This has been a mystery to me.

All the walking robots look like idiots now. But we do have a lot of simulation-based results (Flexible Muscle-Based Locomotion for Bipedal Creatures ), so why can't we just apply the simulation results to a real robot and let it walk, not like an idiot, but like an running ostrich?

With the main loop running at more than 60 fps, I fail to see how possibly the program could fail to stop the robot from losing balance. When I balance a stick on my hand, I could probably only do 5 fps.

We have not only supercomputers connected to the robots, but also reinforcement learning algorithms at our disposal, so what has been the bottleneck in the problem of bipedal walking?

  • $\begingroup$ Hi and welcome to AI SE! You say "All the walking robots look like idiots now." Can you please link us to a video/reference that shows that all walking robots walk like idiots, which is possible? Anyway, I assume you're talking about real-world robots, given that you show us a video of simulated robots walking more or less normally. $\endgroup$ – nbro Mar 19 at 14:01
  • 2
    $\begingroup$ See the Atlas by Boston Dynamics. He kinda looks like an idiot in some parts of this video: youtube.com/watch?v=rVlhMGQgDkY :) I think the road from simulation-to-physical is not a trivial one. There are probably some hard challenges to tackle from a mechanical perspective. Otherwise, programming an agent to do bipedal walking in a simulated environment doesn't seem to challenging to me and is probably straightforward via genetic algorithms. $\endgroup$ – SpiderRico Mar 19 at 17:25

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.