In this paper, we present a generalized, holistic method for automated robotic arm handling of manufactured components in an industrial setting using computer vision. In particular, we address scenarios in which a high volume of manufactured parts are moving along a conveyor belt at random locations and orientations with multiple robotic arms available for manipulation. We also present specific, tested solutions to all stages of the framework as well as some alternative methods based on the literature review. The framework consists of three stages: (1) visual data capture, (2) data interpretation, and (3) command generation and output to robotic arms. In the visual data capture stage, a multi-component computer vision system takes in a live camera feed and exports it to an external processor. In the data interpretation stage, this video feed is interpreted using tools like 3D point clouds and object detection/tracking models to provide useful information such as object number, location, velocity, and orientation. Lastly, the command generation and output to the robotic arms stage takes the information acquired from the analysis in the data interpretation stage and turns it into instructions for robot control. While a full-scale, cohesive system has yet to be tested, our solutions to each stage show the feasibility of implementing such a system in an industrial setting.

Due to Covid-19, in-person robotics labs held in previous semesters were not possible. This paper explores a well-established method to give the students an exceptional learning experience in a robotics class. By surveying students, data was gathered to account for students’ perception when designing the laboratories and lab manuals. In addition, to find an adequate program for the labs, different software was researched and tested. The main factors used to select a software were intuitiveness, cost, online resources, operating system compatibility, Python programming, and software usage. It is concluded that the RoboDK software is the most suitable software for the laboratories, and updated manuals needed to be designed for the Spring 2021 class. Last semester, Spring 2021, another survey was conducted to get students’ feedback on the new lab system. With the additional data, further research may be conducted to refine the laboratories’ assignments and manuals. This paper’s main contribution is to use and analyze RoboDK for online robotics laboratories. Therefore, through this research, a new method was presented that gave students hands-on experience on online laboratories.

No abstract