basavasagar18.bsky.social
MS Robotics UMich!!
8 posts
13 followers
68 following
comment in response to
post
Yes, I agree. I am thinking of a distinct future when we have all the resources in our solar system. Lol, too hypothetical!
comment in response to
post
Fine-tuning is a fine game when you know the test-distribution and I believe that active fine-tuning at test time will be on the cards. But none can truly generalize out-of-distribution. You either collect a hell lot of data or stumble upon an architecture that truly generalizes of OOD for your task
comment in response to
post
Example the bias of CNNs to exploit high-frequency components in image might be good for CV benchmark performance, if you feed the same representations to a robotic policy then it is clearly sub-optimal, shape is more important here ....
comment in response to
post
Well, is it efficient, yes! But is it the optimal, probably no. The problem with pre-trained modules is that their representations are biased by their objective to fit a benchmark. And this objective encapsulates years of community based benchmark overfitting that we don't even think of biases ..
comment in response to
post
I think pure end-to-end learning will be a deployment scenario. Most of the model based planning methods and priors will be used for data generation in simulation for efficient exploration in data collection. But it is hard to win over pure end-to-end learning system if you have the data once.
comment in response to
post
Yes, compared to previous years it has become much more accessible and more like typical supervised learning, which I believe is great. Also looking forward towards your lab opening and following your research. Daniel Brown talks about you!
comment in response to
post
Interesting,I think most people don't apply robotics as an application area because of slow feedback loop. I also don't think that architectures developed for other applications may not be the most optimal for robotics. I believe it depends on the assumption you are making on the data distribution.
comment in response to
post
Hmm, interesting. What do you think is the use case of RAG in robotics? Like Behavior Retrieval?(arxiv.org/abs/2304.08742)