外文翻譯---使用語音識別技術控制的焊接機器人工作單元 英文

1、Use of Voice Recognition for Control of a Robotic Welding Workcell J. Kevin Watson, Douglas M. Todd, and Clyde S. Jones, 111 ABSTRACT: This paper describes work un- derway to evaluate the effectiveness of voice re

2、cognition systems as an element in the control of a robotic welding workcell. Fac- tors being considered for control include program editor access security. preoperation checklist requirements, welding process varia

3、ble control. and robot manipulator mo- tion overrides. In the latter two categories, manual vocal control is being compared against manual tactile control and fully au- tomatic control in terms of speed of re- spons

4、e, accuracy, stability, reliability. and safety. Introduction Voice recognition technology is now rec- ognized as a potential means for easing the workload of operators of complex systems [ 11. Numerous applications

5、 have already been implemented, are in various stages of development, or are under consideration [2]- [5]. These include data entry. control of air- craft systems, and voice identification and verification for secu

6、rity purposes. Voice control has also been proposed for use aboard the space station [6]-[8]. One prime area for application would be control of some functions of robots used for intra- and extravehicular inspectio

7、n. assembly, re- pair, satellite retrieval, and satellite mainte- nance when a crewmember is serving in a supervisory capacity or the system is oper- ating in a teleoperation mode. Voice control of sensors and proce

8、ss variables would free the crewmember’s hands for other tasks, such as direct control or ovemde of the manipu- lator motion. Similarly. the workload asso- ciated with control of many onboard exper- iments could be

9、eased through the use of this technology. This paper describes the application of voice recognition for control of a robotic Presented at the 1986 IEEE International Confer- ence on Systems. Man, and Cybernetics, h

10、eld in Atlanta, Georgia. October 14-17. 1986. J. Kevin Watson and Douglas M. Todd are with the Rock- etdyne Division of Rockwell International. Suite 3 0 .2227 Drake Avenue, SW. Huntsville. AL 35805. Clyde S. Jone

11、s, UI, is with NASA Mar- shall Space Flight Center, AL 35812. 16 welding workcell. This is a complex system involving inputs from multiple sensors and control of a wide variety of robot manipu- lator motions and pr

12、ocess variables. While many functions are automated. a human op- erator serves in a supervisory capacity. ready to ovemde functions wjhen necessary. In the present investigation. a commercially avail- able voice r

13、ecognition system is being inte- grated with a robotic welding workcell at NASA Marshall Space Flight Center, which is used as a test bed for evaluation and de- velopment of advanced technologies for use in fabrica

14、tion of the Space Shuttle Main En- gine. In the system under development, some functions do not yet have automatic closed- loop control. thus requiring continuous mon- itoring and real-time adjustment by the hu- man

15、 operator. Presently, these ovemdes are input to the system through tactile com- mands (;.e.. pushing buttons. turning knobs for potentiometers, or adjusting mechanical devices). Since the operator monitors the proc

16、ess primarily visually, he must either look away from the process to find the proper button or knob or rely on “muscular mem- ory” much as a touch-typist does. In the first case, the time of response to a deviant con

17、- dition may be excessive. In the second case. there is an increased probability of a sec- ondary e m r being introduced by the oper- ator. A voice recognition system could reduce the response time required from

18、the operator. The probability of pushing the wrong button should similarly be reduced. Also, operator fatigue should be minimized. Since the operator can continuously mon- itor the process during ovemde input, the

19、effect of the change can be observed more quickly. Thus. if the desired value is ex- ceeded and reverse correction is required, it should be accomplished more quickly, al- lowing less overshoot. This reduction in os-

20、 cillation about the desired value makes the system more stable. Another factor that can be improved is op- erator safety. In a safety-critical situation, the robot’s operation can be halted imme- diately by use of

21、 the “emergency stop,’’ or E-stop. mode, which is initiated, conven- tionally. by depressing a large button. If an operator inadvertently finds himself in a haz- C272-1708:87!0600-0016 $01 00 1987 IEEE ardous situati

22、on, it may be necessary for him to initiate the E-stop sequence. Should the operator not be within reach of the button, however, he may be unable to take the nec- essary action, and, as a result. could suffer ser

23、ious injury. Having the capability of stop- ping the robot by issuing a voice command could significantly improve the operator’s safety by enabling him to stop the robot even when not within reach of the E-stop butto

24、n. Manual corrections are occasionally re- quired to adjust the location at which the weld filler wire enters the weld pool. Proper entry location is absolutely critical to sound weld quality. Adjustments are made e

25、ither by manually adjusting mechanisms that hold the wirefeed guide tube or by issuing tactile commands to a servomechanism. Use of a voice recognition system could eliminate the need for the operator to place his h

26、and within the working envelope of the robot end effec- tor or. if servomechanisms are employed, could improve speed of response and stabil- ity. Another aspect of robot operation in an industrial environment that

27、is very important is the security of a program editing capability of the system. Under no circumstances should any unauthorized person be able to enter this programming mode and alter the robot’s program. A voice r

28、ecognition system can provide the necessary security by allow- ing access only for individuals who are au- thorized and whose voices can be identified by the system. Background Robotic welding is under development by

29、 NASA and Rocketdyne for the automation of welds on the Space Shuttle Main Engine that are presently made manually. The pro- grammability of a robot can reduce the per- centage of welding defects through a com- bin

30、ation of consistency and repeatability unattainable by its human counterparts. To do this, the robot is programmed to a nom- inal weld path and level of weld process pa- rameters (i.e., current, travel speed. voltag

31、e, wire addition rate). Some adjustment of these values is often necessary due to conditions changing during the weld. A human making a manual weld accomplishes this adjustment I€€€ Control Sysierns Mogozme a safety

32、 feature. To accomplish this, the VRCC has been interfaced into the workcell emergency stop circuit. The emergency stop circuit in the robotic workcell will shut down the welding process and the mechanical mo- tion

33、 of the manipulators. Through the use of a digital signal from the VRCC, a relay is energized that interrupts the necessary cir- . cuits in the weld power supply and robot controller. With the use of the voice recog-

34、 nition system as a safety control for this workcell, we have added a third level of re- dundancy into the emergency stopping abil- ity of the operator (in addition to the present emergency stop buttons). Manipulat

35、or motions are controlled through an axis select button in conjunction with a positive or negative jog button that is depressed by the operator. Once the operator has selected an axis, he depresses one of the

36、jog buttons for the desired travel distance. This function was selected to be controlled by the VRCC because of its utilization dur- ing automatic operation of the manipulator to correct trajectory errors. The circu

37、itry necessary to control this operation draws the signal to ground through the activation of relays for the positive or negative jog mo- tion. Because motion is achieved only as long as these signals are active low

38、. they can be controlled by discrete digital signals from the VRCC. Analog Control Signals There are many variables that affect the quality of weld during the welding process. but the welding current has the greatest

39、 effect over a small range of values. It was for this reason, that the welding current was chosen to be controlled by the voice recognition sys- tem. The welding power supply controls the current level through a

40、voltage circuit that uses a range of 0-10 V DC. These voltage values are converted to current levels from 0 to 300 A for welding. A digital-to-analog converter is used in conjunction with a mul- tiplying circuit.

41、The converter allows the VRCC to control a voltage level that is used by the weld power supply to achieve the proper welding current. The multiplier cir- cuit is necessary to allow the weld power supply to be cont

42、rolled by the other subcon- troller used in the workcell. Experimental Investigation The accuracy and speed of response of corrections to robot manipulator motion and welding process variables made with the VRCC are

43、being compared with those made with the original control system. Step input emrs to robot motion and welding current are introduced randomly into the robot pro- gram. By graphically recording relevant sys- tem output

44、 signals. the time required for the operator to detect the change and initiate cor- rective action may be measured. Response accuracy and stability may also be gaged through similar analysis of the relevant re- cord

45、ed system output signals. Conclusions Future work will investigate voice control of welding filler wirefeed speed and location of wire entry into the weld pool. Also to be investigated is voice control of welding arc

46、 voltage override. Later, restriction of access to the robot program editor by voice recog- nition may be implemented. The use of voice recognition technology for manual supervisory control of industrial robot syst

47、ems is very promising. This tech- nology has application for aerospace welding due to the need to have constant human su- pervision over a multitude of process param- eters in real time. Future development of this

48、 technology will permit rapid expansion of its application to both robotic and nonrobotic processes. Acknowledgment Special thanks to Mr. Jeff Hudson of Mar- tin Marietta Corporation for assistance in the preparatio

49、n of the illustration presented in this article. References [I] C. A . Simpson. hl. E. McCauley. E. F. Rol- land. J . C. Ruth. and B. H. Williges. “Sys- tem Design for Speech Recognition and Gen- eration.“ Hutnnn F

50、actors. vol. 27. no. 2. pp. 115-1-11. 1985. [2] National Research Council. Committee on Computerized Speech Recognition Technol- ogies. Automatic Speech Rerop1irior1 in Se- \*ere E~trironntenrs. National Research C

51、oun- cil. 1984. and Computer,“ Quali8. pp. 16-17. Oct. 3985. [4] E. J. Lerner. “Talking to Your Aircraft.“ Aerospace America. vol. 24. no. 2. pp. 85- 88. 1986. [SI J. T. Memlield. “Bosing Explores Voice Recognitio

52、n for Future Transpon Flight Deck.“ Ariarinn Week and Space Techno/- og!. vol. 124. no. 16. pp. 85-91. 1986. [6] A. Cohen and J. D. Erickson, ..Future Uses of Machine Intelligence and Robotics for the Space Station an

53、d Implications for the U.S. Economy.'' IEEE J . Robotics and Automa- rion. vol. SMC-16. pp. 1 11-12 I. Jan.iFeb. 1986. 131 T. Woo. “Voice: The Link Between Man [7] “Automation and Robotics for the National

54、Space Program,“ California Space Institute Automation and Robotics Panel. Cal Space Repon CS1185-01, Feb. 25, 1985. 181 “Advancing Automation and Robotics Tech- nology for the Space Station and for the U.S. Econom

55、y.“ Advanced Technology Advisory Committee. NASA TM 87566. Mar. 1985. J. Kevin Watson re- ceived a B.S. degree in welding engineering f r o mthe Ohio State University in 1979 and an M.S. de- gree in materials engi-

56、 neering from Rensselaer Polytechnic Institute in 1982. In 1979. he joined the Technical Staff of the Rocketdyne Division of Rockwell International, working in the develop- ment of welding. brazing, and diffusion

57、 bonding processes for the Space Shuttle Main Engine (SSME). advanced boosters, and high-energy la- sers. He has been the Manager of Rocketdyne's Marshall Space Flight Center Robotics Support Unit in Huntsville.

58、 Alabama. since 1984. This group is working jointly with SASA to develop adaptive robotic technologies for welding fabri- cation of the SSME. Douglas M. Todd re- ceived a B.S. degree in engineering from the Uni- ve

59、rsity of Illinois at Chi- cago in 1984. He joined the Technical Staff of the Rocketdyne Division of Rockwell International's Robotics Support Unit at NASA's Marshall Space Flight Center in Hunts- ville. A

60、labama. in 1985. He is working in the de- velopment of robotic control systems integration for use in manufacturing of the Space Shuttle Main Engine. Clyde S. Jones, III, re- ceived the B.S. degree in electrical e

61、ngineering from the University of Al- abama in Huntsville in 1978. He worked for the 1- & -3 ~5 Cheder Corporation in ~ -52 development of produc- tion test equipment for electronics manufactur- ing. Sinc

62、e 1981, he has been involved in the de- velopment of aerospace welding automation as a Control Systems Engi- neer for NASA's Materials and Processes Labo- ratoq at the Marshall Space Flight Center. 18 I € € €