Has anyone here ever thought about trying to get robots to be able to do skateboard tricks? It seems to me that unless they could be perfect every time you would first have to teach them to fall without damaging themselves. I bet that would have lots of applications in other domains!
After a decade of skateboarding, I would say this is not a possibility now at least. The problem is the constant balancing and the constant shifting of weight. Even after a decade of muscle memory, I fall riding down the sidewalk regularly. Current robots seem to be hard-pressed to handle even a little shove.
I found algorithms far superiour than me for 1-2d problems. (inverse pendulum problems, balancing a ball on a 2d plane and exactly controlling its position).
So problems probably are too many degrees of freedom, challenges like proper vision to plan ahead and steer, and in the shoving case also the security aspect (since there's a hard limit on how much force/acceleration a robot can use if it is handled by humans, and if you can shove it, it surely is).
In that sense, a skate-bot (without security limits) seems to be easier than a walking one with limits (which I assume you meant) to me since it takes down the degrees of freedom.
I bet there are people alive now that will be able to produce something like this sooner than we think. I agree that it is a difficult problem to solve ... I just think that we are the verge of being able to attempt something like this. Start by getting the robot to be able to ride on flat ground then just take it through Tony Hawk's trip tips volumes 1-3 building it up step by step.
