The FANUC ARC Mate 100iB Solution arm robot equipped with a vision sensor and the M-170iB robot in a dual-arm configuration.

A robotic arm equipped with FANUC's V-500iA vision sensor for a bin picking application.

Intelligent robots that use vision technology now have the flexibility and functionality to perform tasks that once were thought too difficult or too risky to automate. Advances in vision-system technology have focused on increased recognition of precise parts and greater simplification of programming, setup and use. However, the most significant factor involves cost. Today, costs are typically less than $10,000 for visionsystem hardware that 12 years ago would have cost $30,000 to $40,000.

PC-based vision systems now are interfaced with robots, especially for electromechanical assembly, and they primarily are used for part identification, discrimination, location, orientation, inspection and measurement. Because of the tight tolerances and the need to inspect critical mating parts, vision systems often are required for precision electronics and fiber optics assembly.

Robots are well suited to repetitive tasks, but they are not adept at accommodating changing parameters that involve part position, size or drop-off locations. But a vision system can detect such parameters and guide the robot accordingly. Vision systems also can be used to verify that the correct parts are available to the robot.

Another significant advancement has been in vision-system software. For example, the electronics industry has long used vision systems to detect objects that are, essentially, flat. The software available 12 years ago required consistency, predictable contrasts and textures in parts. Now, robust pattern-matching algorithms tackle three-dimensional objects that have variations in shadows and contrasts. These algorithms address part geometry more than part image. Today, poor lighting, fuzzy images, parallax error, partial occlusion or variations in part qualities pose much less of a problem to vision systems, and this has allowed vision-guided robots to handle a wider range of industrial applications.

Vision systems are also much easier to program today. Some application-specific systems do not require programming, only setup. Programming languages and interfaces of more general-purpose vision systems also have become easier to use, allowing many end users to program their own systems.

Robotic vision systems, long a mainstay of highvolume automotive welding and painting applications, increasingly are used in more general industrial applications because of their greater agility. For instance, an increasing percentage of Fanuc Robotic's general-industrial systems are equipped with vision. Seven years ago, only 1 percent were shipped with vision capabilities. One integrator, who primarily deals with robotics for general-industrial-machining applications, said two years ago that 30 percent of the systems he configures incorporate vision and, at that time, 10 percent of Fanuc Robotic's shipments included vision systems.

In machining or assembly applications, advances in vision software reduce or eliminate the need for gaging tools, fixturing or other part-presentation equipment. For example, a Fanuc Robotics intelligent robot with a three-dimensional (3D) vision sensor and bin-picking software selects randomly oriented parts piled in bins or trays, reducing the need for manual labor, part feeders, positioning jigs and other peripherals. Some applications require an additional, fixed, overhead twodimensional (2D) camera to find the rough location of all parts within its field of view and select a few good candidates for 3D-vision processing. The robot aligns the 3D sensor closely over the parts and the 3D-image-processing function calculates the location and orientation of a chosen part. The application software identifies one part type from another, sorts parts based on special features (such as top surface from bottom surface), picks up partially overlapped parts and automatically recovers from a collision during pickup operations. Vision also determines whether a mating part at the drop-off point is oriented and positioned correctly.

The use of vision and robotics is an important step toward agile manufacturing. Not only is the need for costly dedicated fixtures reduced, but also the process is flexible and quickly accommodates frequent part changeover. Quality control is monitored without the subjectivity of an operator and detailed reports are generated, including dimensional gaging, surface defects and production runs.

Often, robotic systems cannot be justified without a vision component. That is because a robot may be capable of replacing the motions of an operator, but it needs vision to verify that all is well with a process.

The latest robotic innovations concern systems front ended with vision and equipped with force sensors. These units eliminate the drudgery and inaccuracy of manual assembly, and can operate throughout a shift without downtime.

Mr. Roney is manager for vision products & application development at Fanuc Robotics America, Rochester Hills, Mich.