Fig。  9。  The test path and condition

VII。CONCLUSION

This paper introduces an intelligent vehicle system design based on infrared photoelectric sensor trace。 The system employs Freescale's single chip microcomputer as main controller, DC motor as actuator。 The intelligent vehicle hardware and software design are finished。 The intelligent vehicle was tested on the road which middle was pasted black mark line。 The result shows the intelligent vehicle can run at high speed and stability on the straight road。 As long as the vehicle speed is controlled appropriately, the vehicle can run smoothly on the road bend。

REFERENCES

[1] L。 B。 Yan, F。 G。 Fan, “A simple intelligent vehicle based on the single chip microcomputer, ” Electric Technology, 4, 2004, pp。 8-10。 ˄in Chinese˅

[2] J。 P。 Wu, ZH。 G。 Yin, S。 Cao, and K。 Y。 Li,ĀUsage of the reflected infrared sensor in automatic guiding car, ” China Measurement Technology, vol。 30, 2004, pp。 21-23。 ˄in    Chinese˅

[3] B。 H。 Wu, W。 H。 Huang, L。 Chen,  and  M。  Yang,  “The  intelligent vehicle design based on path identification,” Electric Technology Application, 3, 2007, pp。 80-83。 ˄in    Chinese˅

[4]    MC9S12DG128 Device User Guide [Z]。Freescale Semi-Conductor   Inc

㧘2005。

[5] K。 SH。 Huang, L。 G。 Li, W。 Liu, and J。 Hao, “Intelligent vehicle navigation system based on photoelectric Sensor  dispersed arrangement, ” Electric Product World, 2, 2007, pp。 50-54。 ˄ in Chinese˅

Available from: Suresh Perumbure Retrieved on: 05 April 2016

Neural Network Based Hybrid Adaptive Controller for an Autonomously driving Car using Thin Plate Spline Radial Basis Activation Function

P。Suresh1, a and P。V。Manivannan2,b

1,2 MSB 350A, VRRL, PEIL, Mechanical Sciences Block, Mechanical Engineering Department,

Keywords: Self-driving car, nonlinear vehicle dynamics model, lane following, lateral deviation, Neural Network, Thin Plate Spline (TPS) Radial Basis Function (RBF), adaptive control

Abstract: This paper presents a hybrid lateral and longitudinal controller for a self-driving passenger car。 The controller comprises a Proportional Derivative (PD) controller as a closed loop controller and Neural Network (NN) based adaptive compensator as a feed forward controller。 The activation function of the NN adaptive stage is based on a poly-harmonic Thin Plate Spline (TPS) Radial Basis Function (RBF), which promises better accuracy, smoother interpolation and closed form solutions。 The controller development and testing has been performed using a non-linear vehicle dynamics model, which has been developed using the Matlab / Simulink tool。  The Controller performance in terms of vehicle lane following (lateral deviation control) and safe cruising control (longitudinal spacing error control) have been verified through simulations。 Reductions of lateral deviation error by 15% and longitudinal spacing error by 7% have been achieved。

Introduction

Fully autonomous road vehicles, also known as self-driving vehicles, have become a prime area of research in the past decade。 The promise of faster commute times, better safety and fuel economy, in addition to relief from driving have contributed to the focus in this area。 The concept of autonomous vehicles has been around since many years [1, 2]。 The initial thrust was towards the development of Autonomous Highway Systems (AHS) [2]; however it is proving to be economically and environmentally unviable。 Intelligent self-driving vehicles promise to be a better alternative for improving road safety and traffic throughput with the existing road infra-structure。 Introduction of autonomous driving in vehicles is fraught with many challenges like: system integration, implementation of prediction and trust, etc。 [3]。 Research in vehicle dynamics and control systems [4] have lead to a variety of control schemes。 Classical PID controllers, Fuzzy Controllers [5] and controllers based on combinations of different AI techniques (Neural Networks (NN), Fuzzy Control, Genetic Algorithms) [6] have been applied to tackle the road vehicle control problems。 In recent times, AI based control techniques have slowly gained popularity [7]。 Most of the above mentioned control approaches, treats the lateral and longitudinal vehicle control as independent problems。 However, there is a need for development of a combined lateral and longitudinal controller, which can provide optimum performance during the vehicle maneuvers like: lane changing, dynamic obstacle avoidance, etc。 红外光电传感器的智能循迹车辆英文文献和中文翻译(6):http://www.youerw.com/fanyi/lunwen_100371.html