Extreme parkour with legged robots
extreme-parkour.github.io
Extreme parkour with legged robots
1–10 of 195 posts
Re: Extreme parkour with legged robots
#2there ought to be plenty of money in this for delivering explosive payloads...
(Edit: although come to think of it, in the animal world, jump height is much more constrained by 9,81 m/s2 than by body size)
Re: Extreme parkour with legged robots
#3As a reminder: CMU and its robotics program is intimately associated with the US Department of Defense, and although there are certainly civilian applications for this technology, one of the most likely short-term applications is improving legged drones for battlefield deployment (often, it should be said, in humanitarian roles, including search and rescue, or support roles, such as ammo, food, and water resupply, but deployment of armed legged drones is also an active area of research).
Here's a military news article covering the same umbrella grant program this research was funded under: https://www.c4isrnet.com/2022/06/23/darpa-adding-common-sens...
Re: Extreme parkour with legged robots
#4This doesn't look like an extreme environment at all, yet the robot still has his legs sliding quite a bit on various obstacles, which surprised me since it can do complex stuff. They only show slow-motion on perfect moves, which is a bit disingenuous. I thought SOTA was better than this honestly.
Re: Extreme parkour with legged robots
#5Only thing missing in that video is some rando walking by on campus in the background yelling “when they come, I hope they come for you first!”
Re: Extreme parkour with legged robots
#6This gives me Black Mirror-fueled nightmares... not least because those videos suggest that a Black Mirror scenario may not be that far off and what probably saves us for now is battery capacity.
Re: Extreme parkour with legged robots
#7there ought to be plenty of money in this for delivering explosive payloads... (Edit: although come to think of it, in the animal world, jump height is much more constrained by 9,81 m/s2 than by body size)
Physics constrains jump height to be about a few meters regardless of size. The basic problem is that the total energy required scales with mass, but the total energy available also scales with mass. The two end up cancelling out and you get a maximum jump height that is independent of size.
What really matters is the energy density of your storage medium, which is the same to an order of magnitude for any system based on chemical energy. So both a flea and an elephant (along with battery-powered robots) can jump about a meter or two in height.
Re: Extreme parkour with legged robots
#8there ought to be plenty of money in this for delivering explosive payloads... (Edit: although come to think of it, in the animal world, jump height is much more constrained by 9,81 m/s2 than by body size)
Artillery exists.
Delivering explosive payloads is a solved problem. Detecting humans is a solved problem. The hard part is reliably distinguishing enemy solders from friendly soldiers or civilians.
Re: Extreme parkour with legged robots
#9This gives me Black Mirror-fueled nightmares... not least because those videos suggest that a Black Mirror scenario may not be that far off and what probably saves us for now is battery capacity.
What's the Black Mirror scenario?
Re: Extreme parkour with legged robots
#10This doesn't look like an extreme environment at all, yet the robot still has his legs sliding quite a bit on various obstacles, which surprised me since it can do complex stuff. They only show slow-motion on perfect moves, which is a bit disingenuous. I thought SOTA was better than this honestly.
I thought the opposite. Watching it scrabble to get its hind legs up on the ledge - exactly as a dog would do, with the benefit of millions of years of evolution behind it - was very impressive to me.