Imitation Learning Inputting Image Feature to Each Layer of Neural Network
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914645734850560 |
|---|---|
| author | Yamane, Koki Sakaino, Sho Tsuji, Toshiaki |
| author_facet | Yamane, Koki Sakaino, Sho Tsuji, Toshiaki |
| contents | Imitation learning enables robots to learn and replicate human behavior from training data. Recent advances in machine learning enable end-to-end learning approaches that directly process high-dimensional observation data, such as images. However, these approaches face a critical challenge when processing data from multiple modalities, inadvertently ignoring data with a lower correlation to the desired output, especially when using short sampling periods. This paper presents a useful method to address this challenge, which amplifies the influence of data with a relatively low correlation to the output by inputting the data into each neural network layer. The proposed approach effectively incorporates diverse data sources into the learning process. Through experiments using a simple pick-and-place operation with raw images and joint information as input, significant improvements in success rates are demonstrated even when dealing with data from short sampling periods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_09691 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Imitation Learning Inputting Image Feature to Each Layer of Neural Network Yamane, Koki Sakaino, Sho Tsuji, Toshiaki Robotics Artificial Intelligence Machine Learning Imitation learning enables robots to learn and replicate human behavior from training data. Recent advances in machine learning enable end-to-end learning approaches that directly process high-dimensional observation data, such as images. However, these approaches face a critical challenge when processing data from multiple modalities, inadvertently ignoring data with a lower correlation to the desired output, especially when using short sampling periods. This paper presents a useful method to address this challenge, which amplifies the influence of data with a relatively low correlation to the output by inputting the data into each neural network layer. The proposed approach effectively incorporates diverse data sources into the learning process. Through experiments using a simple pick-and-place operation with raw images and joint information as input, significant improvements in success rates are demonstrated even when dealing with data from short sampling periods. |
| title | Imitation Learning Inputting Image Feature to Each Layer of Neural Network |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2401.09691 |