Design and Implementation of Deep Neural Network-Based Control for Automatic Parking Maneuver Process
Design and Implementation of Deep Neural Network-Based Control for Automatic Parking Maneuver Process
复制标题
基于深度神经网络的自动停车机动过程控制设计与实现
DOI：
10.1109/tnnls.2020.3042120
复制
发表时间：
2022-04-01
影响因子：
10.4
通讯作者：
Chen, C. L. Philip
中科院分区：
文献类型：
--
作者：
Chai, Runqi;Tsourdos, Antonios;Chen, C. L. Philip
本文重点介绍了基于深度神经网络（DNN）的控制方案的设计、测试和验证，该控制方案能够预测自主地面车辆（AGV）在停车机动过程中的最佳运动命令。所提出的设计采用多层结构。在第一层中，一个脱敏轨迹优化方法迭代执行，以建立一组时间最优的停车轨迹与噪声扰动的初始配置的考虑。随后，通过使用预先规划的最优停车轨迹数据集，训练若干DNN，以便学习第二层中的系统状态控制动作之间的函数关系。为了进一步提高DNN的性能，设计并应用了一种简单而有效的数据聚合方法。然后，这些训练的DNN被用作运动控制器，以真实的时间生成反馈动作。数值结果表明，该控制方案的有效性和实时适用性的规划和引导的AGV停车机动。实验结果也证明了算法的性能在现实世界中的实现。
This article focuses on the design, test, and validation of a deep neural network (DNN)-based control scheme capable of predicting optimal motion commands for autonomous ground vehicles (AGVs) during the parking maneuver process. The proposed design utilizes a multilayer structure. In the first layer, a desensitized trajectory optimization method is iteratively performed to establish a set of time-optimal parking trajectories with the consideration of noise-perturbed initial configurations. Subsequently, by using the preplanned optimal parking trajectory data set, several DNNs are trained in order to learn the functional relationship between the system state-control actions in the second layer. To obtain further improvements regarding the DNN performances, a simple yet effective data aggregation approach is designed and applied. These trained DNNs are then utilized as the motion controllers to generate feedback actions in real time. Numerical results were executed to demonstrate the effectiveness and the real-time applicability of using the proposed control scheme to plan and steer the AGV parking maneuver. Experimental results were also provided to justify the algorithm performance in real-world implementations.