The feed back loop is getting reduced by those new ways of training, simulation and video generation with realistic physics is kind of changing the game.
Can always skip the real world for training and evolve the controller in simulation.
Currently working on modernizing SIGEL (2000-era project at the University of Dortmund), which uses genetic programming to evolve walking programs for simulated robots in a physics engine.
Some of the 'evolved' walkers so far can be found at youtube.com/@virtualspecies
Differnent kind of beast entirely compared to what NVIDIA is doing, but then again it's fun to see what evolution comes up with - and it works on humble hardware too
Like said by others, the sensor problem is a real one, and personally I don't see a robotic hand matching the dexterity of a human one, within a viable economic cost and sufficient robustness, before a long time (but I could be wrong ).
But for the part that concern physical understanding of the world, adaptability, and basic manipulation, it feels like the field is going through a break through.
The implication might be the apparition of generalist robots, that could perform (in the limit of their dexterity) on a wide range of tasks, commanded by natural language.
Sure, not on pair with human dexterity yet, but as a thought exercise, think of all the things you could do with simple claws, or heavy glove. What if a robot was able to do the same ?
"Matching the dexterity" is a false goal. It's focusing on the wrong things.
As teleoperation readily shows, even a very dumb primitive hand can be salvaged if you get a very advanced control policy to drive it.
Sure, it would still take a lot longer for a well tuned robot with just a pair of UMI-style grippers to tie shoe laces than it would a practiced human. But a robot doesn't have to work faster than a human. "It can do the same task for cheaper" is often good enough.
The right thing to focus on is: AI. We already have robot bodies that are good enough to do many economically valuable tasks. We don't have the AI that would make those bodies perform to their potential. Modern robotics is an AI problem above all.
There are such things as established robotics giants, supplying robotic arms to factories like car plants that put together giant metal panels together and junk food industries assembling muffins into plastic trays and boxing up.
Those companies seem to be rushing to get NVIDIA Isaac systems and some even buying DGX pod hardware to get those systems and processes integrated into existing factories to avoid getting disrupted by startups. I guess those + AI companies like Google applying LLM derived technologies to robotics is what GP is referring to.
Energy, land and row materials will be the main limiting factors.
Mega corp will advance technology exponentially, but for the rest of us we will live in a mix of medieval life style assisted by robotic and low tech. People will exode city and go back to the countryside.
For what concern my self, I'm buying arable land, maybe in couple of years home food production will be fully automated.
> Energy, land and row [raw] materials will be the main limiting factors.
For humans, I think these are limitations because of time and scarcity, but mainly time - given sufficient time, humans can gather all of these. But individual humans do not have indefinite amounts of time. So energy, land and raw materials are scarce for individual humans, and they ascribe value to these.
For machines, I think any limitations on energy, land and raw materials would be a temporary situation, because time isn't the same for machines - a machine could simply keep doing what it's doing until it runs out of energy - which is infinite coming from the sun. Or at least until the energy budget of the population of machines exceeds the energy supplied from the sun. But that won't happen for a while. And parts that wear down are simply replaced.
On a planet as large as the Earth, again, land and raw material limitations are a non-factor until the entirety of the Earth is converted to machines, assuming the energy from the sun is sufficient to account for the conversion.
What would be the timeline for this transition from human society to self-sustaining machine society? I think this might be a question for someone smarter than me (i.e., gpt or claude). I wonder if there aren't already people modeling this scenario to estimate timelines.
Hopping that space colonization will become a thing for the top 0.0001% and that earth will not be their main concern, but yes I’m an optimistic person by nature.
https://www.youtube.com/watch?v=3Y8aq_ofEVs&pp=ygUKbnZpZGlhI...
PS: It's sad that robotic does not seems to get a lot of traction on HN :(