基于仿真平台的自动驾驶汽车转向控制方法优化研究
|
摘要
自动驾驶是通过应用人工智能技术让汽车具备人类驾驶员的驾驶技能,在没有人工干预的情况下能够独立完成复杂多变的驾驶任务。为促进自动驾驶技术的快速发展,确保自动驾驶安全、顺利进行,首先针对传统切线法转向控制模型存在的安全问题,设计加强型切线法速度约束模型对其加以优化,以控制自动驾驶汽车时刻保持在道路边界线内行驶,然后基于TORCS微观仿真平台,对加强型切线法与传统切线法的转向控制效果进行对比验证。结果显示,加强型切线法的自动驾驶转向控制效果明显优于传统切线法,从而使汽车自动驾驶的安全性得到显著提升。
Autopilot is the application of artificial intelligence technology to enable the car to have the driving skills of a human driver,and can independently complete complex and varied driving tasks without human intervention.In order to promote the rapid development of autonomous driving technology research,and ensure safe automatic driving done smoothly,Firstly,aiming at the safety problem of the tangential steering control model,the enhanced tangent method speed constraint model is designed to optimize it,and to control the automatic driving vehicle to constantly maintain safe driving automatically within the road boundary.Then based on the TORCS micro-simulation platform,the steering control effect in terms of safety of the enhanced tangent method and the tangent method is compared and verified.The results show that the enhanced tangential method's automatic driving steering control effect is significantly better than the tangent method,which can provide safer driving protection technology for the field of automatic driving research.
Autopilot is the application of artificial intelligence technology to enable the car to have the driving skills of a human driver,and can independently complete complex and varied driving tasks without human intervention.In order to promote the rapid development of autonomous driving technology research,and ensure safe automatic driving done smoothly,Firstly,aiming at the safety problem of the tangential steering control model,the enhanced tangent method speed constraint model is designed to optimize it,and to control the automatic driving vehicle to constantly maintain safe driving automatically within the road boundary.Then based on the TORCS micro-simulation platform,the steering control effect in terms of safety of the enhanced tangent method and the tangent method is compared and verified.The results show that the enhanced tangential method's automatic driving steering control effect is significantly better than the tangent method,which can provide safer driving protection technology for the field of automatic driving research.
引文
[1]王润民,邓晓峰,徐志刚,等.车联网仿真测试评价技术研究综述[J].计算机应用研究,2018,36(7):1-9.
[2]晏欣炜,朱政泽,周奎,等.人工智能在汽车自动驾驶系统中的应用分析[J].湖北汽车工业学院学报,2018,32(1):40-46.
[3]井泉.浅谈人工智能在自动驾驶汽车中的应用[J].轻型汽车技术,2018(Z1):51-54.
[4] JEAN-PIERRE O,APEL-MULLER M,祖源源.自动驾驶与未来城市发展[J].上海城市规划,2018(2):11-17.
[5]胡海波.人工智能背景下自动驾驶汽车的挑战与展望[J].中国高新区,2018(10):27.
[6]朱敏慧.人工智能推进自动驾驶研发进程[J].汽车与配件,2018(20):38-39.
[7]杨帆.无人驾驶汽车的发展现状和展望[J].上海汽车,2014(3):35-40.
[8]邓志东.人工智能将助力自动驾驶产业落地[J].机器人产业,2017(4):12-21.
[9]韩光辉,陈笑蓉,俞洋,等.基于SUMO平台的微观交通仿真研究[J].计算机工程与科学,2012,34(7):195-198.
[10] BEHRISCH M,KRAJZEWICZ D,WEBER M.Simulation of urban mobility[M].Berlin:Springer Berlin Heidelberg,2014.
[11] FELLENDORF M,VORTISCH P.Microscopic traffic flow simulator vissim[M].New York,NY:Springer New York,2010:63-93.
[12] LU L,YUN T,LI L,et al.A comparison of phase transitions produced by paramics,transmodeler,and vissim[J].Intelligent Transportation Systems Magazine IEEE,2010,2(3):19-24.
[13] COULTER R C.Implementation of the pure pursuit path tracking algorithm[J].Implementation of the Pure Pursuit Path Tracking Algorithm,1992.
[14] THRUN S,MONTEMERLO M,DAHLKAMP H,et al.Stanley:the robot that WON the darpagrand challenge[J].Journal of Field Robotics,2006,23(9):661-692.
[15] BACHA A,BAUMAN C,FARUQUE R,et al.Odin:team victortango's entry in the darpa urban challenge[J].Journal of Field Robotics,2010,25(8):467-492.
[16] MASHADI B,MAHMOUDIKALEYBAR M,AHMADIZADEH P,et al.A path-following driver/vehicle model with optimized lateral dynamic controller[J].Latin American Journal of Solids&Structures,2013,11(4):613-630.
[17]赵熙俊,陈慧岩.智能车辆路径跟踪横向控制方法的研究[J].汽车工程,2011,33(5):382-387.
[18]余如.无人驾驶车辆的自动转向控制[D].长春:吉林大学,2016.
[19]何宁,赵治国,朱阳.基于TORCS平台的虚拟车辆仿真系统开发[J].机械设计与制造工程,2010,39(15):37-41.
[20] CHEN C,SEFF A,KORNHAUSER A,et al.Deepdriving:learning affordance for direct perception in autonomous driving[C].IEEE International Conference on Computer Vision:IEEE,2015:2722-2730.
[2]晏欣炜,朱政泽,周奎,等.人工智能在汽车自动驾驶系统中的应用分析[J].湖北汽车工业学院学报,2018,32(1):40-46.
[3]井泉.浅谈人工智能在自动驾驶汽车中的应用[J].轻型汽车技术,2018(Z1):51-54.
[4] JEAN-PIERRE O,APEL-MULLER M,祖源源.自动驾驶与未来城市发展[J].上海城市规划,2018(2):11-17.
[5]胡海波.人工智能背景下自动驾驶汽车的挑战与展望[J].中国高新区,2018(10):27.
[6]朱敏慧.人工智能推进自动驾驶研发进程[J].汽车与配件,2018(20):38-39.
[7]杨帆.无人驾驶汽车的发展现状和展望[J].上海汽车,2014(3):35-40.
[8]邓志东.人工智能将助力自动驾驶产业落地[J].机器人产业,2017(4):12-21.
[9]韩光辉,陈笑蓉,俞洋,等.基于SUMO平台的微观交通仿真研究[J].计算机工程与科学,2012,34(7):195-198.
[10] BEHRISCH M,KRAJZEWICZ D,WEBER M.Simulation of urban mobility[M].Berlin:Springer Berlin Heidelberg,2014.
[11] FELLENDORF M,VORTISCH P.Microscopic traffic flow simulator vissim[M].New York,NY:Springer New York,2010:63-93.
[12] LU L,YUN T,LI L,et al.A comparison of phase transitions produced by paramics,transmodeler,and vissim[J].Intelligent Transportation Systems Magazine IEEE,2010,2(3):19-24.
[13] COULTER R C.Implementation of the pure pursuit path tracking algorithm[J].Implementation of the Pure Pursuit Path Tracking Algorithm,1992.
[14] THRUN S,MONTEMERLO M,DAHLKAMP H,et al.Stanley:the robot that WON the darpagrand challenge[J].Journal of Field Robotics,2006,23(9):661-692.
[15] BACHA A,BAUMAN C,FARUQUE R,et al.Odin:team victortango's entry in the darpa urban challenge[J].Journal of Field Robotics,2010,25(8):467-492.
[16] MASHADI B,MAHMOUDIKALEYBAR M,AHMADIZADEH P,et al.A path-following driver/vehicle model with optimized lateral dynamic controller[J].Latin American Journal of Solids&Structures,2013,11(4):613-630.
[17]赵熙俊,陈慧岩.智能车辆路径跟踪横向控制方法的研究[J].汽车工程,2011,33(5):382-387.
[18]余如.无人驾驶车辆的自动转向控制[D].长春:吉林大学,2016.
[19]何宁,赵治国,朱阳.基于TORCS平台的虚拟车辆仿真系统开发[J].机械设计与制造工程,2010,39(15):37-41.
[20] CHEN C,SEFF A,KORNHAUSER A,et al.Deepdriving:learning affordance for direct perception in autonomous driving[C].IEEE International Conference on Computer Vision:IEEE,2015:2722-2730.