EmbodiedCoder: Parameterized Embodied Mobile Manipulation via Modern Coding Model
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909846765305856 |
|---|---|
| author | Lin, Zefu Cui, Rongxu Hanning, Chen Wang, Xiangyu Xu, Junjia Jin, Xiaojuan Wenbo, Chen Zhou, Hui Fan, Lue Li, Wenling Zhang, Zhaoxiang |
| author_facet | Lin, Zefu Cui, Rongxu Hanning, Chen Wang, Xiangyu Xu, Junjia Jin, Xiaojuan Wenbo, Chen Zhou, Hui Fan, Lue Li, Wenling Zhang, Zhaoxiang |
| contents | Recent advances in control robot methods, from end-to-end vision-language-action frameworks to modular systems with predefined primitives, have advanced robots' ability to follow natural language instructions. Nonetheless, many approaches still struggle to scale to diverse environments, as they often rely on large annotated datasets and offer limited interpretability.In this work, we introduce EmbodiedCoder, a training-free framework for open-world mobile robot manipulation that leverages coding models to directly generate executable robot trajectories. By grounding high-level instructions in code, EmbodiedCoder enables flexible object geometry parameterization and manipulation trajectory synthesis without additional data collection or fine-tuning.This coding-based paradigm provides a transparent and generalizable way to connect perception with manipulation. Experiments on real mobile robots show that EmbodiedCoder achieves robust performance across diverse long-term tasks and generalizes effectively to novel objects and environments.Our results demonstrate an interpretable approach for bridging high-level reasoning and low-level control, moving beyond fixed primitives toward versatile robot intelligence. See the project page at: https://embodiedcoder.github.io/EmbodiedCoder/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06207 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EmbodiedCoder: Parameterized Embodied Mobile Manipulation via Modern Coding Model Lin, Zefu Cui, Rongxu Hanning, Chen Wang, Xiangyu Xu, Junjia Jin, Xiaojuan Wenbo, Chen Zhou, Hui Fan, Lue Li, Wenling Zhang, Zhaoxiang Robotics Recent advances in control robot methods, from end-to-end vision-language-action frameworks to modular systems with predefined primitives, have advanced robots' ability to follow natural language instructions. Nonetheless, many approaches still struggle to scale to diverse environments, as they often rely on large annotated datasets and offer limited interpretability.In this work, we introduce EmbodiedCoder, a training-free framework for open-world mobile robot manipulation that leverages coding models to directly generate executable robot trajectories. By grounding high-level instructions in code, EmbodiedCoder enables flexible object geometry parameterization and manipulation trajectory synthesis without additional data collection or fine-tuning.This coding-based paradigm provides a transparent and generalizable way to connect perception with manipulation. Experiments on real mobile robots show that EmbodiedCoder achieves robust performance across diverse long-term tasks and generalizes effectively to novel objects and environments.Our results demonstrate an interpretable approach for bridging high-level reasoning and low-level control, moving beyond fixed primitives toward versatile robot intelligence. See the project page at: https://embodiedcoder.github.io/EmbodiedCoder/ |
| title | EmbodiedCoder: Parameterized Embodied Mobile Manipulation via Modern Coding Model |
| topic | Robotics |
| url | https://arxiv.org/abs/2510.06207 |