Compact Task-Aligned Imitation Learning for Laboratory Automation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914361509937152 |
|---|---|
| author | Suzuki, Kanata Nakamurama, Hanon Miyamoto, Kana Ogata, Tetsuya |
| author_facet | Suzuki, Kanata Nakamurama, Hanon Miyamoto, Kana Ogata, Tetsuya |
| contents | Robotic laboratory automation has traditionally relied on carefully engineered motion pipelines and task-specific hardware interfaces, resulting in high design cost and limited flexibility. While recent imitation learning techniques can generate general robot behaviors, their large model sizes often require high-performance computational resources, limiting applicability in practical laboratory environments. In this study, we propose a compact imitation learning framework for laboratory automation using small foundation models. The proposed method, TVF-DiT, aligns a self-supervised vision foundation model with a vision-language model through a compact adapter, and integrates them with a Diffusion Transformer-based action expert. The entire model consists of fewer than 500M parameters, enabling inference on low-VRAM GPUs. Experiments on three real-world laboratory tasks - test tube cleaning, test tube arrangement, and powder transfer - demonstrate an average success rate of 86.6%, significantly outperforming alternative lightweight baselines. Furthermore, detailed task prompts improve vision-language alignment and task performance. These results indicate that small foundation models, when properly aligned and integrated with diffusion-based policy learning, can effectively support practical laboratory automation with limited computational resources. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01110 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Compact Task-Aligned Imitation Learning for Laboratory Automation Suzuki, Kanata Nakamurama, Hanon Miyamoto, Kana Ogata, Tetsuya Robotics Robotic laboratory automation has traditionally relied on carefully engineered motion pipelines and task-specific hardware interfaces, resulting in high design cost and limited flexibility. While recent imitation learning techniques can generate general robot behaviors, their large model sizes often require high-performance computational resources, limiting applicability in practical laboratory environments. In this study, we propose a compact imitation learning framework for laboratory automation using small foundation models. The proposed method, TVF-DiT, aligns a self-supervised vision foundation model with a vision-language model through a compact adapter, and integrates them with a Diffusion Transformer-based action expert. The entire model consists of fewer than 500M parameters, enabling inference on low-VRAM GPUs. Experiments on three real-world laboratory tasks - test tube cleaning, test tube arrangement, and powder transfer - demonstrate an average success rate of 86.6%, significantly outperforming alternative lightweight baselines. Furthermore, detailed task prompts improve vision-language alignment and task performance. These results indicate that small foundation models, when properly aligned and integrated with diffusion-based policy learning, can effectively support practical laboratory automation with limited computational resources. |
| title | Compact Task-Aligned Imitation Learning for Laboratory Automation |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.01110 |