Augmenting Safety-Critical Driving Scenarios while Preserving Similarity to Expert Trajectories
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_ | 1866914762696163328 |
|---|---|
| author | Mirkhani, Hamidreza Khamidehi, Behzad Rezaee, Kasra |
| author_facet | Mirkhani, Hamidreza Khamidehi, Behzad Rezaee, Kasra |
| contents | Trajectory augmentation serves as a means to mitigate distributional shift in imitation learning. However, imitating trajectories that inadequately represent the original expert data can result in undesirable behaviors, particularly in safety-critical scenarios. We propose a trajectory augmentation method designed to maintain similarity with expert trajectory data. To accomplish this, we first cluster trajectories to identify minority yet safety-critical groups. Then, we combine the trajectories within the same cluster through geometrical transformation to create new trajectories. These trajectories are then added to the training dataset, provided that they meet our specified safety-related criteria. Our experiments exhibit that training an imitation learning model using these augmented trajectories can significantly improve closed-loop performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_13347 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Augmenting Safety-Critical Driving Scenarios while Preserving Similarity to Expert Trajectories Mirkhani, Hamidreza Khamidehi, Behzad Rezaee, Kasra Machine Learning Artificial Intelligence Trajectory augmentation serves as a means to mitigate distributional shift in imitation learning. However, imitating trajectories that inadequately represent the original expert data can result in undesirable behaviors, particularly in safety-critical scenarios. We propose a trajectory augmentation method designed to maintain similarity with expert trajectory data. To accomplish this, we first cluster trajectories to identify minority yet safety-critical groups. Then, we combine the trajectories within the same cluster through geometrical transformation to create new trajectories. These trajectories are then added to the training dataset, provided that they meet our specified safety-related criteria. Our experiments exhibit that training an imitation learning model using these augmented trajectories can significantly improve closed-loop performance. |
| title | Augmenting Safety-Critical Driving Scenarios while Preserving Similarity to Expert Trajectories |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2404.13347 |