30。 2227 Drake  Ax'enue。  SW。  Huntsville。  AL  E-stop。  mode,  which  is  initiated,  conven- 35805。 Clyde S。 Jones,  III,  is with NASA  Mar-  tioflally。 by  depressing a large button。  If  an shall Space Flig•ht Center, AL 35812。operator inadvertently  finds himself  in a haz-

values is often  necessary  due to conditions

changing during the weld。 A human making a manual weld accomplishes this adjustment

027 2-1 708。’8 7。'0600-00 1 6  $0 1 。 00    '   1 987  IEEE

readily, while a robot must rely on the lim- ited talents of sensors and the ability of the operator to override functions when neces- sary。

System Integration

The basic elements of the workcell system are shown diagrammatically in the illustra- tion。 The ultimate goal of the system devel- opment work in progress is to generate robot manipulator programs and weld process pro- grams off line, download them to the work- cell supervisory computer, then use sensor subsystems to make closed-loop corrections to the robot path and process variables。 Off- line programming is being done with an In- tergraph modified VAX 780/785-205 com- puter system with Interact color graphics workstations。  Deviations  between  the pro-

Crammed robot path and the actual required path are observed and corrected by a so- phisticated vision-based sensor developed for this application by Ohio State University。 This sensor system is also designed to permit measurement of the molten weld pool sur- face dimensions and correct welding current level to maintain the weld pool dimensions within desired limits。 Presently, a number of functions are still controlled manually, and manual override capability is required for all functions。 As stated in the Introduction。 use of voice reco¿;nition may improve the ac- curacy and speed of response of these man- ual overrides。 To explore this technology, a Votan VRT 6050 stand-alone voice recog- nition terminal has been inte;;rated into the workcell。 This system provides continuous speech recognition of up to 10 sets of words with 75—150 words per set。

The integration of the voice recognition system is broken into analog and discrete signals for control。 The voice recognition system connects to the control computer through a standard RS232-C communica- tions link。

In this project, most of the control cir- cuitry is based on discrete digital signals。 This is due to the on/off state nature of the circuits to be controlled in the robot con- troller。 The circuits of the system to be con- trolled by the voice recognition control com- puter (VRCC) by discrete si;;nals are the emergency stop circuit and the positive jog and negative jog circuits for motion control。 Since the safety of the operator is para- mount in any automated workcell, the voice recognition system should be incorporated as

本文论述了使用声音识别技术的焊接机器人工作单元在工作过程中的效果、程序编辑者接近机器人的安全﹑试行运转的必要性﹑焊接过程的控制变量﹑机器人操作者的动作规范等因素给与考虑。在焊接过程控制和操作动作两个方面，按照反应速度﹑定位精确性﹑焊接稳定性﹑焊接可靠性和安全性把人工声音控制与手工触觉控制和完全自动化控制进行了比较。

引言

声音识别技术已经成为可能缓解操作者工作负担的一种有潜力的复杂系统。许多应用已经落实,或正陆续开发,或正在研究之中。这些措施包括数据的输入﹑飞机的控制﹑和以安全为目的的语音识别。

许多应用语音控制技术还建议用于太空站。 一个主要的应用领域将机器人控制功能用于太空舱内检查、装配、维修、卫星回收、维修卫星,是在船上服务的监督能力和系统运作模式的反馈。 声音感应器和过程控制的变数将使船员影响他手上的其它工作,例如直接控制或推翻的操纵议案。 同样,利用工作量控制机载实验这种技术可以缓解许多工作负担。论文网