Continual Learning for Adaptable Car-Following in Dynamic Traffic Environments
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909262218788864 |
|---|---|
| author | Chen, Xianda Tiu, PakHin Han, Xu Chen, Junjie Wu, Yuanfei Zheng, Xinhu Zhu, Meixin |
| author_facet | Chen, Xianda Tiu, PakHin Han, Xu Chen, Junjie Wu, Yuanfei Zheng, Xinhu Zhu, Meixin |
| contents | The continual evolution of autonomous driving technology requires car-following models that can adapt to diverse and dynamic traffic environments. Traditional learning-based models often suffer from performance degradation when encountering unseen traffic patterns due to a lack of continual learning capabilities. This paper proposes a novel car-following model based on continual learning that addresses this limitation. Our framework incorporates Elastic Weight Consolidation (EWC) and Memory Aware Synapses (MAS) techniques to mitigate catastrophic forgetting and enable the model to learn incrementally from new traffic data streams. We evaluate the performance of the proposed model on the Waymo and Lyft datasets which encompass various traffic scenarios. The results demonstrate that the continual learning techniques significantly outperform the baseline model, achieving 0\% collision rates across all traffic conditions. This research contributes to the advancement of autonomous driving technology by fostering the development of more robust and adaptable car-following models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_14247 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Continual Learning for Adaptable Car-Following in Dynamic Traffic Environments Chen, Xianda Tiu, PakHin Han, Xu Chen, Junjie Wu, Yuanfei Zheng, Xinhu Zhu, Meixin Machine Learning Artificial Intelligence The continual evolution of autonomous driving technology requires car-following models that can adapt to diverse and dynamic traffic environments. Traditional learning-based models often suffer from performance degradation when encountering unseen traffic patterns due to a lack of continual learning capabilities. This paper proposes a novel car-following model based on continual learning that addresses this limitation. Our framework incorporates Elastic Weight Consolidation (EWC) and Memory Aware Synapses (MAS) techniques to mitigate catastrophic forgetting and enable the model to learn incrementally from new traffic data streams. We evaluate the performance of the proposed model on the Waymo and Lyft datasets which encompass various traffic scenarios. The results demonstrate that the continual learning techniques significantly outperform the baseline model, achieving 0\% collision rates across all traffic conditions. This research contributes to the advancement of autonomous driving technology by fostering the development of more robust and adaptable car-following models. |
| title | Continual Learning for Adaptable Car-Following in Dynamic Traffic Environments |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2407.14247 |