MoSE: Skill-by-Skill Mixture-of-Experts Learning for Embodied Autonomous Machines
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912535279566848 |
|---|---|
| author | Xu, Lu Yu, Jiaqian Peng, Xiongfeng Chen, Yiwei Li, Weiming Yoo, Jaewook Chunag, Sunghyun Lee, Dongwook Ji, Daehyun Zhang, Chao |
| author_facet | Xu, Lu Yu, Jiaqian Peng, Xiongfeng Chen, Yiwei Li, Weiming Yoo, Jaewook Chunag, Sunghyun Lee, Dongwook Ji, Daehyun Zhang, Chao |
| contents | To meet the growing demand for smarter, faster, and more efficient embodied AI solutions, we introduce a novel Mixture-of-Expert (MoE) method that significantly boosts reasoning and learning efficiency for embodied autonomous systems. General MoE models demand extensive training data and complex optimization, which limits their applicability in embodied AI such as autonomous driving (AD) and robotic manipulation. In this work, we propose a skill-oriented MoE called MoSE, which mimics the human learning and reasoning process skill-by-skill, step-by-step. We introduce a skill-oriented routing mechanism that begins with defining and annotating specific skills, enabling experts to identify the necessary competencies for various scenarios and reasoning tasks, thereby facilitating skill-by-skill learning. To better align with multi-step planning in human reasoning and in end-to-end driving models, we build a hierarchical skill dataset and pretrain the router to encourage the model to think step-by-step. Unlike other multi-round dialogues, MoSE integrates valuable auxiliary tasks (e.g. perception-prediction-planning for AD, and high-level and low-level planning for robots) in one single forward process without introducing any extra computational cost. With less than 3B sparsely activated parameters, our model effectively grows more diverse expertise and outperforms models on both AD corner-case reasoning tasks and robot reasoning tasks with less than 40% of the parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07818 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MoSE: Skill-by-Skill Mixture-of-Experts Learning for Embodied Autonomous Machines Xu, Lu Yu, Jiaqian Peng, Xiongfeng Chen, Yiwei Li, Weiming Yoo, Jaewook Chunag, Sunghyun Lee, Dongwook Ji, Daehyun Zhang, Chao Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning To meet the growing demand for smarter, faster, and more efficient embodied AI solutions, we introduce a novel Mixture-of-Expert (MoE) method that significantly boosts reasoning and learning efficiency for embodied autonomous systems. General MoE models demand extensive training data and complex optimization, which limits their applicability in embodied AI such as autonomous driving (AD) and robotic manipulation. In this work, we propose a skill-oriented MoE called MoSE, which mimics the human learning and reasoning process skill-by-skill, step-by-step. We introduce a skill-oriented routing mechanism that begins with defining and annotating specific skills, enabling experts to identify the necessary competencies for various scenarios and reasoning tasks, thereby facilitating skill-by-skill learning. To better align with multi-step planning in human reasoning and in end-to-end driving models, we build a hierarchical skill dataset and pretrain the router to encourage the model to think step-by-step. Unlike other multi-round dialogues, MoSE integrates valuable auxiliary tasks (e.g. perception-prediction-planning for AD, and high-level and low-level planning for robots) in one single forward process without introducing any extra computational cost. With less than 3B sparsely activated parameters, our model effectively grows more diverse expertise and outperforms models on both AD corner-case reasoning tasks and robot reasoning tasks with less than 40% of the parameters. |
| title | MoSE: Skill-by-Skill Mixture-of-Experts Learning for Embodied Autonomous Machines |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2507.07818 |