机器人模糊避障外文翻译

1、Autonomous robot obstacle avoidance using a fuzzy logic control schemeWilliam MartinSubmitted on December 4, 2009 CS311 - Final ProjectINTRODUCTIONOne of the considerable hurdles to overcome, when trying to describe a real-world control scheme with first-order logic, is the strong ambiguity found in

2、 both semantics and evaluations. Although one option is to utilize probability theory in order to come up with a more realistic model, this still relies on obtaining information about an agents environment with some amount of precision. However, fuzzy logic allows an agent to exploit inexactness in

3、its collected data by allowing for a level of tolerance. This can be especially important when high precision or accuracy in a measurement is quite costly. For example, ultrasonic and infrared range sensors allow for fast and cost effective distance measurements with varying uncertainty. The propose

4、d applications for fuzzy logic range from controlling robotic hands with six degrees of freedom1 to filtering noise from a digital signal.2 Due to its easy implementation, fuzzy logic control has been popular for industrial applications when advanced differential equations become either computationa

5、lly expensive or offer no known solution. This project is an attempt to take advantage of these fuzzy logic simplifications in order to implement simple obstacle avoidance for a mobile robot.PHYSICAL ROBOT IMPLEMENTATIONChassis and sensorsThe robotic vehicles chassis was constructed from an Excalibu

6、r EI-MSD2003 remote control toy tank. 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-density polyethylene (HDPE) rods were used t

7、o fill in empty spaces. Since HDPE has a rather low surface energy, which is not ideal for bonding with other materials, a propane torch was used to raise surface temperature and improve bonding with an epoxy adhesive.Three Sharp GP2D12 infrared sensors, which have a range of 10 to 80 cm, were used

8、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. This allows for the IR sensors to take three different measurements at 45 degree angles (right, middle, and left distances). This sensor mount was

9、then attached to an HDPE rod with mounting tape and the rod was glued to the tank base with epoxy. Since the minimum distance that can be reliably measured with these sensors is 10 cm, the sensors were placed about 9 cm from the front of the vehicle. This allowed measurements to be taken very close

10、to the front of the robot.ElectronicsIn order to control the speed of each motor, pulse-width modulation (PWM) was used to drive two L2722 op amps in 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.

11、 In order to isolate the motors power supply from the rest of the 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. This was remedied by adding small heat sinks and a fan to the forc

12、ibly disperse heat.Fig. 1. The control circuit used for driving each DC motor. Note that the PWM signal was between 0 and 5 V.MicrocontrollerComputation was handled by an Arduino Duemilanove board with an ATmega328 microcontroller. The board has low power requirements and modifications. In addition,

13、 it has a large number of prototyping of the control circuit and based on the Wiring language. This board provided an easy and low-cost platform to build the robot around.FUZZY CONTROL SCHEME FORIn order to apply fuzzy logic to the robot to interpret measured distances. While the final algorithm dep

14、ended 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 3.1. Membership functionsThree sets of membership functions were created to express

15、 degrees of membership for distances, translational speeds, and rotational speeds. This made for a total 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. Keep

16、ing computation time to a minimum was essential so that many sets of data could be analyzed every second (approximately one every 40 milliseconds). The distance membership functions allowed the distances from the IR sensors to be quickly fuzzified, while the eight speed membership functions converte

17、d fuzzy values back into crisp values.3.2.Rule baseOnce the input data was fuzzified, the 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

18、 then necessary 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 the motor speeds.(a)(b)(c)Fig. 2. The membership functions used for (a) distance, (

19、b) translation speed, and (c) rotational speed. These functions were adapted from similar work done in reference 3.Tjblc . Thu fuzzy logic rule base used for the conliol sclierneKuleLeCcineiKijilnSpeedRolalik*j1NeacNearNearSlowRight big7NearFaiMediumRight small3Near1 arNearSlowMo nirn二NeacFarParFast

20、Right simll5RwNearNearMediumLdi MlKlUh-LirNear1 arSlowRighl Ng7KaiNearFastLcll small8FurFillFarFastNo (urnRESULTSThe fuzzy control scheme allowed for the robot to quickly respond to obstacles it could detect in its environment. This allowed it to follow walls and bend around corners decently without

21、 hitting any obstacles. However, since the IR sensors measurements 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 not register a

22、s an object. In addition, the limited number of rules used may have limited the dynamics of the robots responses. Some articles suggest as many as forty rules6 should be used, while others tend to present between ten and twenty. Since this project did not explore complex kinematics or computational

23、simulations of the robot, it is difficult to determineexactly 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 that IR and similar ultrasonic sensors have with reliably obtaining distanc

24、es, the robustness of fuzzy logic was frequently able to prevent the robot from running into obstacles.CONCLUSIONThere are several easy improvements that could be made to future iterations of this project in order to improve the robots performance. The most dramatic would be to implement the IR or u

25、ltrasonic sensors on a servo so that they could each scan a full 180 degrees. However, this type of overhaul may undermine some of fuzzy logics helpful simplicity. Another helpful tactic would be to use a few types of sensors so that data could be taken at multiple ranges. The IR sensors used in thi

26、s experiment had a minimum distance of 10 cm, so anything in front of this could not be reliably detected. Similarly, the sensors had a maximum distance of 80 cm so it was difficult to react to objects far away. Ultrasonic sensors do offer significantly increased ranges at a slightly increased cost

27、and response time. Lastly, defining more membership functions could help improve the rule base by creating more fine tuned responses. However, this would again increase the complexity of the system.Thus, this project has successfully implemented a simple fuzzy control scheme for adjusting the headin

28、g and speed 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 the design of a system. Furthermore, it is a novel approach to dealing

29、with high levels of uncertainty in real-world environments.REFERENCESEd. M. Jamshidi, N. Vadiee, and T. Ross, Fuzzy logic and control: software and hardware applications, (Prentice Hall: Englewood Cliffs, NJ) 292-328.Ibid, 232-261.W. L. Xu, S. K. Tso, and Y. H. Fung, Fuzzy reactive control of a mobi

30、le robot incorporating a real/virtual target switching strategy, Robotics and Autonomous Systems, 23(3), 171-186 (1998).V. Peri and D. Simon, “Fuzzy logic control for an autonomous robot,” 2005 Annual Meeting of the North American Fuzzy Information Processing Society, 337-342 (2005).A. Martinez, E.

31、Tunstel, and M. Jamshidi, Fuzzy-logic based collision-avoidance for a mobile robot, Robotica, 12(6) 521-527 (1994).W. L. Xu, S. K. Tso, and Y. H. Fung, Fuzzy reactive control of a mobile robot incorporating a real/virtual target switching strategy, Robotics and AutonomousSystems, 23(3), 171-186 (199

32、8).采用模糊逻辑控制使自主机器人避障设计威廉马丁提交于2009年12月4日CS311 -最终项目1弓|言其中一个很大的障碍需要克服，当试图用控制逻辑一阶来描述一个真实世 界设计在发现在这两个语义评价中是个强大的模糊区。虽然一个方案是利用概率 论，以便得到一个更现实的模型，这种获得信息的方法的精度仍然依赖于外部环 境。然而，在其收集数据的公差允许的范围内，模糊逻辑允许利用不精确的间接 方法来实现。在需要高精度测量时它是相当昂贵的。例如，超声波和红外线传感 器在其距离内允许快速和有效的测量但其测量结果存在很大的不确定性。模糊逻 辑控制的应用范围从利用六自由度1控制机器人手臂到从数字信号中过滤噪

33、音。由于其易于实现，模糊逻辑控制一直流行在工业应用中，尤其是高级微分方 程计算复杂或难以解决时。这个项目企图利用简化模糊逻辑，以实现移动机器人 的简单避障。2机器人具体实现2.1底盘和传感器机器人汽车的底盘由Excalibur MSD2003远程控制玩具坦克构成。该装置去 除了所有电子，齿轮和其他多余的部分，只留下了个空架和两个带动坦克履带的 直流电动机。然而，这使得它的表面有些不平滑，所以用高密度聚乙烯（HDPE） 棒来填补空白处。由于高密度聚乙烯具有较低的表面能，当与其他材料粘接时它 并不理想，所以用一丙烷棒与环氧粘合剂来提高表面温度，提高易焊接能力。三夏普GP2D12红外传感器用于测量距

34、离，其测量范围是10至80厘米，分 别。为了更好安装，将一块2.5*15厘米铝被弯曲成3个135度角的小块。用户 既可以将红外传感器采取三种（右，中，左）不同的测量距离分别是45度角。 这种传感器通过安装带和高密度聚乙烯棒安装到坦克的底部。由于可靠地最小测 量距离是10厘米，传感器放置在距离小车前面约9厘米处。这使得测量点非常 接近机器人的前面。2.2电子器件为了控制电机的速度，脉冲宽度调制（PWM）用来驱动两个L2722运算放大 器以使其工作在开环模式（图1）。IC的高输入电阻使马达从供电的PWM电路中 得到非常小功率。为了使电机的供电与其他器件的供电相分开，专门一个9.6 V 竦镉电池为电

35、机供电，而其余的电子器件用一个标准的9伏的电源供电。这样运 算放大器在持续工作时就产生了很少的过热。这部分热通过一个小热槽和一个散 热风扇使其保持平衡。图1.控制电路用于驱动每个直流电动机注：PWM信号电压在0至5V之间。2.3微控制器计算是由Arduino Duemilanove板和ATmega328微控制器完成的。该电路 板具有低功耗和支持原始PWM信号的特点。此外，它还有一个适应快速变化的输 入端。Arduino的编程语言具有C语言的形式。这个电路板提供了简易低成本的 机器人开发电路。3避障的模糊控制方案为了将模糊逻辑应用于机器人运作，而开发了一个诠释测量距离的设计。 虽然最终的算法在很

36、大程度上取决于该机器人本身以及它如何运作，但还是要遵 循一些基本准则的。类似的研究项目既提供模拟结果及模糊控制的执行方法。 3,4,53.1附属功能由此引出了三种附属功能，它们分别是测量距离，平移速度和旋转速度。 他们由2各输入隶属函数和8个输出隶属函数（图2）组成。三角形和梯形函数 是专用的，因为它们计算速度快，易于修改。保持计算时间到最低限度是必要的， 以便多组数据每秒（大约每40毫秒/个）都可以得到分析。距离隶属函数可以使 来自距离红外传感器的距离信息迅速“模糊化”，而8速模糊值函数将其转换回 准确的数值。3.2基本规则一旦输入数据模糊化，模糊逻辑定义的8个规则（表一）就被执行，以便 将

37、模糊值分配给平移速度和旋转速度。这导致每个组件的模糊输出有多个值。 因此有必要采用每个组件的最大值作为模糊值。最后，通过最大输出技术将这些 模糊输出值“解模糊”，其结果是用来更新每个马达的速度。（一）表1用于控制的模糊逻辑规则库Tjblc . Thu fuzzy logic rule base used for the conliol sclierneKuli?LeCcineiKijilnSpeedRolalik*j1NeacNearNearSlowRight big7NearFaiMediumRight small3Near1 arNearSlowMo nirn二NeacKirParFastRight s