Model-free Deep Reinforcement Learning for Urban Autonomous Driving

Urban autonomous driving decision making is challenging due to complex road geometry and multi-agent interactions. Current decision making methods are mostly manually designing the driving policy, which might result in suboptimal solutions and is expensive to develop, generalize and maintain at scal...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2019 IEEE Intelligent Transportation Systems Conference (ITSC) S. 2765 - 2771
Hauptverfasser: Chen, Jianyu, Yuan, Bodi, Tomizuka, Masayoshi
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.10.2019
Schlagworte:
Autonomous vehicles
Decision making
Learning (artificial intelligence)
Machine learning
Roads
Routing
Task analysis
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Urban autonomous driving decision making is challenging due to complex road geometry and multi-agent interactions. Current decision making methods are mostly manually designing the driving policy, which might result in suboptimal solutions and is expensive to develop, generalize and maintain at scale. On the other hand, with reinforcement learning (RL), a policy can be learned and improved automatically without any manual designs. However, current RL methods generally do not work well on complex urban scenarios. In this paper, we propose a framework to enable model-free deep reinforcement learning in challenging urban autonomous driving scenarios. We design a specific input representation and use visual encoding to capture the low-dimensional latent states. Several state-of-the-art model-free deep RL algorithms are implemented into our framework, with several tricks to improve their performance. We evaluate our method in a challenging roundabout task with dense surrounding vehicles in a high-definition driving simulator. The result shows that our method can solve the task well and is significantly better than the baseline.
DOI:10.1109/ITSC.2019.8917306