Multi-Agent Reinforcement Learning for Autonomous On Demand Vehicles

• Published in: IEEE Intelligent Vehicles Symposium pp. 1461 - 1468
• Main Authors: Boyali, Ali, Hashimoto, Naohisa, John, Vijay, Acarman, Tankut
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2019
• Subjects: Decision making; Electric vehicles; Elevators; Energy consumption; Intelligent vehicles; Neural networks; Q-learning; Random variables; Stochastic processes; Time factors
• ISSN: 2642-7214
• DOI: 10.1109/IVS.2019.8813876

In this study, we elaborate the procedure of designing a supervisory controller for the Autonomous Transit on Demand Vehicle (ATODV) system. Reinforcement learning is implemented to reduce the mean waiting time of the passengers, and a cost function is introduced to penalize the energy consumption of the electric vehicles. A stochastic simulation environment for an ATODV pilot project is coded in the Python environment to train the autonomous cart decision process as agents with artificial intelligence. Passenger group behavior, get-on and get-off times, destinations are modeled as random variables. A single Deep Q-Learning Network is trained subject to multi-agent settings. The ATODV system's independent decision making for the carts to reduce the passenger's waiting time while constraining the energy consumption and empty vehicle motion is evaluated.