Important note: sign-up for HBO-ICT, Electrical and Electronic Engineering (ET) and Mechanical Engineering (WTB), students use Bisoncode: L.26577
Important note: sign-up for Mechatronics (MT), students use Bisoncode: L.26583
* The client of this project will attend the Preview on Thursday 28th of November from 13:30 to 16:00 at Saxion Enschede (Ariënsplein 1).
The high-tech production factories in Northwest-Europe are marked by a high mix, low volume product mix. Production automation, flexibilization and optimization are essential processes to manufacture smaller batches, but still with the opportunity to deliver a large variety of products.
Many processes, like assembly lines for soldering of electrical components, can be fully automated by using robotic systems. Specific tasks, however, are still being carried out by humans due to the complexity of the task or the low number of products to be assembled. For instance, opening packaging, gluing of various components, and screwing etc. In situations like these, the robotic systems should be able to corporate with the humans without hurting them or damaging the product: collaborative robotics, or cobots.
The research group Mechatronics is exploring the safe use of collaborative robots in a production environment. Cobots have the capability to share the same workspace as humans. This is mainly achieved by triggering a stop when a force is applied to the cobot. Although very safe, this feature is not really collaborative and very inefficient in a production environment.
To achieve real collaboration between human and cobot, the cobot has to be aware of what’s going on in his environment, a.k.a. spatial awareness. The first safety step is to reduce speed, but eventually to exchange components or assemblies by interacting with the production operator.
To do this, the research group wants to explore the use of for instance machine learning techniques to detect the operator, but also use 3D vision techniques to detect obstacles or human operators in its workspace.
This project will be carried out using a UR5 cobot equipped with a normal industrial camera operating in ROS (robotic operating system) that is currently capable of constructing a DUPLO house. At the end of the project you are able to use ROS; able to use machine learning tools for vision; able to develop vision algorithms. At our research group we also have an interactive pool table.
Keywords: vision, machine learning, cobots, safety, industrial automation.
At the end of this assignment, the following deliverables should be submitted to the client:
- Project documentation (including: project plan, design documentation, software and Final report),
- and a working proof of concept system that is able to detect operators around the robot and visualize them.
Extra info: we have an interactive pool table in our research group for student use.
Required study programs:
Electrical and Electronic Engineering: Vision design; electrical integration.
HBO-ICT: Business Management.
Mechanical Engineering: Mechanical design and integration.
Mechatronics: System engineering; system integration.Sign up now
Questions about this project?
Feel free to contact us if you have any questions about this project. You can call us at 088 - 019 53 11 or use the form below. We wil get back to you within two business days.