Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918104101027840 |
|---|---|
| author | Lee, Giwon Jeong, Wooseong Park, Daehee Jeong, Jaewoo Yoon, Kuk-Jin |
| author_facet | Lee, Giwon Jeong, Wooseong Park, Daehee Jeong, Jaewoo Yoon, Kuk-Jin |
| contents | Motion planning is a crucial component of autonomous robot driving. While various trajectory datasets exist, effectively utilizing them for a target domain remains challenging due to differences in agent interactions and environmental characteristics. Conventional approaches, such as domain adaptation or ensemble learning, leverage multiple source datasets but suffer from domain imbalance, catastrophic forgetting, and high computational costs. To address these challenges, we propose Interaction-Merged Motion Planning (IMMP), a novel approach that leverages parameter checkpoints trained on different domains during adaptation to the target domain. IMMP follows a two-step process: pre-merging to capture agent behaviors and interactions, sufficiently extracting diverse information from the source domain, followed by merging to construct an adaptable model that efficiently transfers diverse interactions to the target domain. Our method is evaluated on various planning benchmarks and models, demonstrating superior performance compared to conventional approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04790 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning Lee, Giwon Jeong, Wooseong Park, Daehee Jeong, Jaewoo Yoon, Kuk-Jin Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Motion planning is a crucial component of autonomous robot driving. While various trajectory datasets exist, effectively utilizing them for a target domain remains challenging due to differences in agent interactions and environmental characteristics. Conventional approaches, such as domain adaptation or ensemble learning, leverage multiple source datasets but suffer from domain imbalance, catastrophic forgetting, and high computational costs. To address these challenges, we propose Interaction-Merged Motion Planning (IMMP), a novel approach that leverages parameter checkpoints trained on different domains during adaptation to the target domain. IMMP follows a two-step process: pre-merging to capture agent behaviors and interactions, sufficiently extracting diverse information from the source domain, followed by merging to construct an adaptable model that efficiently transfers diverse interactions to the target domain. Our method is evaluated on various planning benchmarks and models, demonstrating superior performance compared to conventional approaches. |
| title | Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2507.04790 |