T3OMVP: A Transformer-Based Time and Team Reinforcement Learning Scheme for Observation-Constrained Multi-Vehicle Pursuit in Urban Area

Abstract

Smart Internet of Vehicles (IoVs) combined with Artificial Intelligence (AI) will contribute to vehicle decision-making in the Intelligent Transportation System (ITS). Multi-vehicle pursuit (MVP) games, a multi-vehicle cooperative ability to capture mobile targets, are gradually becoming a hot research topic. Although there are some achievements in the field of MVP in the open space environment, the urban area brings complicated road structures and restricted moving spaces as challenges to the resolution of MVP games. We define an observation-constrained MVP (OMVP) problem in this paper and propose a transformer-based time and team reinforcement learning scheme (T3OMVP) to address the problem. First, a new multi-vehicle pursuit model is constructed based on Decentralized Partially Observed Markov Decision Processes (Dec-POMDPs) to instantiate this problem. Second, the QMIX is redefined to deal with the OMVP problem by leveraging the transformer-based observation sequence and combining the vehicle’s observations to reduce the influence of constrained observations. Third, a simulated urban environment is built to verify the proposed scheme. Extensive experimental results demonstrate that the proposed T3OMVP scheme achieves improvements relative to the state-of-the-art QMIX approaches by 9.66~106.25%, from simple to difficult scenarios.