Universal Robotics Random Bin Picker Application
Universal Robotics has combined automated intelligence with high-speed control to enable 3D sensor input to update robot behavior in real-time. Universal’s applications integrate the best sensors and equipment with three main components to ensure measurable return on investment.
Sensing (Spatial Vision Robotics). Universal engineers are experts at mixing various sensor technologies to generate accurate 3D vision guidance and inspection.
Control (Sensor Servoing). The company has deep knowledge of industrial machine control required to react and move in real-time.
Intelligence (Neocortex). To ensure quick and efficient completion of the task, Universal applies patented machine learning techniques to control patterned behavior while reacting to sensor data .
Traditional vision approaches can’t automatically detect and identify complex parts randomly placed in a pile. Even with the problem simplified, the result was either overly complex, too slow for normal operations, or had low return on investment.
Universal introduces a breakthrough application – Universal Robotics Random Bin Picker. This application enables a robot to automatically move a number of randomly placed parts at typical speeds, regardless of their orientation or how deep the stack.
This cost-effective breakthrough from Universal uses a suite of sensors that integrates off-the-shelf structured light sensors and pairs of cameras for stereoscopic vision.
The standard application moves one part in any orientation at up to 12 per minute with standard motion control. Whether loosely or tightly packed, either on the floor, conveyor or container, the parts can be in any orientation. This application dynamically provides 3D guidance to the robot for parts regardless of the presence or type of labels or material type. It also provides accurate 3D vision guidance whether the parts are individually placed on a flat or randomly packed tightly in bin up to 48” deep. The cost effective approach eliminates expensive fixturing and automated tables, and works well under varying light conditions. Optionally, Universal’s Random Bin Picking can handle up to 3 parts in any orientation with any combined mix of SKUs per layer. Optional high-speed Sensor Servoing can further increase throughput where required.
Parts can be randomly oriented; loosely or tightly packed in unlimited layers
Easily identifies parts as small as 2” even if partially occluded under varying lighting
Picks & places up to 12 parts per minute
Identifies parts regardless of color, labels, shape or complexity
Flexibility eliminates costly fixturing
Optional high speed throughput
Optional premium sensor suite for ± 0.5 mm accuracy across field of view
Optional 3 SKU multi-part handling
Less than 24 month payback
Many vendors today are adding 3D vision to their capabilities due to customer demand. Universal Robotics is founded on NASA patents that lay the groundwork for robots to be spatially intelligent far beyond just 3D stereoscopic vision.
3D real-time sensing enables:
Random orientation of parts
Variation within parts, such as label types
Optional high speed motion control reaction
World class sensor suites tailored to the situation
Breakthrough cost effectiveness
Spatial Vision Robotics software can work with any industrial robot, and with a wide variety of sensors. Universal offers three sensor suite resolutions – standard (± 5.0mm accuracy), enhanced (± 2.5mm accuracy), and premium (± 0.5mm accuracy) to fit the requirements of the task. The Random Bin Picker can be integrated with either new robots or retrofitted with existing robots having payloads from 5kg to over 500kg, and is designed to fit into standard workcell spaces wherever possible.
Depending on the sensing required, touch, acceleration, and proximity sensors may be added. The Random Bin Picker provides the 3D position(X,Y,Z) and pose (Rx,Ry,Rz) for complex parts in arbitrary orientations in a bin, on a conveyor or assembly area.

After calibration of cameras and sensors, Spatial Vision Robotics software coordinates 3D input to the robot by getting an overall 3D view of the boxes, detecting all parts that match a 3D CAD model, selecting a part to be moved, and monitoring the motion of the robot as it places the part. If there are numerous boxes, the Random Bin Picker automatically selects the highest or closest box and progressively moves through the stack.
The 3D sensor system uses a combination of 3D stereoscopic vision and structured light for identifying SKU position. It generates X, Y, Z position and Rx, Ry, Rz pose values as needed for each box, then interfaces directly to the robot controllers through a PC.
This application adds unique reflective surface matching to handle a wide range of reflective plastics, Mylar surfaces, and clear parts.
The parts may be in a bin above the floor, at floor level, or recessed into the floor, or on a table as shown below in a typical workcell configuration.


