Discrete Contrastive Learning for Diffusion Policies in Autonomous Driving
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_ | 1866915185294311424 |
|---|---|
| author | Kujanpää, Kalle Baimukashev, Daulet Munir, Farzeen Azam, Shoaib Kucner, Tomasz Piotr Pajarinen, Joni Kyrki, Ville |
| author_facet | Kujanpää, Kalle Baimukashev, Daulet Munir, Farzeen Azam, Shoaib Kucner, Tomasz Piotr Pajarinen, Joni Kyrki, Ville |
| contents | Learning to perform accurate and rich simulations of human driving behaviors from data for autonomous vehicle testing remains challenging due to human driving styles' high diversity and variance. We address this challenge by proposing a novel approach that leverages contrastive learning to extract a dictionary of driving styles from pre-existing human driving data. We discretize these styles with quantization, and the styles are used to learn a conditional diffusion policy for simulating human drivers. Our empirical evaluation confirms that the behaviors generated by our approach are both safer and more human-like than those of the machine-learning-based baseline methods. We believe this has the potential to enable higher realism and more effective techniques for evaluating and improving the performance of autonomous vehicles. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05229 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Discrete Contrastive Learning for Diffusion Policies in Autonomous Driving Kujanpää, Kalle Baimukashev, Daulet Munir, Farzeen Azam, Shoaib Kucner, Tomasz Piotr Pajarinen, Joni Kyrki, Ville Robotics Artificial Intelligence Learning to perform accurate and rich simulations of human driving behaviors from data for autonomous vehicle testing remains challenging due to human driving styles' high diversity and variance. We address this challenge by proposing a novel approach that leverages contrastive learning to extract a dictionary of driving styles from pre-existing human driving data. We discretize these styles with quantization, and the styles are used to learn a conditional diffusion policy for simulating human drivers. Our empirical evaluation confirms that the behaviors generated by our approach are both safer and more human-like than those of the machine-learning-based baseline methods. We believe this has the potential to enable higher realism and more effective techniques for evaluating and improving the performance of autonomous vehicles. |
| title | Discrete Contrastive Learning for Diffusion Policies in Autonomous Driving |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2503.05229 |