DABI: Evaluation of Data Augmentation Methods Using Downsampling in Bilateral Control-Based Imitation Learning with Images
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910635236786176 |
|---|---|
| author | Kobayashi, Masato Buamanee, Thanpimon Uranishi, Yuki |
| author_facet | Kobayashi, Masato Buamanee, Thanpimon Uranishi, Yuki |
| contents | Autonomous robot manipulation is a complex and continuously evolving robotics field. This paper focuses on data augmentation methods in imitation learning. Imitation learning consists of three stages: data collection from experts, learning model, and execution. However, collecting expert data requires manual effort and is time-consuming. Additionally, as sensors have different data acquisition intervals, preprocessing such as downsampling to match the lowest frequency is necessary. Downsampling enables data augmentation and also contributes to the stabilization of robot operations. In light of this background, this paper proposes the Data Augmentation Method for Bilateral Control-Based Imitation Learning with Images, called "DABI". DABI collects robot joint angles, velocities, and torques at 1000 Hz, and uses images from gripper and environmental cameras captured at 100 Hz as the basis for data augmentation. This enables a tenfold increase in data. In this paper, we collected just 5 expert demonstration datasets. We trained the bilateral control Bi-ACT model with the unaltered dataset and two augmentation methods for comparative experiments and conducted real-world experiments. The results confirmed a significant improvement in success rates, thereby proving the effectiveness of DABI. For additional material, please check https://mertcookimg.github.io/dabi |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_04370 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DABI: Evaluation of Data Augmentation Methods Using Downsampling in Bilateral Control-Based Imitation Learning with Images Kobayashi, Masato Buamanee, Thanpimon Uranishi, Yuki Robotics Autonomous robot manipulation is a complex and continuously evolving robotics field. This paper focuses on data augmentation methods in imitation learning. Imitation learning consists of three stages: data collection from experts, learning model, and execution. However, collecting expert data requires manual effort and is time-consuming. Additionally, as sensors have different data acquisition intervals, preprocessing such as downsampling to match the lowest frequency is necessary. Downsampling enables data augmentation and also contributes to the stabilization of robot operations. In light of this background, this paper proposes the Data Augmentation Method for Bilateral Control-Based Imitation Learning with Images, called "DABI". DABI collects robot joint angles, velocities, and torques at 1000 Hz, and uses images from gripper and environmental cameras captured at 100 Hz as the basis for data augmentation. This enables a tenfold increase in data. In this paper, we collected just 5 expert demonstration datasets. We trained the bilateral control Bi-ACT model with the unaltered dataset and two augmentation methods for comparative experiments and conducted real-world experiments. The results confirmed a significant improvement in success rates, thereby proving the effectiveness of DABI. For additional material, please check https://mertcookimg.github.io/dabi |
| title | DABI: Evaluation of Data Augmentation Methods Using Downsampling in Bilateral Control-Based Imitation Learning with Images |
| topic | Robotics |
| url | https://arxiv.org/abs/2410.04370 |