CAPS: Context-Aware Priority Sampling for Enhanced Imitation Learning in Autonomous Driving
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908869262835712 |
|---|---|
| author | Mirkhani, Hamidreza Khamidehi, Behzad Ahmadi, Ehsan Elmahgiubi, Mohammed Zhang, Weize Arasteh, Fazel Rajguru, Umar Rezaee, Kasra Bai, Dongfeng |
| author_facet | Mirkhani, Hamidreza Khamidehi, Behzad Ahmadi, Ehsan Elmahgiubi, Mohammed Zhang, Weize Arasteh, Fazel Rajguru, Umar Rezaee, Kasra Bai, Dongfeng |
| contents | In this paper, we introduce Context-Aware Priority Sampling (CAPS), a novel method designed to enhance data efficiency in learning-based autonomous driving systems. CAPS addresses the challenge of imbalanced datasets in imitation learning by leveraging Vector Quantized Variational Autoencoders (VQ-VAEs). In this way, we can get structured and interpretable data representations, which help to reveal meaningful patterns in the data. These patterns are used to group the data into clusters, with each sample being assigned a cluster ID. The cluster IDs are then used to re-balance the dataset, ensuring that rare yet valuable samples receive higher priority during training. We evaluate our method through closed-loop experiments in the CARLA simulator. The results on Bench2Drive scenarios demonstrate the effectiveness of CAPS in enhancing model generalization, with substantial improvements in both driving score and success rate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01650 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CAPS: Context-Aware Priority Sampling for Enhanced Imitation Learning in Autonomous Driving Mirkhani, Hamidreza Khamidehi, Behzad Ahmadi, Ehsan Elmahgiubi, Mohammed Zhang, Weize Arasteh, Fazel Rajguru, Umar Rezaee, Kasra Bai, Dongfeng Machine Learning Robotics In this paper, we introduce Context-Aware Priority Sampling (CAPS), a novel method designed to enhance data efficiency in learning-based autonomous driving systems. CAPS addresses the challenge of imbalanced datasets in imitation learning by leveraging Vector Quantized Variational Autoencoders (VQ-VAEs). In this way, we can get structured and interpretable data representations, which help to reveal meaningful patterns in the data. These patterns are used to group the data into clusters, with each sample being assigned a cluster ID. The cluster IDs are then used to re-balance the dataset, ensuring that rare yet valuable samples receive higher priority during training. We evaluate our method through closed-loop experiments in the CARLA simulator. The results on Bench2Drive scenarios demonstrate the effectiveness of CAPS in enhancing model generalization, with substantial improvements in both driving score and success rate. |
| title | CAPS: Context-Aware Priority Sampling for Enhanced Imitation Learning in Autonomous Driving |
| topic | Machine Learning Robotics |
| url | https://arxiv.org/abs/2503.01650 |