部分可观测马尔可夫决策过程
计算机科学
马尔可夫决策过程
强化学习
智能决策支持系统
决策支持系统
智能交通系统
过程(计算)
钥匙(锁)
避碰
软件
人工智能
作者
Jiayi Liu,Kai Lin,Giancarlo Fortino
标识
DOI:10.1109/codit55151.2022.9803919
摘要
Intelligent driving technology plays a key role in reducing road traffic accidents and ensuring driving, where the vehicle behavior decision making capability largely determines the driving performance of intelligent vehicles. At this point, more research is focused on enhancing vehicle environment identification and vehicle control capabilities, with decision-making systems receiving less attention. In order to improve the accuracy of intelligent vehicle behavior decision making and ensure the active safety of path planning, this paper firstly establishes an edge intelligence based software-defined Internet of Vehicles (ESIOV) architecture. Then, a POMDP-based intelligent vehicle behavior decision model is designed using the time-series iterative property of partially observable Markov decision process (POMDP). Finally, a reinforcement learning vehicle behaviour decision (ERVBD) algorithm based on edge intelligence is proposed to ensure the accuracy of intelligent vehicle behavior decision results and improve the decision speed. The simulation results show that ERVBD can successfully implement vehicle behavioural decision making, enabling intelligent vehicles to anticipate collision risks and adopt reasonable avoidance strategies in real time.
科研通智能强力驱动
Strongly Powered by AbleSci AI