Automated Depalletizing

About Automated Depalletizing

Fizyr’s modular software segments, classifies, does quality control and finds the best grasp poses of items and parcels that vary in shape, size, color, stacking, material, etc. Our deep learning algorithms allow robots to pick unknown objects from bulk or conveyors, with over 99% success rate in picking precision.

From boxes and trays to deformable objects, from closely stacked or overlapping objects to damaged goods, Fizyr software product enables robots to deal with variations on pallets successfully.

Based on all classifiers, Fizyr algorithms propose over 100 grasp poses every second in challenging environments, empowering robots to move faster and with confidence, while depalletizing unknown SKUs. Our software product robustly segments even for transparent or white-taped boxes and empowers robots to pick from cluttered scenes!

Our deep learning algorithm are trained for: • Segmentation: Detecting the physical boundaries of hard-to-see items in a truck. Dealing with closely stacked and overlaps. • Classifications: Including boxes, bags of coffee or cacao beans, milk powder, etc. Detecting packaging material and damages. • 6 DoF Grasp Poses: Proposing the best grasp strategy based on all classifiers. You can configure your preferred multi-suction gripper. Our software will propose which (combination of) different suction cups to apply.

Keywords

• 3D Vision
• Ai
• Artificial Intelligence
• Computer Vision
• Deep Learning
• Deformables
• Depalletizer
• Depalletizing
• Industrial Robotics
• Intralogistics
• Machine Learning
• Machine Vision Software
• Material Handling
• Order Picking
• Parcel Picking
• Parcel Singulation
• Random Shapes
• Robotics
• Robotics Automation
• Universal Picking

Address

• Headquarters

  Julianalaan 67A2628BC DelftZuid-Holland, Netherlands