外文翻譯--采用模糊邏輯控制使自主機器人避障設(shè)計（節(jié)選）

1、<p>　　1300英文單詞，6800英文字符，2300漢字</p><p><b>　　外文翻譯：</b></p><p>　　Autonomous robot obstacle avoidance using a fuzzy logic control scheme</p><p>　　William Martin</p&g

2、t;<p>　　Submitted on December 4, 2009</p><p>　　CS311 - Final Project</p><p>　　1. INTRODUCTION</p><p>　　One of the considerable hurdles to overcome, when trying to describe a

3、real-world control scheme with first-order logic, is the strong ambiguity found in both semantics and evaluations. Although one option is to utilize probability theory in order to come up with a more realistic model, thi

4、s still relies on obtaining information about an agent's environment with some amount of precision. However, fuzzy logic allows an agent to exploit inexactness in its collected data by allowing for a level of </p&

5、gt;<p>　　2. PHYSICAL ROBOT IMPLEMENTATION</p><p>　　2.1. Chassis and sensors</p><p>　　The robotic vehicle's chassis was constructed from an Excalibur EI-MSD2003 remote control toy tank

6、. The device was stripped of all electronics, gears, and extraneous parts in order to work with just the empty case and two DC motors for the tank treads. However, this left a somewhat uneven surface to work on, so high-

7、density polyethylene (HDPE) rods were used to fill in empty spaces. Since HDPE has a rather low surface energy, which is not ideal for bonding with other materials, a propane torch w</p><p>　　Three Sharp GP2

8、D12 infrared sensors, which have a range of 10 to 80 cm, were used for distance measurements. In order to mount these appropriately, a 2.5 by 15 cm piece of aluminum was bent into three even pieces at 135 degree angles.

9、This allows for the IR sensors to take three different measurements at 45 degree angles (right, middle, and left distances). This sensor mount was then attached to an HDPE rod with mounting tape and the rod was glued to

10、the tank base with epoxy. Since the minimum d</p><p>　　2.2. Electronics</p><p>　　In order to control the speed of each motor, pulse-width modulation (PWM) was used to drive two L2722 op amps in

11、open loop mode (Fig. 1). The high input resistance of these ICs allow for the motors to be powered with very little power draw from the PWM circuitry. In order to isolate the motor's power supply from the rest of the

12、 electronics, a 9.6 V NiCad battery was used separately from a standard 9 V that demand on the op amps led to a small amount of overheating during continuous operation. Th</p><p>　　Fig. 1. The control circui

13、t used for driving each DC motor. Note that the PWM signal was between 0 and 5 V.</p><p>　　2.3. Microcontroller</p><p>　　Computation was handled by an Arduino Duemilanove board with an ATmega328

14、 microcontroller. The board has low power requirements and modifications. In addition, it has a large number of prototyping of the control circuit and based on the Wiring language. This board provided an easy and low-cos

15、t platform to build the robot around.</p><p>　　3. FUZZY CONTROL SCHEME FOR</p><p>　　In order to apply fuzzy logic to the robot to interpret measured distances. While the final algorithm depended

16、 critically on the geometry of the robot itself and how it operates, some basic guidelines were followed. Similar research projects provided both simulation results and ideas for implementing fuzzy control.3,4,5</p>

17、;<p>　　3.1. Membership functions</p><p>　　Three sets of membership functions were created to express degrees of membership for distances, translational speeds, and rotational speeds. This made for a t

18、otal of two input membership functions and eight output membership functions (Fig. 2). Triangle and trapezoidal functions were used exclusively since they are quick to compute and easy to modify. Keeping computation time

19、 to a minimum was essential so that many sets of data could be analyzed every second (approximately one every 40 milliseco</p><p>　　3.2.Rule base</p><p>　　Once the input data was fuzzified, the

20、eight defined fuzzy logic rules (Table I) were executed in order to assign fuzzy values for translational speed and rotation. This resulted in multiple values for the each of the fuzzy output components. It was then nece

21、ssary to take the maximum of these values as the fuzzy value for each component. Finally, these fuzzy output values were "defuzzified" using the max-product technique and the result was used to update each of t

22、he motor speeds.</p><p><b>　　(a)</b></p><p><b>　　(b)</b></p><p><b>　　(c)</b></p><p>　　Fig. 2. The membership functions used for (a)

23、distance, (b) translation speed, and (c) rotational speed. These functions were adapted from similar work done in reference 3.</p><p>　　4. RESULTS</p><p>　　The fuzzy control scheme allowed for t

24、he robot to quickly respond to obstacles it could detect in its environment. This allowed it to follow walls and bend around corners decently without hitting any obstacles. However, since the IR sensors' measurements

25、 depended on the geometry of surrounding objects, there were times when the robot could not detect obstacles. For example, when the IR beam hit a surface with oblique incidence, it would reflect away from the sensor and

26、not register as an object.</p><p>　　exactly how many rules should be used. However, for the purposes of testing fuzzy logic as a navigational aide, the eight rules were sufficient. Despite the many problems

27、that IR and similar ultrasonic sensors have with reliably obtaining distances, the robustness of fuzzy logic was frequently able to prevent the robot from running into obstacles.</p><p>　　5. CONCLUSION</p

28、><p>　　There are several easy improvements that could be made to future iterations of this project in order to improve the robot's performance. The most dramatic would be to implement the IR or ultrasonic s

29、ensors on a servo so that they could each scan a full 180 degrees. However, this type of overhaul may undermine some of fuzzy logic's helpful simplicity. Another helpful tactic would be to use a few types of sensors

30、so that data could be taken at multiple ranges. The IR sensors used in this experimen</p><p>　　Thus, this project has successfully implemented a simple fuzzy control scheme for adjusting the heading and spee

31、d of a mobile robot. While it is difficult to determine whether this is a worthwhile application without heavily researching other methods, it is quite apparent that fuzzy logic affords a certain level of simplicity in t

32、he design of a system. Furthermore, it is a novel approach to dealing with high levels of uncertainty in real-world environments.</p><p>　　6. REFERENCES</p><p>　　1 Ed. M. Jamshidi, N. Vadiee, an

33、d T. Ross, Fuzzy logic and control: software and hardware applications, (Prentice Hall: Englewood Cliffs, NJ) 292-328.</p><p>　　2 Ibid, 232-261.</p><p>　　3 W. L. Xu, S. K. Tso, and Y. H. Fung, &

34、quot;Fuzzy reactive control of a mobile robot incorporating a real/virtual target switching strategy," Robotics and Autonomous Systems, 23(3), 171-186 (1998).</p><p>　　4 V. Peri and D. Simon, “Fuzzy log

35、ic control for an autonomous robot,” 2005 Annual Meeting of the North American Fuzzy Information Processing Society, 337-342 (2005).</p><p>　　5 A. Martinez, E. Tunstel, and M. Jamshidi, "Fuzzy-logic bas

36、ed collision-avoidance for a mobile robot," Robotica, 12(6) 521–527 (1994).</p><p>　　6 W. L. Xu, S. K. Tso, and Y. H. Fung, "Fuzzy reactive control of a mobile robot incorporating a real/virtual ta

37、rget switching strategy," Robotics and Autonomous Systems, 23(3), 171-186 (1998).</p><p>　　采用模糊邏輯控制使1自主機器人避障設(shè)計</p><p>　　William Martin 威廉馬丁</p><p>　　Submitted on December 4, 2

38、009 提交于2009年12月4日</p><p>　　CS311 - Final Project CS311 -最終設(shè)計</p><p>　　1、INTRODUC引言 </p><p>　　其中一個很大的障礙需要克服，當試圖用控制邏輯一階來描述一個真實世界設(shè)計在發(fā)現(xiàn)在這兩個語義evaluations.評價中control scheme with first-ord

39、er logic, is the strong ambiguity found in both semantics and設(shè)計設(shè)計設(shè)計是個強大的模糊區(qū)。Although one option is to utilize probability theory in order to come up with a mo雖然一個方案是利用概率論，以便得到一個更realistic model, this still relies on obta

40、ining information about an agent's environment with some現(xiàn)實的模型，這種獲得信息的方法的精度仍然依賴于外部環(huán)境amount of precision.。然而，在其收集data by allowing for a level of tolerance.數(shù)據(jù)的公差允許的范圍內(nèi),模糊邏輯允許利用不精確的間接方法來實現(xiàn)。在需要高精度o</p><p>　　2

41、、機器人具體實現(xiàn) </p><p>　　2.1 底盤和傳感器 </p><p>　　機器人汽車的底盤由Excalibur MSD2003遠程控制玩具坦克構(gòu)成。該裝置去除了所有電子，齒輪和其他多余的部分，只留下了個空架和兩個帶動坦克履帶的直流電動機。然而，這使得它的表面有些不平滑，所以用高密度聚乙烯（HDPE）棒來填補空白處。由于高密度聚乙烯具有較低的表面能，當與其他材料粘接時它并不理想，所

42、以用一丙烷棒與環(huán)氧粘合劑來提高表面溫度，提高易焊接能力。</p><p>　　三夏普GP2D12紅外傳感器用于測量距離，其測量范圍是10至80厘米，分別。為了更好安裝，將一塊2.5*15厘米鋁被彎曲成3個135度角的小塊。用戶既可以將紅外傳感器采取三種（右，中，左）不同的測量距離分別是45度角。這種傳感器通過安裝帶和高密度聚乙烯棒安裝到坦克的底部。由于可靠地最小測量距離是10厘米，傳感器放置在距離小車前面約9厘米

43、處。這使得測量點非常接近機器人的前面。</p><p><b>　　2.2 電子器件</b></p><p>　　為了控制電機的速度，脈沖寬度調(diào)制（PWM）用來驅(qū)動兩個L2722運算放大器以使其工作在開環(huán)模式（圖1）。IC的高輸入電阻使馬達從供電的PWM電路中得到非常小功率。為了使電機的供電與其他器件的供電相分開，專門一個9.6 V鎳鎘電池為電機供電，而其余的電子器件

44、用一個標準的9伏的電源供電。這樣運算放大器在持續(xù)工作時就產(chǎn)生了很少的過熱。這部分熱通過一個小熱槽和一個散熱風扇使其保持平衡。</p><p>　　圖1.控制電路用于驅(qū)動每個直流電動機</p><p>　　注：PWM信號電壓在 between 0 and 5 V.0至5V之間。 </p><p><b>　　2.3 微控制器 </b></p

45、><p>　　計算是由Arduino Duemilanove板和ATmega328微控制器完成的。該電路板具有低功耗和支持原始PWM信號的特點。此外，它還有一個適應(yīng)快速變化的輸入端。Arduino的編程語言具有C語言的形式。這個電路板提供了簡易低成本的機器人開發(fā)電路。</p><p>　　3、避障的模糊控制方案 </p><p>　　為了將模糊邏輯應(yīng)用于機器人運作，而開

46、發(fā)了一個詮釋測量距離的設(shè)計。雖然最終的算法在很大程度上取決于該機器人本身以及它如何運作，但還是要遵循一些基本準則的。類似的研究項目既提供模擬結(jié)果及模糊控制的執(zhí)行方法[3-5]。</p><p><b>　　3.1 附屬功能 </b></p><p>　　由此引出了三種附屬功能,它們分別是測量距離，平移速度和旋轉(zhuǎn)速度。他們由2各輸入隸屬函數(shù)和8個輸出隸屬函數(shù)（圖2）組成

47、。三角形和梯形函數(shù)是專用的，因為它們計算速度快，易于修改。保持計算時間到最低限度是必要的，以便多組數(shù)據(jù)每秒（大約每40毫秒/個）都可以得到分析。距離隸屬函數(shù)可以使來自距離紅外傳感器的距離信息迅速“模糊化”，而8速模糊值函數(shù)將其轉(zhuǎn)換回準確的數(shù)值。 </p><p><b>　　3.2 基本規(guī)則</b></p><p>　　一旦輸入數(shù)據(jù)模糊化，模糊邏輯定義的8個規(guī)則（表一

48、）就被執(zhí)行，以便將模糊值分配給平移速度和旋轉(zhuǎn)速度。這導(dǎo)致每個組件的模糊輸出有多個值。因此有必要采用每個組件的最大值作為模糊值。最后，通過最大輸出技術(shù)將這些模糊輸出值“解模糊”，其結(jié)果是用來更新每個馬達的速度。 </p><p><b>　　(一)</b></p><p><b>　?。ǘ?lt;/b></p><p><

49、b>　?。ㄈ?lt;/b></p><p><b>　　(c) </b></p><p><b>　　圖2 </b></p><p>　　圖2.附屬函數(shù)分別用來測量（一）距離，（二）翻譯速度，以及（三）轉(zhuǎn)動速度。這些函數(shù)從參考文獻3類似的內(nèi)容中借鑒而來。 </p><p>　　表1 用

50、于控制的模糊邏輯規(guī)則庫 </p><p><b>　　4、結(jié)果 </b></p><p>　　該設(shè)計使模糊控制的機器人能夠迅速回應(yīng)檢測到的障礙。這使得它能沿著墻壁和角落行動而不會撞擊到任何障礙物。然而，由于紅外傳感器的尺寸取決于周圍物體幾何形狀，很多時候機器人也無法檢測到障礙物。例如，當紅外線光束擊中地面的傾斜處事，則反映出遠離傳感器和不認為是一個障礙對象。此外，使用

51、有限數(shù)量的規(guī)則可能限制機器人的一些反應(yīng)。有些文章建議多達40條規(guī)則應(yīng)加以使用，而另一些傾向于10和20條之間[6]。由于該項目不探索復(fù)雜的機器人運動學或模擬計算，以至于它是難以確定到底有多少規(guī)則應(yīng)該被使用。但是，作為一個模糊邏輯的宗旨測試導(dǎo)航助手，八個規(guī)則就足夠了。盡管有許多相似的問題，IR和超聲波傳感器的距離有可靠地獲取途徑，魯棒性模糊邏輯通常是能夠能防止機器人跑向障礙物。</p><p><b>　

52、　5、 結(jié)論 </b></p><p>　　這有幾個簡單的改進方法可以借鑒到未來的迭代項目中以提高機器人的性能。最引人注目的將是實現(xiàn)紅外線或超聲波傳感器在伺服使他們能夠每次掃描一個完整的180度。然而，這種類型的改革可能會破壞一些模糊邏輯的簡化。另一個有用策略是使用一些不同的傳感器，使數(shù)據(jù)獲取多元化。該紅外傳感器在設(shè)計中使用的是最小測量距離為10厘米的，所以很多障礙在前面無法可靠地檢測到。同樣，最大測

53、量距離是80厘米的傳感器也是對遠處的物體很難作出反應(yīng)。超聲波傳感器在稍微增加成本和反應(yīng)時間的同時，可以有效增大測量范圍。最后，定義更多附屬函數(shù)可以改善機器人的反應(yīng)能力。但是，這樣做將再次增加系統(tǒng)的復(fù)雜性。</p><p>　　因此，一個簡單的模糊控制機器人的移動方向和移動速度的方案，通過本設(shè)計成功的實現(xiàn)了。在沒有經(jīng)過大量的其他方法的研究時，很難確定這是否是一個值得的方法這是很明顯，但是模糊邏輯系統(tǒng)的設(shè)計，提供了一

54、種對某些層面的簡單化研究的方法。此外，它是一個處理環(huán)境中各種實際不確定性的新方法。</p><p><b>　　6. </b></p><p><b>　　參考文獻 </b></p><p>　　[1] Ed. 埃德·米賈姆希迪，注Vadiee，并噸羅斯和控制，模糊邏輯：軟件和硬件應(yīng)用，（普倫蒂斯霍爾：黃俊英，新

55、澤西州）292-328。 </p><p>　　[2] Ibid, 232-261. 同上，232-261。 </p><p>　　[3] WL Xu, SK Tso, and YH Fung, "Fuzzy reactive control of a mobile robot incorporating a 輪候冊許，水庫草，和YH豐，“模糊控制結(jié)合被動移動機器人真實/虛擬目標

56、轉(zhuǎn)換“戰(zhàn)略，機器人和自主系統(tǒng)，23（3），171-186 (1998).（1998年）。 </p><p>　　[4] V. Peri and D. Simon, “Fuzzy logic control for an autonomous robot,” 2005 Annual Meeting of 五圍和D.西蒙，“模糊邏輯控制的自主機器人為”2005年年度會議北美模糊信息處理學會，337-342（2005）

57、。 </p><p>　　[5] A. Martinez, E. Tunstel, and M. Jamshidi, "Fuzzy-logic based collision-avoidance for a mobile 答：馬丁內(nèi)茲，大腸桿菌Tunstel和M.賈姆希迪，“模糊邏輯基礎(chǔ)的防撞為移動機器人“Robotica，12（6）521-527（1994）。 </p><p>