[SIGGRAPH Asia 2025] Physics-Based Motion Imitation with Adversarial Differential Discriminators
Автор: Ziyu Zhang
Загружено: 2025-10-04
Просмотров: 2448
Tired of designing and tuning reward functions? ADD can help!
ADD is an adversarial Multi-Objective Optimization (MOO) solution that is broadly applicable to a range of problems, including motion tracking. It automatically balances the various objectives, reducing the burden of manual reward engineering and weight tuning.
Website: https://add-moo.github.io/
Arxiv: https://arxiv.org/abs/2505.04961
Code: https://github.com/xbpeng/MimicKit
Timeline:
00:00 Overview
01:09 ADD for Motion Imitation
02:15 Humanoid Motion Imitation
02:29 Humanoid (Parkour)
02:45 Humanoid (Datasets)
03:02 Performance Comparison
03:41 Robot Motion Imitation
03:54 Non-motion-imitation tasks
04:09 Quadruped Locomotion
04:24 Walker Benchmark
04:55 Ablation
![[SIGGRAPH Asia 2025] Physics-Based Motion Imitation with Adversarial Differential Discriminators](https://i.ytimg.com/vi/SZpQfXNDulo/maxresdefault.jpg)
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке:
![Мы получили 2,5 млн рублей чтобы сделать экзоскелет, и это наконец закончилось [2/2]](https://image.4k-video.ru/id-video/X3uZq2joiW8)
