1
$\begingroup$

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?

Improve this question
$\endgroup$
2
  • $\begingroup$ 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
    Commented Mar 19, 2020 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
    Commented Mar 19, 2020 at 17:25

0

Reset to default

You must log in to answer this question.

Browse other questions tagged .