Roboception Introduces ItemPickAI
AI-based Module enables Picking and Oriented Placing of 'Unseen' Objects
With the software image 25.01.0, Roboception has also launched its latest software component: rc_reason ItemPickAI.
The rc_reason ItemPickAI software enables AI-based grasping and oriented placement of so-called ‘unseen’ objects – i.e. objects, that the system has not explicitly learned by teaching models or seen in training data in advance.
ItemPickAI enables automated separation and oriented placement even of deformable objects: Robotic pick-and-place applications such as the palletizing and unpacking of bags, sacks and various pouch packaging can be implemented precisely and efficiently.
This AI-supported solution for robotic pick-and-place applications with suction grippers computes aligned gripping poses on unknown, deformable objects of a certain category. These objects can be fed in chaotic boxes or load carriers, unmixed and mixed configurations as well as precisely oriented placement are possible.
A vision system consisting of a 3D stereo sensor (rc_visard/ rc_visard NG or rc_viscore) and ItemPickAI Module reliably detects and segments unknown objects with uneven surfaces and deformable filling and provides the robot with precise grasp points for an efficient handling of the objects using a suction gripper. Robust segmentation of the units is ensured by the use of neural networks.
Applications can be found not only in classic automation, but also and above all in the field of logistics: with the ItemPickAI module, the robot can pick disordered and crushable objects from a crate and place them in an aligned position. The solution is also suitable for unpacking pallets and placing objects on conveyor belts, e.g. on a cross-belt sorter.
- veröffentlicht von: Marina Sonzogni
- Kategorie: General