计算机应用 ›› 2019, Vol. 39 ›› Issue (10): 2870-2875.DOI: 10.11772/j.issn.1001-9081.2019040629

• 人工智能 • 上一篇    下一篇

基于深度级联神经网络的自动驾驶运动规划模型

白丽贇, 胡学敏, 宋昇, 童秀迟, 张若晗   

  1. 湖北大学 计算机与信息工程学院, 武汉 430062
  • 收稿日期:2019-04-15 修回日期:2019-06-12 出版日期:2019-10-10 发布日期:2019-08-21
  • 通讯作者: 胡学敏
  • 作者简介:白丽贇(1995-),女,陕西汉中人,硕士研究生,主要研究方向:深度神经网络;胡学敏(1985-),男,湖南岳阳人,副教授,博士,主要研究方向:机器学习、运动规划;宋昇(1997-),男,河南郑州人,主要研究方向:运动规划;童秀迟(1996-),女,湖北随州人,硕士研究生,主要研究方向:机器学习;张若晗(1997-),女,湖北襄阳人,硕士研究生,主要研究方向:深度学习。
  • 基金资助:
    国家自然科学基金资助项目(61806076);湖北省自然科学基金资助项目(2018CFB158);湖北省大学生创新创业训练计划项目(201810512055)。

Motion planning model based on deep cascaded neural network for autonomous driving

BAI Liyun, HU Xuemin, SONG Sheng, TONG Xiuchi, ZHANG Ruohan   

  1. School of Computer Science and Information Engineering, Hubei University, Wuhan Hubei 430062, China
  • Received:2019-04-15 Revised:2019-06-12 Online:2019-10-10 Published:2019-08-21
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61806076), the Hubei Provincial Natural Science Foundation of China (2018CFB158), the Undergraduate Innovation Training Project of Hubei Province (201810512055).

摘要: 针对基于规则的运动规划算法需要预先定义规则和基于深度学习的方法没有利用时间特征的问题,提出一种基于深度级联神经网络的运动规划模型。该模型将卷积神经网络(CNN)和长短期记忆网络(LSTM)这两种经典的深度学习模型进行融合并构成一种新的级联神经网络,分别提取输入图像的空间和时间特征,并用以拟合输入序列图像与输出运动参数之间的非线性关系,从而完成从输入序列图像到运动参数的端到端的规划。实验利用模拟驾驶环境的数据进行训练和测试,结果显示所提模型在乡村路、高速路、隧道和山路四种道路中均方根误差(RMSE)不超过0.017,且预测结果的稳定度优于未使用级联网络的算法一个数量级。结果表明,所提模型能有效地学习人类的驾驶行为,并且能够克服累积误差的影响,适应多种不同场景下的路况,具有较好的鲁棒性。

关键词: 自动驾驶, 运动规划, 深度级联神经网络, 卷积神经网络, 长短期记忆模型

Abstract: To address the problems that rule-based motion planning algorithms under constraints need pre-definition of rules and temporal features are not considered in deep learning-based methods, a motion planning model based on deep cascading neural networks was proposed. In this model, the two classical deep learning models, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network, were combined to build a novel cascaded neural network, the spatial and temporal features of the input images were extracted respectively, and the nonlinear relationship between the input sequential images and the output motion parameters were fit to achieve the end-to-end planning from the input sequential images to the output motion parameters. In experiments, the data of simulated environment were used for training and testing. Results show that the Root Mean Squared Error (RMSE) of the proposed model in four scenes including country road, freeway, tunnel and mountain road is less than 0.017, and the stability of the prediction results of the proposed model is better than that of the algorithm without using cascading neural network by an order of magnitude. Experimental results show that the proposed model can effectively learn human driving behaviors, eliminate the effect of cumulative errors and adapt to different scenes of a variety of road conditions with good robustness.

Key words: autonomous driving, motion planning, deep cascaded neural network, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) model

中图分类号: