Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2406.17795 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909231551086592 |
|---|---|
| author | Mu, Yuxuan Zou, Shihao Yin, Kangning Tian, Zheng Cheng, Li Zhang, Weinan Wang, Jun |
| author_facet | Mu, Yuxuan Zou, Shihao Yin, Kangning Tian, Zheng Cheng, Li Zhang, Weinan Wang, Jun |
| contents | In computer animation, driving a simulated character with lifelike motion is challenging. Current generative models, though able to generalize to diverse motions, often pose challenges to the responsiveness of end-user control. To address these issues, we introduce RACon: Retrieval-Augmented Simulated Character Locomotion Control. Our end-to-end hierarchical reinforcement learning method utilizes a retriever and a motion controller. The retriever searches motion experts from a user-specified database in a task-oriented fashion, which boosts the responsiveness to the user's control. The selected motion experts and the manipulation signal are then transferred to the controller to drive the simulated character. In addition, a retrieval-augmented discriminator is designed to stabilize the training process. Our method surpasses existing techniques in both quality and quantity in locomotion control, as demonstrated in our empirical study. Moreover, by switching extensive databases for retrieval, it can adapt to distinctive motion types at run time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_17795 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RACon: Retrieval-Augmented Simulated Character Locomotion Control Mu, Yuxuan Zou, Shihao Yin, Kangning Tian, Zheng Cheng, Li Zhang, Weinan Wang, Jun Computer Vision and Pattern Recognition Graphics In computer animation, driving a simulated character with lifelike motion is challenging. Current generative models, though able to generalize to diverse motions, often pose challenges to the responsiveness of end-user control. To address these issues, we introduce RACon: Retrieval-Augmented Simulated Character Locomotion Control. Our end-to-end hierarchical reinforcement learning method utilizes a retriever and a motion controller. The retriever searches motion experts from a user-specified database in a task-oriented fashion, which boosts the responsiveness to the user's control. The selected motion experts and the manipulation signal are then transferred to the controller to drive the simulated character. In addition, a retrieval-augmented discriminator is designed to stabilize the training process. Our method surpasses existing techniques in both quality and quantity in locomotion control, as demonstrated in our empirical study. Moreover, by switching extensive databases for retrieval, it can adapt to distinctive motion types at run time. |
| title | RACon: Retrieval-Augmented Simulated Character Locomotion Control |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2406.17795 |