Path planning and tracking for vehicle parallel parking based on preview BP neural network PID controller

Abstract

In order to diminish the impacts of external disturbance such as parking speed fluctuation and model uncertainty existing in steering kinematics, this paper presents a parallel path tracking method for vehicle based on preview back propagation (BP) neural network PID controller. The forward BP neural network can adjust the parameters of PID controller in real time. The preview time is optimized by considering path curvature, change in curvature and road boundaries. A fuzzy controller considering barriers and different road conditions is built to select the starting position. In addition, a kind of path planning technology satisfying the requirement of obstacle avoidance is introduced. In order to solve the problem of discontinuous curvature, cubic B spline curve is used for curve fitting. The simulation results and real vehicle tests validate the effectiveness of the proposed path planning and tracking methods.

Keywords

parallel parking / path tracking / path planning / BP neural network / curve fitting

References

[1] Jeong S H, Choi C G, Oh J N, et al. Low cost design of parallel parking assist system based on an ultrasonic sensor[J]. International Journal of Automotive Technology, 2010, 11(3): 409-416.

[2] Lee C K, Lin C L, Shiu B M. Autonomous vehicle parking using hybrid artificial intelligent approach[J]. Journal of Intelligent and Robotic Systems, 2009, 56(3): 319-343.

[3] Mukherjee R, Anderson D P. A surface integral approach to the motion planning of nonholonomic systems[J]. Journal of Dynamic Systems, Measurement, and Control, 1994, 116(3): 315-325.

[4] Laumond J P, Jacobs P E, Taix M, et al. A motion planner for nonholonomic mobile robots[J]. IEEE Transactions on Robotics and Automation, 1994, 10(5): 577-593.

[5] Jiang K, Seneviratne L D. A sensor guided autonomous parking system for nonholonomic mobile robots[C]. Proceedings of the IEEE International Conference on Robotics and Automation. Detroit, USA, 1999.

[6] Fraichard T, Scheuer A. From Reeds and Shepp’s to continuous-curvature paths[J]. IEEE Transactions on Robotics, 2004, 20(6): 1025-1035.

[7] Wang Y J, Cartmell M P. Autonomous vehicle parallel parking design using function fitting approaches[J]. Robotica, 1998, 16(2): 159-170.

[8] Gómez-Bravo F, Cuesta F, Ollero A, et al. Continuous curvature path generation based on β-spline curves for parking manoeuvres[J]. Robotics and Autonomous Systems, 2008, 56(4): 360-372.

[9] Song B. Cooperative lateral vehicle control for autonomous valet parking[J]. International Journal of Automotive Technology, 2013, 14(4): 633-640.

[10] Demirli K, Khoshnejad M. Autonomous parallel parking of a car-like mobile robot by a neuro-fuzzy sensor-based controller[J]. Fuzzy Sets and Systems, 2009, 160(19): 2876-2891.

[11] Lian K Y, Chin C S, Chiang T S. Parallel parking a carlike robot using fuzzy gain scheduling[C]. Proceedings of the IEEE International Conference on Control Applications. Hawaii, USA, 1999.

[12] Ollero A, García-Cerezo A, Martínez J L, et al. Fuzzy tracking methods for mobile robots[C]. Applications of Fuzzy Logic: Towards High Machine Intelligence Quotient Systems. Prentice Hall, USA, 1997.

[13] Li H Z, Li L, Song J, et al. Comprehensive lateral driver model for critical maneuvering conditions[J]. International Journal of Automotive Technology, 2011, 12(5): 679-686.