Process layout
This solution was used to develop a bin picking workstation for ActiNav, Universal Robots' autonomous motion solution. ActiNav is a comprehensive system capable of vision inspection, collision avoidance, and real-time robot motion control. In collaboration with Vention, Universal Robots conducted research to improve the efficiency of bin picking based on workpiece height, picking angles, and the distance between the robot and parts. Vention developed a specialized workstation that allows for easy adjustment of these critical factors. Through testing the time and accuracy of picking 100 workpieces, the team successfully developed a workstation that reduced operation time by 40%.
Components
| Robot |
|
|---|
Workflow
| STEP 1. | Recognition: The system identifies parts within the infeed bin. |
|---|---|
| STEP 2. | Picking: The robot picks parts starting from the top-most stacked items. |
| STEP 3. | Placing: The picked parts are placed at designated positions within the discharge bin. |
| STEP 4. | Repeat: The sorting and picking cycle is performed continuously. |
Features
Rapid Site Deployment
Intuitive Teaching: Enables fast robot programming through the teach pendant and manual demonstration.
Smart Training: Pick-and-place routines can be quickly trained via demonstrations and 3D scanning.
High Operational Efficiency
Maximized Uptime: Maintains high availability through autonomous motion planning and integrated collision avoidance.
Extended Operation: Supports the use of deep bins, significantly reducing the frequency of manual refills.
Results
| Key Benefits | Improved picking cycle times and accuracy.
Drastic reduction in teaching and setup time.
|
|---|
Unauthorized copying or reproduction of any content on Marosol may violate the Unfair Competition Prevention Act and Copyright Act.
Recommended Solution
CNC Machine Tending using Mitsubishi Robot & Drawer System
This solution automates the process of picking raw materials from a storage drawer system and loading them into a CNC machine using a Mitsubishi industrial robot. The system features a specialized drawer unit that opens both inside and outside the robot cell, allowing operators to safely load raw materials from the outside while the robot independently picks and places parts inside. This configuration maximizes space efficiency within the robot cell and ensures a high level of operational safety.
Power Cable Bin Picking using UR5e, Deep Learning, and Reinforcement Learning
This solution automates product sorting, assembly, and packing by utilizing 3D Vision, Deep Learning (Instance Segmentation), Reinforcement Learning (RL), and Motion Planning (OMPL) algorithms. By using 3D vision to recognize product types, product locations, and box positions in real-time, the system can automatically compensate for changes in positioning. The integration of deep learning and reinforcement learning for object identification allows the solution to be applied even to irregularly shaped objects. Because the system calibrates itself through continuous learning—even when conditions change, such as vision/robot misalignment or switching to different products—it ensures easy operation, simplified maintenance, and minimized downtime.
Recyclable Plastic Sorting using Delta Robots and Deep Learning
This solution utilizes 2D Vision, Deep Learning (Instance Segmentation), Reinforcement Learning (RL), and Motion Planning (OMPL) algorithms to rapidly recognize and sort recyclable plastics on a moving conveyor belt. The system features high-performance vision capable of quickly identifying objects even with highly irregular shapes. Through advanced motion planning, it executes sorting tasks with exceptional speed and precision.