Date of Submission
Mechatronics Engineering, Computer Engineering, Mechanical Engineering
Dr. Adeel Khalid
Dr. Margaret Lowder
This project was sponsored by Clorox to design and create an automatic bottle-unscrambling system for possible implementation at their bottling plant in Chile. The objective was to use a robotic arm to unscramble bottles from an incoming conveyor belt and place them upright on an outbound conveyor belt. Throughout the research, design, and testing of solutions for this project, several design alternatives were found for each discipline, and will be presented to Clorox so that they can make an informed decision for how and if they want to move forward with implementation of this project.
The project was split into three main sections, based on the experience and discipline of each KSU Team member. Peter Jacobs, Mechatronics Engineering Major, was assigned to the robotic arm, as well as the general lab space setup. He was also the main coordinator between the KSU Team and the Clorox Team. Preston Delaware, Computer Engineering Major, was assigned to the machine vision. Ryan Foster, Mechanical Engineering Major, was assigned to the mechanical alignment of bottles as well as gripper design and fabrication.
For this project, a custom mechanical alignment system was designed and implemented. Using a combination of gravity-fed chutes and compressed air, this design was 100% successful at aligning the incoming bottles along the primary axis of the bottle and parallel with the length of the conveyor at the bottle rate specified by Clorox. A custom end effector was designed, fabricated, tested, and refined for this application. This end effector was able to successfully grip and release the bottles for this application.
This project was limited by the space and materials available to the KSU Team in the lab, such as the robotic arm that was not designed for high-speed, pick-and-place operations. Despite these limitations, the KSU Team was able to successfully implement a fully working bottle unscrambling system, albeit at a slower speed than would be actually implemented by Clorox.
The final achievement of note is the use of machine learning for the machine vision. The speed requirements issued by the Clorox Team was a hinderance on what type of image processing could be used. When a machine learning neural network was implemented, the processing of bottle orientation was able to be done with much more speed and accuracy.
Project PowerPoint Presentation
Blipper Project Overview Final.mp4 (288803 kB)
3110-100_BLIPPER MECHANICAL DRAWING SET.pdf (706 kB)
bottle_detection.py (4 kB)
Jetson Nano Code
Applied Mechanics Commons, Computer-Aided Engineering and Design Commons, Digital Communications and Networking Commons, Electrical and Electronics Commons, Manufacturing Commons, Other Engineering Commons, Robotics Commons, Systems and Communications Commons