Academic Journal of Computing & Information Science, 2022, 5(8); doi: 10.25236/AJCIS.2022.050808.
Weipei Fu, Qiannuo Li, Zhihao Fan
College of Electronic Information and Engineering, Heilongjiang University of Science and Technology, Harbin, Heilongjiang, China
In modern society, cars have been widely used. Every driver will face the problem of reversing. Experienced drivers can park the car to the designated position quickly and accurately. However, most drivers, especially some novices who have just obtained their driver's license, are very worried about the problem of parking. It is often difficult to meet both accuracy and speed. At this time, the automatic parking system appeared in front of the public. As one of the representative systems in the era of vehicle intelligence, the automatic parking system has become the main way for major automobile companies to show their strength in vehicle intelligence; In today's increasingly scarce parking spaces and shrinking parking space, automatic parking system has gradually become a "standard accessory" of vehicles and one of the main reference items for consumers to buy cars. Based on theory and practice, this paper analyzes the possible situations of automatic parking and solves the following problems to improve the automatic parking system. The acceleration model is solved by differential method. The unmanned vehicle travels along a straight line for 1.381m and reaches the maximum limit speed of 20km / h. When unmanned vehicle turns, it is necessary to establish the model of minimum curvature path and minimum path length to express the relationship between them. The initial position of the unmanned vehicle is at the intersection of the parking lot. Three parking situations will be considered, namely vertical parking space, parallel parking space and inclined parking space. A visual trajectory graph will be established to indicate the speed, path, acceleration and other parameters of each point, which vividly shows that the parking can be completed safely and quickly without conflict and collision.
Ackerman steering model, Dijkstra algorithm, VISSIM model
Weipei Fu, Qiannuo Li, Zhihao Fan. Research on automatic parking path optimization based on Ackerman model. Academic Journal of Computing & Information Science (2022), Vol. 5, Issue 8: 50-57. https://doi.org/10.25236/AJCIS.2022.050808.
 B MULLER,J DEUTSCHER,S GRODDE. Continuous Curvature Trajectory Design and Feedforword Control for Parking a Car [J]. IEEE Transaction on Control Systems Technology, 2007, 15(3); 541-553.
 C H CHEN,C W HSU,C C YAO. A Novel Design for Full Automatic Parking System [C]. Proceedings of the 12th International Conference on ITS Telecommunacations. Taipei, 2012:175-179.
 D GORINEVSKY, A KAPITANOVSKY, A GOLDENBERC. Neural Network Architecture for trajectory Generation and Control of Automatic Car Parking [J]. IEEE Transaction on Control Systems Technology, 1996, 4 (1): 50-56
 M R Heinen, F S Osorio, F J Heinen, C Kellber. SEVA3D: Using articial neural networks to autonomous vehicle parking control [C]. In: Proceedings of the 2006 International Joint Conference on Neural Networks. Vancouver, Canada: IEEE, 2006: 4704-4711.
 Meng Xiangxi Research on automatic parking method based on panoramic vision [D]. Jilin University, 2021 DOI: 10.27162/d.cnki. gjlin. 2021.003360.
 Xue Haoyuan, Lian Jinyi, Wang Jialun, Ren Yanqiang Improvement of Ackerman steering model and Simulation of electronic differential control [J] Automotive practical technology, 2020, (10): 118-121
 Zhang Daoquan, Cheng Xiang, Ke Wei, Tang Haochong Optimization and verification of reducing the minimum turning radius of a vehicle [J] Automotive practical technology, 2022, 47 (04): 92-95 DOI: 10.16638/j.cnki.1671-7988.2022.004.022.
 PTV. Vissim 10 user manual [Z]. German: Planung. 2021.
 Gai Songxue, Zeng Xiaoqing, Yue Xiaoyuan, Yuan Zihao Parking space guidance model based on user system double-layer optimization algorithm [J] Journal of Jilin University (Engineering Edition): 2010 1-8
 F. Braghin, F. Cheli, S. Melzi, and E. Sabbioni. Race driver model. Comput. Struct., 86(13-14): 1503–1516, 2008.