计算机工程与应用2024，Vol.60Issue(15)：91-100,10.DOI:10.3778/j.issn.1002-8331.2304-0223
面向复杂交通场景的自动驾驶运动规划模型
Motion Planning Model for Autonomous Driving in Complex Traffic Scenarios
摘要
Abstract
To address the problems that existing autonomous driving motion planning methods fail to effectively utilize the long-term continuous time features and the problem of low success rate in complex traffic scenarios,a Transformer-based autonomous driving motion planning model for complex traffic scenes is proposed.The method uses GPT-2 as the base model,and through temporal modeling of offline reinforcement learning,it can effectively characterize the dependen-cies of the state,action,and reward data of vehicles in the offline reinforcement learning model over a long period of time,allowing the model to effectively learn more from historical planning data and improve the accuracy and safety in complex traffic scenarios.The experiments are simulated and tested in the MetaDrive simulator,and the results show that the model has achieved a success rate of up to 93%in complex traffic scenarios such as merging into main roads and entering traffic circles,which are 20,19,and 13 percentage points higher than the success rates of the existing state-of-the-art method including behavior cloning,batch-constrained deep Q-learning(BCQ),and twin delayed deep deterministic policy gradient with behavioral cloning(TD3+BC),respectively.This indicates that the proposed method is more effec-tive to learn driving strategies from low quality datasets and with better generalization performance and robustness com-pared with other comparative methods.关键词
Transformer/离线强化学习/复杂交通场景/自动驾驶/运动规划Key words
Transformer/offline reinforcement learning/complex traffic scenarios/autonomous driving/motion planning分类
信息技术与安全科学引用本文复制引用
任佳佳,柳寅奎,胡学敏,向宸,罗显志..面向复杂交通场景的自动驾驶运动规划模型[J].计算机工程与应用,2024,60(15):91-100,10.基金项目
国家自然科学基金面上项目(62273135) （62273135）
湖北省自然科学基金(2021CFB460) （2021CFB460）
湖北省大学生创新创业训练计划基金(S202210512017,S202210512030,S202110512065). （S202210512017,S202210512030,S202110512065）
