MIT 6.S191 (2020): Generalizable Autonomy for Robot Manipulation

[@cagneymoreau4216]

because things change so fast this recent high level view is a great jumping off point for further study. thank you!

[@darkhanzholtayev3224]

powerful lecture, I like kind of things like how they think and ask from themselves right questions.

[@minkbag3843]

Lol the subtitles at 40:09. Kinda ironic :D

[@louerleseigneur4532]

thanks

[@Avisheknandi12]

25:57 Machine Learning in Early Human State!!! Its learning to use the tools what ours ancestors used.!!!

[@hanyanglee9018]

3:20 Any one knows the video? link plz. thanks.

[@keanhong2]

i guess you need this kzbin.info/www/bejne/laSlc5SEjsqraac or u can find more video on Boston Dynamics on KZbin Channel , there is many Robots video u can watch

[@RishabhJain-uk2qt]

I have a question but before that first, I watched all videos till this one I grabbed like every part but couldn't understand them. Like in the first 6 lectures we got brief about the techniques of deep learning and a bunch of other stuff but these guest lectures couldn't bring anything from this, we learned beginner than directly go for the expert. Coming to the question is I would like to know what are the things needed to understand briefly, these upcoming technologies and these guest lectures? either mathematical knowledge or the knowledge about these technologies? If anyone could answer this query of mine I would be very much thankful.

[@mohammedfawaaz693]

Same question

[@siddhanttandon4427]

You need to invest time in this topic. Read more and watch videos on youtube regarding concepts you did not understand in the guest lectures and then after a while, you will be able to connect the dots. Still, to answer your question, I will say having a strong mathematical foundation in Bayesian learning, statistical inference, and numerical optimization will be very useful in understanding these topics on a deeper level, but those subjects are a full undergraduate degree.

[@dennysam829]

I think the initial lectures aimed to give you a foundation and I personally a lot while doing the lab assignments. The initial lectures were also just giving you an overview of the dominant fields in DL (they literally put together generative in a 40 min lecture). The objective of this seems to be for us to dive deeper into things interest for us. We won't be able to master both AI and robotics, just like we wouldn't master organic chemistry and quantum mechanics . These lectures are giving you , exposure as to what all are possible out there. No course is going to cover everything at once.

[@zuyuanzhu]

It seems no one cares about robot manipulation, given that there are hundreds or even thousands of comments in other lectures.

[@zeesamuel9885]

my dog is smarter than these robots lol.