• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于径向基函数神经网络的非结构化环境下自动驾驶车辆运动规划

Motion planning for autonomous vehicle based on radial basis function neural network in unstructured environment.

作者信息

Chen Jiajia, Zhao Pan, Liang Huawei, Mei Tao

机构信息

School of Engineering Science, University of Science and Technology of China, Hefei 230026, China.

Institute of Advanced Manufacturing Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Changzhou 213164, China.

出版信息

Sensors (Basel). 2014 Sep 18;14(9):17548-66. doi: 10.3390/s140917548.

DOI:10.3390/s140917548
PMID:25237902
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC4208238/
Abstract

The autonomous vehicle is an automated system equipped with features like environment perception, decision-making, motion planning, and control and execution technology. Navigating in an unstructured and complex environment is a huge challenge for autonomous vehicles, due to the irregular shape of road, the requirement of real-time planning, and the nonholonomic constraints of vehicle. This paper presents a motion planning method, based on the Radial Basis Function (RBF) neural network, to guide the autonomous vehicle in unstructured environments. The proposed algorithm extracts the drivable region from the perception grid map based on the global path, which is available in the road network. The sample points are randomly selected in the drivable region, and a gradient descent method is used to train the RBF network. The parameters of the motion-planning algorithm are verified through the simulation and experiment. It is observed that the proposed approach produces a flexible, smooth, and safe path that can fit any road shape. The method is implemented on autonomous vehicle and verified against many outdoor scenes; furthermore, a comparison of proposed method with the existing well-known Rapidly-exploring Random Tree (RRT) method is presented. The experimental results show that the proposed method is highly effective in planning the vehicle path and offers better motion quality.

摘要

自动驾驶车辆是一种配备环境感知、决策、运动规划以及控制与执行技术等功能的自动化系统。由于道路形状不规则、实时规划要求以及车辆的非完整约束，在非结构化和复杂环境中导航对自动驾驶车辆来说是一项巨大挑战。本文提出一种基于径向基函数（RBF）神经网络的运动规划方法，以引导自动驾驶车辆在非结构化环境中行驶。该算法基于道路网络中可用的全局路径，从感知网格地图中提取可行驶区域。在可行驶区域内随机选择采样点，并使用梯度下降法训练RBF网络。通过仿真和实验对运动规划算法的参数进行了验证。结果表明，所提出的方法能生成一条灵活、平滑且安全的路径，可适应任何道路形状。该方法在自动驾驶车辆上得以实现，并针对许多户外场景进行了验证；此外，还将所提出的方法与现有的著名快速扩展随机树（RRT）方法进行了比较。实验结果表明，该方法在规划车辆路径方面非常有效，并且能提供更好的运动质量。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/000c59d3ccd8/sensors-14-17548f18.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/75613ee13369/sensors-14-17548f1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/8933508c2477/sensors-14-17548f2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/0d414e26c584/sensors-14-17548f3a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/c51a10b3ecf6/sensors-14-17548f4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/e22446ba7b95/sensors-14-17548f5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/3230754c48fb/sensors-14-17548f6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/cc09b02e1706/sensors-14-17548f7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/9d2e78238e78/sensors-14-17548f8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/bfe87ad34728/sensors-14-17548f9.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/b6f7284930d0/sensors-14-17548f10.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/8616e56b7d2b/sensors-14-17548f11.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/73efd4357591/sensors-14-17548f12.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/f3d3228aeb4e/sensors-14-17548f13.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/1fb243af5d53/sensors-14-17548f14.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/df4525ff51f3/sensors-14-17548f15.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/246f216ed1a2/sensors-14-17548f16.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/e4e2c0598ba8/sensors-14-17548f17.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/000c59d3ccd8/sensors-14-17548f18.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/75613ee13369/sensors-14-17548f1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/8933508c2477/sensors-14-17548f2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/0d414e26c584/sensors-14-17548f3a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/c51a10b3ecf6/sensors-14-17548f4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/e22446ba7b95/sensors-14-17548f5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/3230754c48fb/sensors-14-17548f6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/cc09b02e1706/sensors-14-17548f7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/9d2e78238e78/sensors-14-17548f8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/bfe87ad34728/sensors-14-17548f9.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/b6f7284930d0/sensors-14-17548f10.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/8616e56b7d2b/sensors-14-17548f11.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/73efd4357591/sensors-14-17548f12.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/f3d3228aeb4e/sensors-14-17548f13.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/1fb243af5d53/sensors-14-17548f14.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/df4525ff51f3/sensors-14-17548f15.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/246f216ed1a2/sensors-14-17548f16.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/e4e2c0598ba8/sensors-14-17548f17.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ef12/4208238/000c59d3ccd8/sensors-14-17548f18.jpg

相似文献

1
Motion planning for autonomous vehicle based on radial basis function neural network in unstructured environment.基于径向基函数神经网络的非结构化环境下自动驾驶车辆运动规划
Sensors (Basel). 2014 Sep 18;14(9):17548-66. doi: 10.3390/s140917548.
2
Robust Drivable Road Region Detection for Fixed-Route Autonomous Vehicles Using Map-Fusion Images.基于地图融合图像的固定路线自动驾驶车辆鲁棒可行驶区域检测
Sensors (Basel). 2018 Nov 27;18(12):4158. doi: 10.3390/s18124158.
3
Drivers' Visual Behavior-Guided RRT Motion Planner for Autonomous On-Road Driving.用于自主道路驾驶的驾驶员视觉行为引导的快速随机搜索树运动规划器
Sensors (Basel). 2016 Jan 15;16(1):102. doi: 10.3390/s16010102.
4
Real-time path planning for autonomous vehicle off-road driving.自动驾驶车辆越野行驶的实时路径规划。
PeerJ Comput Sci. 2024 Jul 24;10:e2209. doi: 10.7717/peerj-cs.2209. eCollection 2024.
5
A Method on Dynamic Path Planning for Robotic Manipulator Autonomous Obstacle Avoidance Based on an Improved RRT Algorithm.一种基于改进RRT算法的机器人操作臂自主避障动态路径规划方法。
Sensors (Basel). 2018 Feb 13;18(2):571. doi: 10.3390/s18020571.
6
Research on Autonomous Vehicle Path Planning Algorithm Based on Improved RRT* Algorithm and Artificial Potential Field Method.基于改进RRT*算法和人工势场法的自动驾驶车辆路径规划算法研究
Sensors (Basel). 2024 Jun 16;24(12):3899. doi: 10.3390/s24123899.
7
An Optimized Trajectory Planner and Motion Controller Framework for Autonomous Driving in Unstructured Environments.一种用于非结构化环境中自动驾驶的优化轨迹规划器和运动控制器框架。
Sensors (Basel). 2021 Jun 27;21(13):4409. doi: 10.3390/s21134409.
8
Local Path Planning of Autonomous Vehicle Based on an Improved Heuristic Bi-RRT Algorithm in Dynamic Obstacle Avoidance Environment.基于改进启发式双向快速扩展随机树算法的动态避障环境下自动驾驶车辆局部路径规划
Sensors (Basel). 2022 Oct 19;22(20):7968. doi: 10.3390/s22207968.
9
Cooperative Dynamic Motion Planning for Dual Manipulator Arms Based on RRT*Smart-AD Algorithm.基于RRT*智能自适应算法的双臂协作动态运动规划
Sensors (Basel). 2023 Sep 8;23(18):7759. doi: 10.3390/s23187759.
10
Research on Lane-Changing Decision Making and Planning of Autonomous Vehicles Based on GCN and Multi-Segment Polynomial Curve Optimization.基于GCN和多段多项式曲线优化的自动驾驶车辆换道决策与规划研究
Sensors (Basel). 2024 Feb 23;24(5):1439. doi: 10.3390/s24051439.

引用本文的文献

1
Human-Like Obstacle Avoidance Trajectory Planning and Tracking Model for Autonomous Vehicles That Considers the River's Operation Characteristics.考虑河流运行特点的自主车辆类人避障轨迹规划与跟踪模型。
Sensors (Basel). 2020 Aug 26;20(17):4821. doi: 10.3390/s20174821.
2
Radial Basis Function Neural Network with Localized Stochastic-Sensitive Autoencoder for Home-Based Activity Recognition.基于局部随机敏感自动编码器的径向基函数神经网络在家庭活动识别中的应用。
Sensors (Basel). 2020 Mar 8;20(5):1479. doi: 10.3390/s20051479.
3
Drivers' Visual Behavior-Guided RRT Motion Planner for Autonomous On-Road Driving.

本文引用的文献

1
Efficient Training of Artificial Neural Networks for Autonomous Navigation.用于自主导航的人工神经网络的高效训练
Neural Comput. 1991 Spring;3(1):88-97. doi: 10.1162/neco.1991.3.1.88.
2
An aerial–ground robotic system for navigation and obstacle mapping in large outdoor areas.一种用于大型户外区域导航和障碍物测绘的空-地机器人系统。
Sensors (Basel). 2013 Jan 21;13(1):1247-67. doi: 10.3390/s130101247.
3
Nonlinear adaptive PID control for greenhouse environment based on RBF network.基于 RBF 网络的温室环境非线性自适应 PID 控制。
用于自主道路驾驶的驾驶员视觉行为引导的快速随机搜索树运动规划器
Sensors (Basel). 2016 Jan 15;16(1):102. doi: 10.3390/s16010102.
Sensors (Basel). 2012;12(5):5328-48. doi: 10.3390/s120505328. Epub 2012 Apr 26.
4
A Comparison of RBF Neural Network Training Algorithms for Inertial Sensor Based Terrain Classification.基于惯性传感器的地形分类的 RBF 神经网络训练算法比较。
Sensors (Basel). 2009;9(8):6312-29. doi: 10.3390/s90806312. Epub 2009 Aug 12.
5
The dynamic wave expansion neural network model for robot motion planning in time-varying environments.用于时变环境中机器人运动规划的动态波扩展神经网络模型。
Neural Netw. 2005 Apr;18(3):267-85. doi: 10.1016/j.neunet.2005.01.004.
6
An efficient neural network approach to dynamic robot motion planning.一种用于动态机器人运动规划的高效神经网络方法。
Neural Netw. 2000 Mar;13(2):143-8. doi: 10.1016/s0893-6080(99)00103-3.