somebody points out evidence that string theory is actually of major relevance to interactive theorem proving.
Edit: I would even start learning string theory then.
Now that is utter and complete nonsense. And that is why I am criticising HoTT. HoTT might be a beautiful mathematical theory. I am not competent in judging that, to be so, I would have to invest more time. But there is not a single shred of evidence that HoTT will improve automated, or for that matter interactive theorem proving. And I am pretty competent to judge that.