Engineer kache argues simulator training can resolve the bottleneck.
Positive users express optimism about hybrid data approaches for robotics scaling while negative users argue the core issues are hardware limitations or inadequate simulations rather than data collection.
wrong. it's simulators

@chris_j_paxton Would serve robotics data collection apply here? I believe they are already selling data if i’m not mistaken

@yacineMTB IRL is the ultimate simulator.

@chris_j_paxton Always was wondering why there was such a little focus on hybrid approaches. I'm confident the best outcome is finding the right mix of the different types of data.

@yacineMTB Wrong, it's actually time. We can't account for unknown unknowns until we know them in due time.

@yacineMTB it's incredible how much real-world time companies will waste instead of improving the damn sim. blows my mind

@yacineMTB wrong. Robotics problem is hardware problem. Robotics is not gonna advance one centimeter, As it is dominated by CS folks.
Engineer kache argues simulator training can resolve the bottleneck.