The traffic accidents, traffic jams and parking problems come to appear, and have caused more and more concerns of people. The automatic parking system can help us a lot to solve these problems. The automatic parking system in this paper includes two sections, environment perception and automatic controller. The median filter and least square method are used to process the laser sensor data. Then, feasible parking space can be displayed by using K-means clustering method. The Matlab fuzzy GUI is used to establish the fuzzy controller. The kinematics equation of car is utilized to simulate the automatic vertical parking in the Matlab/simulation with the different initial path angles. Experiment results show that the environmental perception method has perfect performance and the controlling algorithm of the automatic parking system has good feasibility.
With the increase of the cars, most cities are facing a series of problems such as the traffic jams, parking difficulties and the imperfect road traffic management facilities [
In 2007, the Lexus first equipped intelligent Parking Assist System APGS (Advanced Parking Guidance System) in LS460L. The system can help the drivers complete parallel and vertical parking successfully. As the new ESO and Tiguan entered China in 2011, the Volkswagen’s second generation automatic parking assist system use the ultrasonic sensor to detect the parking space by scanning road on both sides and prompt drivers to change to reverse gear. If the accelerator and brake are controlled very good, the parallel and vertical parking will be achieved easily with the help of automatic parking system. In 2013, Ford posted a system that achieved the real “automatic”, it didn’t need drivers to control the speed, braking, etc [
There are some flawed sensor data because of the sensor’s precision and environmental disturbances. That is, errors about ambient information that affect the accuracy of path planning caused by the mismatch of data acquired by sensor and the actual environment. In order to improve accuracy of environment recognition, for most sensor data, data preprocessing is required before data analysis. The preprocessing by using the least square method and the median filtering algorithm is applied in this paper.
Median Filtering Algorithm: The main idea of Median filtering is to is to run through the data in a digital image entry by entry, finding the median of neighboring entries and replacing each entry with it. The data points of a digital image or a set of data were sorted and replaced according to this principle.
Least Square Method: The Least Square Method is a standard approach in regression analysis. Setting (xi, yi) (i = 0, 1, ⋯, m) for points of a dataset and wi > 0 (i = 0, 1, ⋯, m) for the weight coefficient of each point. In function space S = span{φ0(x), φ1(x), ⋯, φn(x)}, and ask for S*(x) in the Formula (1)satisfy the Formula (2).
The method of acquiring function S*(x) is called least square method of data fitting.
As we can see from
The basic principle of K-Means clustering is elaborated as [
Step 1: K1 [Initialization]: k data points {c1, c2, …, ck}of dataset
Step 2: K2 [Assign xi]: Calculating the distance dij, j = 1, 2, …, k from {[xi], i = 1, 2, ⋯, n} to each initial cluster center {c1, c2, …, ck}, the data xi are classified into the nearest class.
Step 3: K3 [Revise ci]: The new class cluster center of each class is acquired through calculating the average of all the data in each class.
Step 4: K4 [Deviation calculation]:
Step 5: K5 [Whether the D is convergent]: If D is convergent, the whole algorithm will end. Otherwise, it returns to K2 until convergence has been reached.
The parking space detection result is shown in
The environment perception coordinate system of automatic parking system includes the global coordinate and the vehicle coordinate system. The origin of vehicle coordinate system is set to the midpoint of the rear axle. X-axis is projected to the vehicle rear axle and directs right, and Y-axis lies in the vehicle longitudinal axis and directs forward. The midpoint of the rear axle serves as the coordinates of the vehicle position in the global coordinate system. The course angle of the vehicle is shown as the direction of the vehicle and donated by (
Regarding the vehicle as a rigid body with low speed and assuming vehicle movement direction is consistent with the movement direction of rear wheels, and the motion trajectory of rear wheels could be considered as the motion trajectory of the vehicle body. Under this condition, the center coordinate of the rear wheel axis
can be considered as vehicle body’s coordinate and the trajectory of the vehicle can be expressed by
The membership function of each input and output and the parameter settings of fuzzy controller is elaborated in literature [
Red rectangle represents the car model in
If q = 10˚, movement track of vehicle and the change curve of the vehicle course angle are shown in
When the initial course angle is 10˚, it is necessary for successfully parking to keep unchanged course angle for a period of time, then gradually increase its value when the vehicle close enough to the parking space, as it is shown in
If q = −10˚, movement track of vehicle and the change curve of the vehicle course angle are shown in
When the initial course angle q = −10˚, the course angle should be increased obviously to make the automobile aligned quickly. The simulation results are shown in
Compared three different kinds of parking simulation results. We can draw the conclusion that the parking simulation is best when q = 0˚. When q is −10˚ or 10˚, the parking simulation result is not as better as q = 0˚.
Next key point is to establish the vehicle kinematic model and design the fuzzy controller for automatic parking system, then carry out simulation on both the automatic vertical parking and parallel parking process. This section firstly established automobile kinematic model by using Arman kinematic model and simplified the vehicle dynamics model during the parking process. The second step is to gain the appropriate membership functions and fuzzy rules in fuzzy toolbox of Matlab. Setting the coordinate of the vehicle (x, y, q) as the inputs and the front wheel steering angle as the output of the fuzzy controller. The simulation results showed the perfect feasibility and real-time.
Since the parking simulation results are acquired based on the assumption of low speed station, the Arman vehicle dynamics model is employed in actual situation instead of the kinematic model. So improving the model and carrying out related research sunder other speed conditions need further works.
Yibing Zhao,Jining Li,Yuan Yang, (2015) Study on Environment Perception and Automatic Navigation Technology for the Automatic Parking System. World Journal of Engineering and Technology,03,46-51. doi: 10.4236/wjet.2015.33C007