外文翻譯--智能汽車系統(tǒng)控制算法的研究

1、<p><b>　　英文翻譯</b></p><p>　　翻譯資料(英文) Study of Control Algorithm for Smart Car System </p><p>　　翻譯資料(中文) 智能汽車系統(tǒng)控制算法的研究 </p>&

2、lt;p>　　院 系：電子與信息工程學(xué)院</p><p>　　專 業(yè)：電子信息工程 </p><p>　　二Ｏ一一 年 十二 月 二十八 日</p><p>　　2011 Fourth International Conference on Information and Computing</p><p>　　S

3、tudy of Control Algorithm for Smart Car System</p><p>　　Ruixian li</p><p>　　School of Transportation and Vehicle Engineering Shandong University of Technology Zibo, China ;Email:lrx@sdut.edu.cn&

4、lt;/p><p>　　Abstract—In this paper, target identification and trajectory technology are analyzed. The tracking control algorithm based on the photoelectric sensors is proposed. The algorithm utilizes the errors

5、 of the location and the signal of route as input parameters, to regulate the output angle of the steering gear. The smart car system includes the straight trajectory control algorithm, the curvy trajectory control algor

6、ithm and the S-type trajectory control algorithm according to the different charac</p><p>　　Index Terms—photoelectric sensor, black trajectory, smart car</p><p>　　I. INTRODUCTION</p><

7、p>　　A smart car system is composed of the power supply module, the sensor module, the Direct Current (DC) driving motor module, the path identification module, the communication and debugging module and the single-chi

8、p module. In order to make the smart car move along the trajectory with reasonable speed, the detection of the path information, the DC servo motor control and the driving motor control must be hung together by the singl

9、e-chip. If the data of the sensor is not properly collected and ide</p><p>　　Figure 1. Total control program for the smart car</p><p>　　In this paper, we adopt the photoelectric sensors to detec

10、t the information of the reference trajectories for a smart car to track. In order to achieve preferable stability for a smart car running along the reference trajectories, we put forward a solution according to the main

11、 control function of the smart car system, which includes the information identification of the black line, the angle control of steering gear and the speed regulation control of the driving motor. In the entire smart ca

12、r </p><p>　　II. THE IMPLEMENTATION OF THE TRACKING CONTROL ALGORITHM</p><p>　　A. Photoelectric sensor layout</p><p>　　The photoelectric sensor is made up of a series of lightemittin

13、g and light-reaccepting diodes. A black trajectory is the runway. Light intensity reflected from the black trajectory is different from that of the white trajectory. We propose a common method which is discrete recogniti

14、on algorithm based on above the principle. The diode voltage value will be sent into the microcontroller through the I/O ports . CPU determines whether or not the sensor is on the top of the marked line according to t<

15、;/p><p>　　The layout, the number and the interval of photoelectric sensors are all closely related to the control algorithm. In order to predict the farther distance and achieve higher efficiency, we adopt a so

16、lution that 1 type showed in Figure 2. 10 photoelectric sensors are used. Photoelectric sensors are arranged in unequal spacing. Such non-linear form has superiority and scientificalness. The black dots represent the ins

17、tallation position of photoelectric sensors, symmetrical distribution on both si</p><p>　　Figure 2. The layout of photoelectric sensors</p><p>　　B. The Algorithm of Stable Operation System</p

18、><p>　　The tracking control algorithm is used to regulate the motor speed and the steering gear angle. When the photoelectric sensors between NO.3 and NO.6 are always low-level effective, it can be claimed that

19、 photoelectric sensors have detected the straight trajectory. At the moment, the smart car will run in full speed. In this case the smart car can achieve the maximum speed. When the photoelectric sensors between NO.0 and

20、 NO.3 or between NO.6 and NO.9 are always lowlevel effective, it can be claim</p><p>　　The location of a smart car is determined by the feedback value of photoelectric sensors. The analog signal values of ph

21、otoelectric sensors which have detected black line are transformed into digital signal values. The values are between 0 and 255. Then the smart car system makes a judgment to determine which sensor value is less than 80.

22、 The lesser values show that the sensors have detected the location of the black line. Then its mark bit is set into 0 in C++ program. And the CPU calculates th</p><p>　　Figure 3. Tracking control algorithm

23、flow chart</p><p>　　C. Smart Car Tracking Control Algorithm</p><p>　　1) Straight Trajectory Control Algorithm: Running in a straight line is a basic and important requirement for a smart car. In

24、 this case the smart car can achieve the maximum speed and the maximum acceleration. The maximum speed is about 9m/s-10m/s or faster. The straight line algorithm can be implemented as the cesures depicted in Figure 4.<

25、;/p><p>　　The smart car system determines the straight control algorithm according to the path information which is detected by the photoelectric sensors and calls the appropriate procedure to control the motor

26、 speed and the steering angle.</p><p>　　2) Curvy Trajectory and S-type Trajectory Control</p><p>　　Algorithms: When the smart car system detects the curvy trajectory, it ran under the manner tha

27、t takes the shortcut. In other words the smart car moves along the inner of the trajectory rather than followes the trajectory.</p><p>　　Figure 4. Straight trajectory control strategy</p><p>　　W

28、hen the central point is deflective, the smart car will appear deflective phenomenon. The smart car system laid the foundation for taking the near way in the curvy trajectory. After the smart car system records the infor

29、mation of the first circle, it can distinguish the next corner information directly and turn left or right while the smart car is running in the second circle. Then it can cross the curvy trajectory according to a smalle

30、r radius, reduce the distance and save the time. Figure 5 i</p><p>　　Figure 5. Curvy trajectory control strategy</p><p>　　While the smart car is moving along the S-type trajectory, if the speed

31、can not be controlled effectively, it may run out of the runway. Figure 6 and Figure 7 show the S-type control strategy.</p><p>　　The smart car system records the digital signal values of the AD module and c

32、ompares with the number 255, if the values of sensors of the right are less than 255, set A1=1; if the values of sensors of the central are less than 255, set A2=1; if the values of sensors of the left are less than 255,

33、 set A3=1. If A1, A2 and A3 are all 1, it can be claimed that the sensors have detected the S-type trajectory.</p><p>　　3) The Possible Situation and Its Corresponding</p><p>　　Algorithm: Becaus

34、e the smart car is rear-wheel drived, if the smart car accelerates when it crosses a curvy trajectory, there may have a over-steering phenomenon. The smart car system need to accurately control the steering gear. If all

35、the 10 photoelectric sensors can not detect the black trajectory, which implies that the smart car run out of the runway. In this case, the smart car system should carry out the following control strategy in Figure 8.<

36、;/p><p>　　Figure 6. The subroutine of judging runway which is curvy trajectory or Stype trajectory</p><p>　　If all the 10 photoelectric sensors can not detect the black trajectory, the smart car sy

37、stem can determine the location of the black trajectory through Interrupt Mode. Then the smart car system determines that whether or not the smart car is out of</p><p>　　the runway. If it is, the smart car s

38、ystem works under the error handling mechanism. If not, the smart car system continues operating the tracking control algorithm. The error handling mechanism is that the smart car system read the latest historical data f

39、rom MAP table and sends it to the central processing unit. Then the CPU determines the sensor which is the last one detected the black line and controls the steering gear so that the smart car can turn back.</p>&

40、lt;p>　　D. PID Control of The Smart Car System</p><p>　　The smart car system makes the motor actual velocity close to the given speed according to PID algorithm . In the C/OS-II system, digital PID control

41、 algorithm is divided into the position form control algorithm and the incremental form control one. In order to reduce the calculated amount and get a stable result, the steering gear control will adopt the incremental

42、form control algorithm. Figure 9 is the flow process of the calculation.</p><p>　　Figure 7. The flow chart of S-type trajectory target speed</p><p>　　Figure 8. The interrupt program to determine

43、 whether or not the smart car ran out of the runway</p><p>　　Figure 9. The Control Module of Motor Speed</p><p>　　The smart car system can control the steering angle easily by using the coordina

44、te method. For example, when No.0 detected the black trajectory, the smart system would set up the corresponding coordinate figure for -17. The lateral sensor is farther from the centerline, there is a bigger coordinate

45、figure corresponding to the sensor. Table 1 show that every photoelectric sensor has a unique coordinate figure.</p><p>　　TABLE I. COORDINATES MATCHING WITH THE PHOTOELECTRIC SENSORS</p><p>　　

46、We compile the C++ program in CodeWarrior IDE . The following code is the main program code.</p><p>　　The definition of PID structure: struct PID { int Proportion; // Proportional Const int Integral; // Inte

47、gral Const int Derivative; // Derivative Const int LastError; // Error[-1] int PrevError; // Error[-2] int Outlimit;// Output limiter int Output; } speed1; </p><p>　　Calculation of PID: double PIDCalc( PID *

48、pp, double NextPoint ,double A, double Pup, double Pdown);</p><p>　　The initialization of the structure of speed: void init_pid(struct PID *pid,int p_gain,int i_gain,int d_gain, int le,int pe,int outlimit, i

49、nt ot);</p><p>　　Calculating the PWM duty cycle: PWM=PIDCalc(&speed1,SetPoint,Speed); *MotorPWM =PWM;</p><p>　　III. THE EXPERIMENTAL RESULT</p><p>　　Through the simulation resul

50、ts as can be seen in Figure10, we observe that by using the improved algorithm the smart car can track the prescribed trajectories with satisfying stability and faster speed.</p><p>　　Figure 10. The smart ca

51、r stable operation under the simulation environment</p><p>　　IV. CONCLUSION</p><p>　　In this paper, a tracking control algorithm based on the photoelectric sensors is proposed. The smart car can

52、 move smoothly along the prescribed trajectories. The simulation shows that the tracking control algorithm makes the smart car more flexible and more stable. However, it still needs to improve the smart car system. For e

53、xample, how to make the smart car run smoothly in more complex environment and how to make the motor speed more effectively. We will solve these problems in the future.</p><p>　　REFERENCES</p><p&g

54、t;　　[1] Zheng Jianli, Huang Lijia, Ge Pengfei, and Liu Xiangfei, “Autonomous Tracking in Intelligent Vehicle Based on CCD”. JOURNAL OF DONG HUA UNIVERSITY (NATURAL SCIENCE), Vol.34, No.6, Dec.2008, pp.728-731</p>

55、<p>　　[2] Jia Yong, “Steering Control of Intelligent Vehicle Based on the Synthesis of Fuzzy Control Arithmetic”. Computer Knowledge And Technology, Vol.4, No.7, December 2008, pp.1877-1878,1899</p><p>

56、　　[3] LIU Jin, QI Xiao-hui, and LI Yong-ke, “Intelligent Vehicle Fuzzy-PID Control Algorithm Based on Vision” Automatic Measurement and Control, O. I. Automation, 2008, Vol. 27, No.10, pp.67-68,69</p><p>　　[

57、4] Zhuo Qing, Huang Kaisheng, and Shao Beibei. Learn to do the smart car–the challenge "Freescale" Cup. Beijing University of Aeronautics & Astronautics Press, 2007.</p><p>　　[5] Shao Beibei. T

58、he online development methodology of Single-chip embedded applications . Tsinghua University Press, Beijing 2004.</p><p>　　[6] Zheng Kougen, Tang Jie, and He Tongneng, Embedded systems - the Design and Appli

59、cation used 68HC12 and HCS12 , Electronics Industry Press, Beijing, 2006.</p><p>　　[7] Stephen Prata. U.S.A , C++ primer plus , Posts&telecommunications press, 2002.</p><p>　　[8] Chen Shizhi

60、, uC/OS- 􀄊 core analysis, Transplantation and Driver Development. Posts&telecommunications press , 2007</p><p>　　2011年第四次國際會(huì)議，信息與計(jì)算</p><p>　　智能汽車系統(tǒng)控制算法的研究</p><p>　　李睿賢

61、淄博，中國山東理工大學(xué)交通與車輛工程學(xué)院電子郵件：lrx@sdut.edu.cn</p><p>　　摘要本文的目標(biāo)識(shí)別和軌跡技術(shù)分析。跟蹤控制算法光電傳感器的建議。該算法利用的位置和路線作為輸入信號(hào)的錯(cuò)誤參數(shù)，以規(guī)范舵機(jī)輸出角。 “智能車系統(tǒng)包括直線軌跡控制算法，彎曲的軌跡控制算法和S型根據(jù)不同的軌跡控制算法特征軌跡。實(shí)驗(yàn)表明，通過使用該算法，智能車可以順利移動(dòng)沿直線軌跡，彎曲的軌跡和S型軌跡與滿意的精度。&

62、lt;/p><p>　　索引條款——光電傳感器，黑色的軌跡，智能汽車</p><p><b>　　導(dǎo)言</b></p><p>　　一個(gè)智能車系統(tǒng)是由電源模塊，傳感器模塊，直流電（DC）駕駛電機(jī)模塊，路徑識(shí)別模塊，溝通和調(diào)試模塊和單芯片模塊。為了使智能車沿移動(dòng)以合理的速度軌跡，路徑檢測(cè)信息，直流伺服電機(jī)控制和驅(qū)動(dòng)電機(jī)控制必須掛在一起的單芯片。如果數(shù)

63、據(jù)傳感器是不正確的收集和鑒定，并轉(zhuǎn)向伺服電機(jī)控制有一個(gè)錯(cuò)誤的操作，智能車將嚴(yán)重動(dòng)搖，甚至偏離跑道。如果直流驅(qū)動(dòng)電機(jī)控制是無效的，它也可能導(dǎo)致在直線或彎曲的速度過快的速度較慢軌跡。從圖1中，我們可以看到如何在智能車系統(tǒng)運(yùn)行。</p><p>　　圖1。智能汽車的總量控制計(jì)劃</p><p>　　在本文中，我們采用光電傳感器來檢測(cè)一個(gè)智能汽車的信息參考軌跡跟蹤。為了實(shí)現(xiàn)一個(gè)智能車可取穩(wěn)定沿著參

64、考軌跡運(yùn)行，我們提出了解決方案的主要控制功能的智能車信息識(shí)別系統(tǒng)，其中包括黑線，舵機(jī)的角度控制和速度調(diào)節(jié)控制驅(qū)動(dòng)電機(jī)，在整個(gè)智能車系統(tǒng)中，光電傳感器作為智能車的眼睛必須完全正確的識(shí)別路徑信息，使智能車系統(tǒng)運(yùn)行穩(wěn)定。跟蹤控制策略包括：直線算法，曲線算法，S型線算法和錯(cuò)誤處理機(jī)制算法。這種跟蹤算法具有以下優(yōu)勢(shì)：集合，離散信號(hào)點(diǎn)少的集合，在抗干擾能力強(qiáng)的環(huán)境下，只需很短的時(shí)間響應(yīng)和較低的成本。仿真結(jié)果表明，如果智能車光電傳感器布局安排正確，跟

65、蹤控制算法會(huì)持有類似的CCD的影響。</p><p>　　二、跟蹤控制算法的實(shí)施</p><p><b>　　1、光電傳感器布局</b></p><p>　　光電傳感器是由一個(gè)系列的發(fā)光和光接收的二極管組成的。一個(gè)黑色的軌跡跑道，黑色的軌跡反映的光強(qiáng)度與白色軌跡所反映的是不同的。我們提出了一個(gè)常用的對(duì)上述原則基于離散識(shí)別算法的方法。二極管上的電

66、壓值將通過I / O端口被發(fā)送到單片機(jī)上。 CPU確定與否是根據(jù)頂部上標(biāo)線的輸入端口電壓的傳感器，在這些智能車系統(tǒng)的屏幕上的傳感器的頂部會(huì)出現(xiàn)黑色軌跡。在目前，智能車系統(tǒng)可以相對(duì)確定智能車的位置和路徑信息。</p><p>　　布局，數(shù)量和間隔光電傳感器都是密切相關(guān)的控制算法。為了預(yù)測(cè)更遠(yuǎn)的距離和實(shí)現(xiàn)更高的效率，我們采取了一種如1型在圖2中顯示的解決方案，光電傳感器在不平等的間距排列中是用10光電傳感器使用的，這

67、種非線性形式有優(yōu)勢(shì)和科學(xué)性兩種，黑點(diǎn)代表光電傳感器的安裝位置，對(duì)稱兩側(cè)分布，兩個(gè)光電傳感器的相鄰之間的距離被設(shè)定為22，16.5，16.5，16.5，10，16.5，16.5，16.5和22種，單位為毫米，電路板是用螺絲固定在U型支架上的，整個(gè)身體固定在智能車前。</p><p>　　圖2 光電傳感器的布局</p><p>　　2、穩(wěn)定運(yùn)行系統(tǒng)的算法</p><p

68、>　　跟蹤控制算法是用來調(diào)節(jié)電機(jī)速度和舵機(jī)的角度的。當(dāng)光電3號(hào)和6號(hào)之間的傳感器總是低級(jí)有效時(shí)，它可以聲稱是光電傳感器檢測(cè)到的直線軌跡。目前，智能車正在全速運(yùn)行，在這種情況下，智能車可以實(shí)現(xiàn)最高速度，當(dāng)光電傳感器0號(hào)，3號(hào)或6號(hào)和9號(hào)之間總是低級(jí)有效時(shí)，可以聲稱是光電傳感器檢測(cè)到的S型或彎曲的軌跡。在這種情況下，智能車應(yīng)提前減速左轉(zhuǎn)或右轉(zhuǎn)，為了避免運(yùn)行出來，智能車的速度不應(yīng)該過高。我們采用一種有限速度的戰(zhàn)略來解決問題，當(dāng)拖車的光電

69、傳感器的距離為22mm時(shí)，最大速度為3M / S.當(dāng)光電傳感器的距離為16.5毫米，最高時(shí)速是3.3米/秒。圖3是穩(wěn)定運(yùn)行的系統(tǒng)流程圖。</p><p>　　一個(gè)智能車的位置，是由反饋光電傳感器的值所決定的。模擬信號(hào)的值光電傳感器檢測(cè)到的黑線是轉(zhuǎn)換成數(shù)字的信號(hào)值，值介于0和255。智能車系統(tǒng)是確定傳感器的值小于80的一種判斷，值較小就表明，傳感器檢測(cè)到的是黑線的位置，在C + +程序中，其標(biāo)志位設(shè)置為0，根據(jù)標(biāo)志

70、位，CPU計(jì)算坐標(biāo)，智能車系統(tǒng)將會(huì)發(fā)出相應(yīng)的PWM脈沖舵機(jī)，并根據(jù)坐標(biāo)獲得所需的智能車的角度。例如，如果0號(hào)，1，2，7，8，9傳感器檢測(cè)到黑線，我們可以得出結(jié)論，智能車將偏離直線軌跡,智能車系統(tǒng)會(huì)使智能車提早減速并給予必要的速度，而智能車就會(huì)沿著彎曲的軌跡移動(dòng)速度和角度，當(dāng)4號(hào)，5個(gè)傳感器檢測(cè)到黑線時(shí)，它可聲稱是智能車沿直線移動(dòng)軌跡的。因此，智能車將會(huì)加快。</p><p>　　圖3 跟蹤控制算法流程圖&l

71、t;/p><p>　　3、智能車跟蹤控制算法</p><p>　　1）直軌跡控制算法：直線運(yùn)行對(duì)于一個(gè)智能車來說是一個(gè)基本、重要的要求。在這種情況下，智能車可以達(dá)到最高速度和最大加速度，最大速度約為9m/s-10m/s或更快，直線算法作為cesures可以實(shí)現(xiàn)，如圖4所示的。</p><p>　　根據(jù)由光電傳感器和調(diào)用相應(yīng)的程序檢測(cè)到的路徑信息控制電機(jī)的轉(zhuǎn)速和轉(zhuǎn)向角，智

72、能車系統(tǒng)會(huì)確定直線控制算法。</p><p>　　2）彎曲軌跡和S型軌跡控制算法：當(dāng)智能車系統(tǒng)檢測(cè)彎曲軌跡時(shí)，它可以在快捷的方式下運(yùn)行，換句話說，就是智能車沿內(nèi)部軌跡而不是接下來的軌跡移動(dòng)。</p><p>　　圖4 直軌跡控制策略</p><p>　　當(dāng)中心點(diǎn)偏斜時(shí)，智能車將出現(xiàn)偏斜的現(xiàn)象，智能車系統(tǒng)在彎曲軌跡附近奠定了基礎(chǔ)，智能車系統(tǒng)記錄的第一個(gè)圓的信息之后

73、，它可以直接區(qū)分下角信息并向左或向右轉(zhuǎn)彎，而智能車運(yùn)行在第二個(gè)圓時(shí)，它可以跨越到一個(gè)較小半徑的彎曲軌跡，從而減少距離和節(jié)省時(shí)間。圖5是彎曲的軌跡控制策略。</p><p>　　圖5 彎曲的軌跡控制策略</p><p>　　雖然智能車沿著S型軌跡運(yùn)行，如果速度不能得到有效的控制，它可能會(huì)跑道耗盡。圖6和圖7顯示的是S型控制戰(zhàn)略。</p><p>　　智能車系統(tǒng)記錄

74、的數(shù)字信號(hào)值為AD模塊和比較數(shù)255時(shí)，如果值權(quán)傳感器少于255個(gè)，設(shè)置A1= 1;如果值中央的傳感器都小于255，設(shè)置A2= 1;如果值左邊的傳感器是小于255，設(shè)置A3= 1。如果A1，A2和A3都是是1時(shí)，它可以聲稱傳感器檢測(cè)S型軌跡。</p><p>　　3）可能發(fā)生的情況及其相應(yīng)的算法：由于智能車是后輪驅(qū)動(dòng)的，如果智能車穿過彎曲軌跡加速時(shí)，有可能有過度轉(zhuǎn)向的現(xiàn)象，智能車系統(tǒng)需要精確控制舵機(jī)；如果所有的1

75、0光電傳感器無法檢測(cè)到黑色軌跡時(shí)，意味著智能車運(yùn)行的跑道會(huì)耗盡，在這種情況下，智能車系統(tǒng)應(yīng)該開展以下在圖8中的控制策略。</p><p>　　圖6 彎曲軌跡或Stype判斷跑道的子程序彈道</p><p>　　如果所有的10個(gè)光電傳感器無法檢測(cè)到黑色軌跡，智能車系統(tǒng)可以通過中斷模式的黑色軌跡確定位置，然后智能車系統(tǒng)決定智能車是否出跑道。如果是的話，智能車系統(tǒng)會(huì)在錯(cuò)誤的處理機(jī)制原理下工作

76、；如果沒有，智能車系統(tǒng)繼續(xù)經(jīng)營跟蹤控制算法。錯(cuò)誤處理機(jī)制是智能車系統(tǒng)從映射表中閱讀到的最新的歷史數(shù)據(jù)，并把它發(fā)送到中央處理單元，那么CPU決定這是最后一個(gè)檢測(cè)到黑線和控制舵機(jī)的傳感器以便智能車可以回頭。</p><p>　　4、PID控制的智能車系統(tǒng)</p><p>　　根據(jù)PID算法，智能車系統(tǒng)，使接近給定的速度電機(jī)的實(shí)際速度在μC/ OS – Iisystem中，數(shù)字PID控制算法分為

77、位置形式的控制算法和增量窗體控件算法。為了減少計(jì)算量，并得到非穩(wěn)態(tài)結(jié)果，舵機(jī)控制將采取thencremental的形式控制算法。圖9是計(jì)算的流水作業(yè)。</p><p>　　圖7 S型軌跡目標(biāo)速度的流程圖</p><p>　　圖8 中斷程序，以確定是否智能車跑出跑道</p><p>　　圖9 電機(jī)轉(zhuǎn)速的控制模塊</p><p>

78、;　　智能車系統(tǒng)可控制轉(zhuǎn)向角很容易被使用坐標(biāo)法。例如，當(dāng)No.0detected黑色的軌跡，智能系統(tǒng)將設(shè)立thecorresponding-17坐標(biāo)圖。從中心線的橫向傳感器更遠(yuǎn)，有一個(gè)更大的坐標(biāo)圖對(duì)應(yīng)傳感器。表1顯示，每一個(gè)光電傳感器具有獨(dú)特的坐標(biāo)圖。</p><p>　　表一 坐標(biāo)PHOTOELECTRICSENSORS匹配</p><p>　　我們?cè)贑odeWarrior IDE

79、編譯C + +程序，下面的代碼是主要的程序代碼。</p><p>　　PID結(jié)構(gòu)的定義：結(jié)構(gòu)的PID{INT比例;//比例Constint積分;/ /積分Constint衍生物;/ /衍生Constint LastError;/ /錯(cuò)誤[-1] INT PrevError;/ /錯(cuò)誤[-2] INT Outlimit;/ /輸出limiterint輸出} SPEED1;PID的計(jì)算：雙PIDCalc（PID* P

80、P，雙NextPoint，雙A，雙小狗，雙Pdown）; 速度結(jié)構(gòu)的初始化：無效init_pid（結(jié)構(gòu)的PID PID，p_gain i_gain intd_gain，樂，PE，INT outlimit，OT）; 計(jì)算PWM的占空比：PWM= PIDCalc（SPEED1，設(shè)定值，速度）; * MotorPWM= PWM。</p><p><b>　　三、實(shí)驗(yàn)結(jié)果</b></p>

81、<p>　　通過仿真結(jié)果在圖10中可以看到，我們觀察到通過使用改進(jìn)的算法智能車可以按規(guī)定的軌跡跟蹤與滿足穩(wěn)定和更快速度。</p><p>　　圖10 智能車仿真環(huán)境下的穩(wěn)定運(yùn)行</p><p><b>　　四、結(jié)論</b></p><p>　　在本文中，光電傳感器在提出一個(gè)跟蹤控制算法的基礎(chǔ)上，智能車可以沿規(guī)定的軌跡順利移動(dòng)

82、。仿真結(jié)果表明，跟蹤控制算法能使智能車更靈活和更穩(wěn)定，然而，它仍需要改善智能車系統(tǒng)，例如，如何使智能車在更為復(fù)雜的環(huán)境中順利運(yùn)行，以及如何更有效地使電機(jī)轉(zhuǎn)速，我們將在未來解決這些問題。</p><p><b>　　參考文獻(xiàn)</b></p><p>　　[1] 鄭監(jiān)利縣，黃禮嘉，葛鵬飛，劉香妃，“基于CCD的智能車輛自主跟蹤”，東華大學(xué)學(xué)報(bào)（理學(xué)版），第34卷，第6期，

83、2008年12月，pp.728- 731</p><p>　　[2] 賈勇，“基于模糊控制算法的合成”智能車輛轉(zhuǎn)向控制，電腦知識(shí)與技術(shù)，第4卷，第7號(hào)，2008年12月，pp.1877- 1878，1899</p><p>　　[3] 劉進(jìn)，齊曉輝，李勇科，“車輛智能模糊PID控制算法，基于視覺的”自動(dòng)測(cè)量和控制，其他投資自動(dòng)化，2008年卷，27日，第10期，第67-69，68，69&l

84、t;/p><p>　　[4] 卓青，黃凱盛，邵貝貝，學(xué)做智能車挑戰(zhàn)“飛思卡爾”杯。北京航空航天大學(xué)出版社，2007</p><p>　　[5] 邵貝貝，單芯片嵌入式應(yīng)用的在線開發(fā)方法。清華大學(xué)出版社，北京2004年</p><p>　　[6] 鄭芤哏，湯杰，赫嗵能，嵌入式系統(tǒng) - 設(shè)計(jì)和應(yīng)用，電子工業(yè)出版社，北京，200668HC12和HCS12使用</p>