Vision Systems Let Robots See What They Are Doing
Before manufacturers add vision capabilities, they should consider what their systems must contribute to production operations and select technology that fully meets those needs. The post Vision Systems Let Robots See What They Are Doing appeared first on Fabricating & Metalworking.
For nearly a century, manufacturers have developed and applied robotic equipment to boost speed, accuracy and repeatability in a wide variety of tasks. In the last 40 years, vision technology has enabled robots to view a known workspace, detect objects and perform desired actions. Together, the robot, programming software and imaging hardware increase productivity and consistency. Vision systems expand a robot’s range of applications with increased flexibility to handle greater variation in parts and processes.
Basic Vision System Functions
Robotic vision systems provide four basic functions: positioning, inspection, measurement and code reading. The most common is positioning, namely determining an object’s location and reporting it to the robot controller. The controller typically then directs the robot to pick up the object and place it somewhere else. Inspection functions view an object to identify missing or defective features. Users also can program a system to measure an object’s dimensions, area and volume.
Finally, a vision system can decode and read one-dimensional (1D) and two-dimensional (2D) codes to provide optical character recognition (OCR) and verification (OCV). OCR recognizes alphanumeric characters by comparison to a library of character patterns, while OCV verifies that an alphanumeric character is complete.
Levels of Robotic Vision
Introduced in the 1980s and early 1990s, the first commercial robotic vision systems performed 2D part recognition, in which a camera acquires images of objects across X and Y planes. These systems provide two-dimensional feedback to guide basic robotic functions and are most frequently used in simple applications that involve batches of very similar parts in pre-determined locations.
A 2D vision system’s recognition and location capabilities eliminate the need for an operator to handle a part and put it in a fixture. With 2D vision, robots can sort and organize objects. Because of their simplicity and thorough development over time, 2D systems are easy and cost effective to integrate and operate.
2D vision technology works best with strong, contrasting lighting and parts that lay relatively flat with limited overlap, such as in simple automated pick-and-place operations. Variably shaped parts, dim or uneven lighting conditions and advanced handling operations also can challenge the effectiveness of 2D robotic vision systems.
For more-complex tasks, 3D vision uses complex imaging technologies – such as multiple cameras – to detect X and Y part locations as well as Z (height) measurements and angles in all three planes, enabling determination of an object’s shape and volume. A 3D vision system can adapt to overlapped and stacked items in so-called “semi-structured” applications that involve parts at different heights, layers and angles. Applications mainly focus on positioning, measurement and inspection.
The flexibility of 3D vision systems enables them to adapt to changes in a process, operate accurately under poor lighting conditions and fully exploit the capabilities of six-axis robots. These systems recognize parts, determine distances and calculate trajectories in 3D space, enabling a robot to optimize the path on which it moves an object.
These 3D robotic vision systems expand the range of robotic applications beyond simple part location. With integrated 3D cameras, advanced robots can inspect components, construct intricate assemblies and adjust dynamically to varying parts and locations. The sole tradeoff is added complexity and expense. To determine whether an application requires 3D vision or if a 2D setup will meet the needs of a production line, manufacturers can consult with the robot manufacturer or a system integrator to assess the application and plan for the best approach.
Robotic Camera Systems
Depending on what a vision system must accomplish, it uses one of three primary camera placements. Stationary setups mount the camera where it can view the workspace, at the expense of limited operation flexibility. Alternately, a robot-mounted camera provides enhanced flexibility and enables coverage of a large area, but cycle times may increase to allow software to process input from the camera before directing the robot’s next move.
In a third approach, a fixed-mount camera observes the robot as it carries a part, perhaps handling and placing a piece of sheet metal. The robot picks up the part randomly with a suction-cup gripper. The camera then determines the position of the sheet metal on the gripper and software directs the robot to place the part precisely where desired.
Camera Environment and Technology
2D applications must depend on the coverage area of the camera lens and lighting that generates sufficient contrast for clear part identification. Different lighting techniques, such as ring lights or backlight, may produce optimum results depending on the part and its surroundings. 3D imaging can use a variety of camera processes, including electronic scanning or snapshots.
Object detection and imaging technologies can include structured sensors that analyze the reflection of light projected onto a part so they can read part dimensions. Time-of-flight cameras project infrared light onto an object and measure the time required for the light to reflect back to the camera so they can determine depth information.
Software
Robotic vision applications use software that processes a camera image and then directs the action of the robot based on visual information. Rule-based software stores, sorts and uses data following rules developed by humans. The system uses the rules to interpret and act on visual information from a camera. Some software packages use deep-learning technology that utilizes artificial intelligence (AI) and machine learning to accomplish tasks such as object detection and recognition.
Full-featured, Flexible 2D and 3D Robotic Vision
Integrated systems embedded on robots can offer powerful tools for 2D object recognition, reading bar codes and performing OCR and OCV. The vision tools locate, inspect and read codes on stationary or moving parts. Systems such as KUKA.VisionTech are engineered to be easy to integrate, access and use.
With a high-quality camera in an IP 67 housing, KUKA.VisionTech supports a wide variety of robot operations, even in unstructured environments, for use in applications that range from fast moving consumer goods to food. Code recognition capability simplifies product traceability, which can be essential for sustainability or quality control. At the same time, the system enables manufacturers to safeguard production output and reduce costs.
When it comes to 3D visions systems, 3D stereo cameras have had a huge impact on the advancement of robot vision system technology. They allow robots to recognize parts – not just their location, but also their orientation. With such systems, KUKA successfully automates the highly challenging bin-picking process. The 3D stereo camera/vision system captures a part image and transfers it to software, which then uses the images to extract data representing viable parts that the robot can pick. From the image, the software rates which part is in the optimal pick position or relatively close to it, then sends decisions to the robot.
Choosing a Robotic Vision System
Robotic vision capability has evolved from simple part recognition to fast, flexible, complex sensor systems. Before manufacturers add vision capabilities, they should consider what their systems must contribute to production operations and select technology that fully meets those needs. To choose the most efficient, cost-effective system – and one that seamlessly interfaces with various types of cameras – rely on guidance from a robot manufacturer such as KUKA or a system integrator.
The post Vision Systems Let Robots See What They Are Doing appeared first on Fabricating & Metalworking.
