In this paper, a solution is presented for a robotic manipulation problem in industrial settings. The problem is sensing objects on a conveyor belt, identifying the target, planning and tracking an interception trajectory between end effector and the target. Such a problem could be formulated as combining object recognition, tracking and interception. For this purpose, we integrated a vision system to the manipulation system and employed tracking algorithms. The control approach is implemented on a real industrial manipulation setting, which consists of a conveyor belt, objects moving on it, a robotic manipulator, and a visual sensor above the conveyor. The trjectory for robotic interception at a rendezvous point on the conveyor belt is analytically calculated. Test results show that tracking the raget along this trajectory results in interception and grabbing of the target object.
Vision Based Robotic Interception in Industrial Manipulation Tasks
2007-12-21
oai:zenodo.org:1075830
Article (Journal)
Electronic Resource
English
DDC: | 629 |
Bridging Language, Vision and Action: Multimodal VAEs in Robotic Manipulation Tasks
ArXiv | 2024
|Vision-Based Interception of Tethered and Swaying Targets Using Aerial Manipulation
Springer Verlag | 2022
|Parameter Estimation for Deformable Objects in Robotic Manipulation Tasks
Springer Verlag | 2023
|