AdaBoost-Bagging deep inverse reinforcement learning for autonomous taxi cruising route and speed planning

• Published in: Transportation research. Part E, Logistics and transportation review Vol. 177; p. 103232
• Main Authors: Liu, Shan, Zhang, Ya, Wang, Zhengli, Gu, Shiyi
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.09.2023
• Subjects: Autonomous taxi; Cruising route planning; Cruising speed planning; Ensemble learning; Inverse reinforcement learning; Autonomous taxi; Ensemble learning; Cruising route planning; Cruising speed planning; Inverse reinforcement learning
• ISSN: 1366-5545; 1878-5794
• DOI: 10.1016/j.tre.2023.103232

Taxi cruising route planning has attracted considerable attention, and relevant studies can be broadly categorized into three main streams: recommending one or multiple areas, providing a detailed cruising route, and deriving the optimal routing policy. However, these studies depend on accurate pick-up/drop-off information, and seldom pay attention to cruising speed planning. In view of the rapid development of autonomous taxis, this study proposes AdaBoost-Bagging maximum entropy deep inverse reinforcement learning to learn cruising policy from experienced taxi drivers’ trajectories. Moreover, we develop a trajectory-based self-attention bidirectional LSTM model to adjust cruising speeds on different roads. Numerical experiments using real taxi trajectories in Chengdu, China demonstrate the effectiveness of our approach in learning taxi drivers’ policies and improving taxis’ operational efficiency. •Propose AdaBoost-Bagging maximum entropy inverse reinforcement learning.•Plan autonomous taxi’s cruising path on trajectories without pick-up/drop-off record.•Learn cruising speed control from experienced taxi drivers for autonomous taxis.•Numerical experiments using real taxi trajectories are conducted to verify our model.