An immediately useful application of this is in roombas that can not just clean the floor but effectively avoid/move obstacles. All the vaccums i have gotten generally get stuck or suck in paper/usb cables and get stuck in corners. There are two planning aspects here 1. Choosing a workflow(i.e. a series of general steps that can achieve a goal) 2. Generating low level policy actions given a state(i.e. sensor data). L…
I don't think its even necessary to pick up the wire. The newest vacuums use cameras to try to avoid common obstacles, but the image classification is so rudimentary they get stuck anyway. Having the common sense to stay away from the end of the cable is all the robot needs to not get stuck.
Robotics is such a lovely world. For the hobbyists, I'm really curious about how to get the home-brew robotics training lab working at home? The last time I reviewd this, you'd spend thousands of dollars just to get a reasonable robotic arm. Right now, if work is relegated to the rich research departments of mega corporations, this certainly doesn't seem more interesting than a corporate press release..
This is false to very large degree, you have simulations for robotics, and you can buy/build your self cheaper versions.
What are some good open source simulators suitable for robotics development?
(preferably a physics simulator library, not an entire framework)
This seem like an cool upgrade from RT1, judging from the result. It seems to now also output the delta of the end-effector pose, which was previously handled by a different motion planner. It does seem like this work (and a lot of robot learning works) are still stuck on position/velocity control and not impedance control. Which is essentially output where to go, either closed-loop with a controller or open-loop wit…
thank you for sharing your thoughts! is there anyway I can get in touch with you, through email or some other means?
This is a step towards what I think AGI would be: a model trained on visual and language data from the Internet used as a prior for an action model (finetuned perhaps with reinforcement learning) that would be able to learn how to use the frozen prior to make useful actions; I would separate the prior from the action model so there is no possibility of catastrophic forgetting (this is dealt by co-fine-tuning the mode…
That seems like a real step in the direction of AGI but not anywhere near the full solution. The current context windows are far too small to replicate human intelligence. I can’t quite put my finger on it but it feels like we are missing a sort of bridge between learning done in-context and offline training. A true AGI would be able to learn in-context and then quickly apply those lessons to the base model. If in context learning is analogous to a person’s short term memory, we need a mechanism to move short term memory to long term memory.
In the near term I expect we will see much more general robotics that know how to do lots of tasks and can follow basic instructions, but lack the ability to develop complex new skills over time. Robots doing dishes and laundry will soon be feasible, just don’t expect unbounded self improvement.
This is a step towards what I think AGI would be: a model trained on visual and language data from the Internet used as a prior for an action model (finetuned perhaps with reinforcement learning) that would be able to learn how to use the frozen prior to make useful actions; I would separate the prior from the action model so there is no possibility of catastrophic forgetting (this is dealt by co-fine-tuning the mode…
That seems like a real step in the direction of AGI but not anywhere near the full solution. The current context windows are far too small to replicate human intelligence. I can’t quite put my finger on it but it feels like we are missing a sort of bridge between learning done in-context and offline training. A true AGI would be able to learn in-context and then quickly apply those lessons to the base model. If in co…
I agree that it would be much better if a model could move the knowledge to the weights, but I don't think it's necessary. Models like RNN have practically infinite lossy "context window", and I think it would be much more reasonable to find an RNN architecture that would scale like a transformer than what you propose, while still achieving our goal. An alternative analogy you can think of is that the frozen weights in the model are our DNA, while the state or "context window" of the model is our state.