Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces

Jiayuan Du, Yuebing Song, Yiming Zhao, Xianghui Pan, Jiawei Lian, Yuchu Lu, Liuyi Wang, Chengju Liu, Qijun Chen

Abstract

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.

Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces

Abstract

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.
Paper Structure (20 sections, 9 equations, 4 figures, 6 tables)

This paper contains 20 sections, 9 equations, 4 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. End-to-End Autonomous Driving in CARLA
  4. Lifelong Learning
  5. Method
  6. Multi-modal Perception Backbone
  7. Dynamic Dual Knowledge Spaces
  8. Causal Feature Enhancement Module
  9. Evolutionary Trajectory Decoder
  10. Loss Function
  11. Experiments
  12. Dataset and Metrics
  13. Implementation Details
  14. Main Results
  15. Ablation Study
  16. ...and 5 more sections

Figures (4)

  • Figure 1: Driving score, success rate and multi-ability success rate during the lifelong learning process. Our method not only demonstrates superior overall driving performance but also substantially mitigates catastrophic forgetting.
  • Figure 2: Overview architecture of our proposed method.
  • Figure 3: Lifelong performance on CARLA benchmark DEV10 jia2025drivetransformer.
  • Figure 4: Clustering results of dynamic knowledge spaces during the learning process.