Computer Engineering and Applications ›› 2024, Vol. 60 ›› Issue (14): 114-122.DOI: 10.3778/j.issn.1002-8331.2304-0208

• Pattern Recognition and Artificial Intelligence • Previous Articles     Next Articles

Motion Planning for Autonomous Driving in Dense Traffic Scenarios

XIAO Yuwei, YAO Xizi, HU Xuemin, LUO Xianzhi   

  1. School of Computer Science and Information Engineering, Hubei University, Wuhan 430062, China
  • Online:2024-07-15 Published:2024-07-15

面向高密度交通场景的自动驾驶运动规划

肖雨微,姚溪子,胡学敏,罗显志   

  1. 湖北大学 计算机与信息工程学院,武汉 430062

Abstract: Aiming at the problem that the existing motion planning methods for autonomous driving ignore the interaction of surrounding vehicles when extracting state information and the bad planning effect in dense traffic scenarios, a motion planning model combined with graph neural network and deep reinforcement learning is proposed. Firstly, based on the graph neural network, an interactive feature representation method of self-driving vehicles is proposed to extract spatial interaction features of multiple traffic participants. In this case, a learning strategy for motion planning is designed based on twin delayed deep deterministic policy gradient (TD3), and the next action is predicted from the interactive features so as to realize motion planning. The proposed method is compared with the current motion planning model LSTM+TD3,TD3 and deep deterministic policy gradient (DDPG) for autonomous driving, in dense traffic scenarios, the experimental results of training and testing in the PGDrive driving simulator increased by 36%, 43%, 23% and 13, 19, 53?percentage points compared with the comparison method, which means the proposed method can effectively solve the problem of interactive information perception of surrounding vehicles for better motion planning of autonomous driving.

Key words: autonomous driving, motion planning, interactive feature, graph neural network, reinforcement learning

摘要: 针对现有自动驾驶运动规划方法在提取状态信息时忽略了周边车辆交互、在高密度交通场景下规划效果不理想的问题,提出了一种联合图神经网络和深度强化学习的运动规划模型。基于图神经网络提出了一种自动驾驶车辆的交互式特征提取方法,再基于双延迟深度确定性策略梯度(twin delayed deep deterministic policy gradient,TD3)算法从交互式特征中预测车辆的动作,从而实现运动规划。将所提模型与目前自动驾驶运动规划模型LSTM+TD3、TD3及深度确定性策略梯度(deep deterministic policy gradient,DDPG)模型进行对比,在PGDrive驾驶模拟器中进行训练和测试的实验结果表明,在高密度交通场景中,所提方法的训练奖励值和测试成功率相比于对比方法提升了约36%、43%、23%及13、19、53个百分点。表明所提方法能有效解决自动驾驶周边车辆的交互式信息感知问题,更好地实现自动驾驶运动规划。

关键词: 自动驾驶, 运动规划, 交互式特征, 图神经网络, 强化学习