Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Du, Jiayuan, Song, Yuebing, Zhao, Yiming, Pan, Xianghui, Lian, Jiawei, Lu, Yuchu, Wang, Liuyi, Liu, Chengju, Chen, Qijun
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910083788570624
author Du, Jiayuan
Song, Yuebing
Zhao, Yiming
Pan, Xianghui
Lian, Jiawei
Lu, Yuchu
Wang, Liuyi
Liu, Chengju
Chen, Qijun
author_facet Du, Jiayuan
Song, Yuebing
Zhao, Yiming
Pan, Xianghui
Lian, Jiawei
Lu, Yuchu
Wang, Liuyi
Liu, Chengju
Chen, Qijun
contents End-to-End autonomous driving (E2E-AD) systems face challenges in lifelong learning, including catastrophic forgetting, difficulty in knowledge transfer across diverse scenarios, and spurious correlations between unobservable confounders and true driving intents. To address these issues, we propose DeLL, a Deconfounded Lifelong Learning framework that integrates a Dirichlet process mixture model (DPMM) with the front-door adjustment mechanism from causal inference. The DPMM is employed to construct two dynamic knowledge spaces: a trajectory knowledge space for clustering explicit driving behaviors and an implicit feature knowledge space for discovering latent driving abilities. Leveraging the non-parametric Bayesian nature of DPMM, our framework enables adaptive expansion and incremental updating of knowledge without predefining the number of clusters, thereby mitigating catastrophic forgetting. Meanwhile, the front-door adjustment mechanism utilizes the DPMM-derived knowledge as valid mediators to deconfound spurious correlations, such as those induced by sensor noise or environmental changes, and enhances the causal expressiveness of the learned representations. Additionally, we introduce an evolutionary trajectory decoder that enables non-autoregressive planning. To evaluate the lifelong learning performance of E2E-AD, we propose new evaluation protocols and metrics based on Bench2Drive. Extensive evaluations in the closed-loop CARLA simulator demonstrate that our framework significantly improves adaptability to new driving scenarios and overall driving performance, while effectively retaining previous acquired knowledge.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14354
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces
Du, Jiayuan
Song, Yuebing
Zhao, Yiming
Pan, Xianghui
Lian, Jiawei
Lu, Yuchu
Wang, Liuyi
Liu, Chengju
Chen, Qijun
Machine Learning
Artificial Intelligence
Robotics
End-to-End autonomous driving (E2E-AD) systems face challenges in lifelong learning, including catastrophic forgetting, difficulty in knowledge transfer across diverse scenarios, and spurious correlations between unobservable confounders and true driving intents. To address these issues, we propose DeLL, a Deconfounded Lifelong Learning framework that integrates a Dirichlet process mixture model (DPMM) with the front-door adjustment mechanism from causal inference. The DPMM is employed to construct two dynamic knowledge spaces: a trajectory knowledge space for clustering explicit driving behaviors and an implicit feature knowledge space for discovering latent driving abilities. Leveraging the non-parametric Bayesian nature of DPMM, our framework enables adaptive expansion and incremental updating of knowledge without predefining the number of clusters, thereby mitigating catastrophic forgetting. Meanwhile, the front-door adjustment mechanism utilizes the DPMM-derived knowledge as valid mediators to deconfound spurious correlations, such as those induced by sensor noise or environmental changes, and enhances the causal expressiveness of the learned representations. Additionally, we introduce an evolutionary trajectory decoder that enables non-autoregressive planning. To evaluate the lifelong learning performance of E2E-AD, we propose new evaluation protocols and metrics based on Bench2Drive. Extensive evaluations in the closed-loop CARLA simulator demonstrate that our framework significantly improves adaptability to new driving scenarios and overall driving performance, while effectively retaining previous acquired knowledge.
title Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces
topic Machine Learning
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2603.14354