Ben Ling
@belinghy.bsky.social
I make believable virtual characters at Electronic Arts | UBC PhD
This particular example is done using DeepMimic arxiv.org/abs/1804.02717, with very small changes to the reward and policy input. We have a related paper on motion cleanup coming out soon and looking forward to sharing it!
February 8, 2025 at 9:49 PM
This particular example is done using DeepMimic arxiv.org/abs/1804.02717, with very small changes to the reward and policy input. We have a related paper on motion cleanup coming out soon and looking forward to sharing it!
I think pdf links only provide enough information to link to show the "terrible" case. Guessing the "good" one shows up only when the pdf has been preprocessed. Not a Zotero user, but I worked on a bookmarklet providing similar functionality github.com/belinghy/PDF....
February 7, 2025 at 5:20 PM
I think pdf links only provide enough information to link to show the "terrible" case. Guessing the "good" one shows up only when the pdf has been preprocessed. Not a Zotero user, but I worked on a bookmarklet providing similar functionality github.com/belinghy/PDF....
I really like this example. Besides the improved collision, the solution involved multiple steps:
1. L knee collides with R reducing lower body momentum
2. L falls early allowing R arm to swing over
3. L foot hooks R shin causing R to fall
4. R carries enough momentum to slide the right distance
1. L knee collides with R reducing lower body momentum
2. L falls early allowing R arm to swing over
3. L foot hooks R shin causing R to fall
4. R carries enough momentum to slide the right distance
February 6, 2025 at 7:50 PM
I really like this example. Besides the improved collision, the solution involved multiple steps:
1. L knee collides with R reducing lower body momentum
2. L falls early allowing R arm to swing over
3. L foot hooks R shin causing R to fall
4. R carries enough momentum to slide the right distance
1. L knee collides with R reducing lower body momentum
2. L falls early allowing R arm to swing over
3. L foot hooks R shin causing R to fall
4. R carries enough momentum to slide the right distance
Multiplayer motion cleanup is like solving a physics puzzle—agents learn to apply forces collaboratively to reproduce the desired motion. Recapturing with mocap is impractical—or even impossible depending on how closely the motion must match—but simulation makes it attainable.
February 6, 2025 at 7:41 PM
Multiplayer motion cleanup is like solving a physics puzzle—agents learn to apply forces collaboratively to reproduce the desired motion. Recapturing with mocap is impractical—or even impossible depending on how closely the motion must match—but simulation makes it attainable.