Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.04050 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913572867538944 |
|---|---|
| author | Yang, Bochen Deng, Kaizhong Peters, Christopher J Mylonas, George Elson, Daniel S. |
| author_facet | Yang, Bochen Deng, Kaizhong Peters, Christopher J Mylonas, George Elson, Daniel S. |
| contents | Optical sensing technologies are emerging technologies used in cancer surgeries to ensure the complete removal of cancerous tissue. While point-wise assessment has many potential applications, incorporating automated large area scanning would enable holistic tissue sampling. However, such scanning tasks are challenging due to their long-horizon dependency and the requirement for fine-grained motion. To address these issues, we introduce Memorized Action Chunking with Transformers (MACT), an intuitive yet efficient imitation learning method for tissue surface scanning tasks. It utilizes a sequence of past images as historical information to predict near-future action sequences. In addition, hybrid temporal-spatial positional embeddings were employed to facilitate learning. In various simulation settings, MACT demonstrated significant improvements in contour scanning and area scanning over the baseline model. In real-world testing, with only 50 demonstration trajectories, MACT surpassed the baseline model by achieving a 60-80% success rate on all scanning tasks. Our findings suggest that MACT is a promising model for adaptive scanning in surgical settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_04050 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Memorized action chunking with Transformers: Imitation learning for vision-based tissue surface scanning Yang, Bochen Deng, Kaizhong Peters, Christopher J Mylonas, George Elson, Daniel S. Robotics Optical sensing technologies are emerging technologies used in cancer surgeries to ensure the complete removal of cancerous tissue. While point-wise assessment has many potential applications, incorporating automated large area scanning would enable holistic tissue sampling. However, such scanning tasks are challenging due to their long-horizon dependency and the requirement for fine-grained motion. To address these issues, we introduce Memorized Action Chunking with Transformers (MACT), an intuitive yet efficient imitation learning method for tissue surface scanning tasks. It utilizes a sequence of past images as historical information to predict near-future action sequences. In addition, hybrid temporal-spatial positional embeddings were employed to facilitate learning. In various simulation settings, MACT demonstrated significant improvements in contour scanning and area scanning over the baseline model. In real-world testing, with only 50 demonstration trajectories, MACT surpassed the baseline model by achieving a 60-80% success rate on all scanning tasks. Our findings suggest that MACT is a promising model for adaptive scanning in surgical settings. |
| title | Memorized action chunking with Transformers: Imitation learning for vision-based tissue surface scanning |
| topic | Robotics |
| url | https://arxiv.org/abs/2411.04050 |