HeteroMorpheus: Universal Control Based on Morphological Heterogeneity Modeling
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929446855901184 |
|---|---|
| author | Hao, YiFan Yang, Yang Song, Junru Peng, Wei Zhou, Weien Jiang, Tingsong Yao, Wen |
| author_facet | Hao, YiFan Yang, Yang Song, Junru Peng, Wei Zhou, Weien Jiang, Tingsong Yao, Wen |
| contents | In the field of robotic control, designing individual controllers for each robot leads to high computational costs. Universal control policies, applicable across diverse robot morphologies, promise to mitigate this challenge. Predominantly, models based on Graph Neural Networks (GNN) and Transformers are employed, owing to their effectiveness in capturing relational dynamics across a robot's limbs. However, these models typically employ homogeneous graph structures that overlook the functional diversity of different limbs. To bridge this gap, we introduce HeteroMorpheus, a novel method based on heterogeneous graph Transformer. This method uniquely addresses limb heterogeneity, fostering better representation of robot dynamics of various morphologies. Through extensive experiments we demonstrate the superiority of HeteroMorpheus against state-of-the-art methods in the capability of policy generalization, including zero-shot generalization and sample-efficient transfer to unfamiliar robot morphologies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_01230 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HeteroMorpheus: Universal Control Based on Morphological Heterogeneity Modeling Hao, YiFan Yang, Yang Song, Junru Peng, Wei Zhou, Weien Jiang, Tingsong Yao, Wen Robotics Machine Learning In the field of robotic control, designing individual controllers for each robot leads to high computational costs. Universal control policies, applicable across diverse robot morphologies, promise to mitigate this challenge. Predominantly, models based on Graph Neural Networks (GNN) and Transformers are employed, owing to their effectiveness in capturing relational dynamics across a robot's limbs. However, these models typically employ homogeneous graph structures that overlook the functional diversity of different limbs. To bridge this gap, we introduce HeteroMorpheus, a novel method based on heterogeneous graph Transformer. This method uniquely addresses limb heterogeneity, fostering better representation of robot dynamics of various morphologies. Through extensive experiments we demonstrate the superiority of HeteroMorpheus against state-of-the-art methods in the capability of policy generalization, including zero-shot generalization and sample-efficient transfer to unfamiliar robot morphologies. |
| title | HeteroMorpheus: Universal Control Based on Morphological Heterogeneity Modeling |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2408.01230 |