It is still a challenging topic to make reactive driving behaviors in complex urban environments as road users' intentions are unknown. Model-based reinforcement learning (MBRL) offers great potential to learn a reactive policy by constructing a world model that can provide informative states and imagination training. However, a critical limitation in relevant research lies in the scene-level reconstruction representation learning, which may overlook key interactive vehicles and hardly model the interactive features among vehicles and their long-term intentions. Therefore, this paper presents a novel MBRL method with a predictive individual world model (PIWM) for autonomous driving. PIWM describes the driving environment from an individual-level perspective and captures vehicles' interactive relations and their intentions via trajectory prediction task. Meanwhile, a behavior policy is learned jointly with PIWM. It is trained in PIWM's imagination and effectively navigates in the urban driving scenes leveraging intention-aware latent states. The proposed method is trained and evaluated on simulation environments built upon real-world challenging interactive scenarios. Compared with popular model-free and state-of-the-art model-based reinforcement learning methods, experimental results show that the proposed method achieves the best performance in terms of safety and efficiency.
Dream to Drive With Predictive Individual World Model
IEEE Transactions on Intelligent Vehicles ; 9 , 12 ; 8224-8238
2024-12-01
5632416 byte
Article (Journal)
Electronic Resource
English
Automotive engineering | 2010
|Newsline - Swiss World dream ends
Online Contents | 1999
1001 dream cars you must drive before you die
SLUB | 2012
|Australian Formula SAE teams drive the dream in Detroit
British Library Online Contents | 2004