Uncertainty-Driven Data Aggregation for Imitation Learning in Autonomous Vehicles

Imitation learning has shown promise for autonomous driving, but suffers from covariate shift, where the policy performs poorly in unseen environments. DAgger is a popular approach that addresses this by leveraging expert demonstrations. However, DAgger’s frequent visits to sub-optimal states can lead to several challenges. This paper proposes a novel DAgger framework that integrates Bayesian uncertainty estimation via mean field variational inference (MFVI) to address this issue. MFVI provides better-calibrated uncertainty estimates compared to prior methods. During training, the framework identifies both uncertain and critical states, querying the expert only for these states. This targeted data collection reduces the burden on the expert and improves data efficiency. Evaluations on the CARLA simulator demonstrate that our approach outperforms existing methods, highlighting the effectiveness of Bayesian uncertainty estimation and targeted data aggregation for imitation learning in autonomous driving.