Search for: All records

This paper explores how mechanical and aerospace engineering (MAE) students understand and improve their data proficiency throughout their engineering curriculum. Data is essential for engineering students to be proficient in handling, as it is involved in every aspect of engineering. With the growing ubiquity of data and data analysis in all engineering fields, engineering students need to learn and master data skills to be competitive in the current and future job market. However, there is a lack of research on how non-computer science or software engineering majors perceive data proficiency and how they seek opportunities to develop data skills, especially as it relates to specific subdomains. In this paper, we investigate how students perceive data proficiency and how they develop using interview data from N = 27 MAE students at a research institution in the southeastern United States. Using the How People Learn framework, we analyzed the data through thematic analysis methods with a postpositivist approach, considering the bounded context of this study. The results show that MAE students value data proficiency as a crucial skill for their future careers and recognize its importance in making evidence-based engineering decisions. The study also reveals that, even though data proficiency is often a “hidden competency,” MAE students intuitively find various ways to enhance their data skills. These findings may help engineering educators to tailor their instruction to their students’ needs, address misconceptions about data and data proficiency, and prepare a data-literate future engineering workforce. 

Robotic manipulators are widely used in various industries for complex and repetitive tasks. However, they remain vulnerable to unexpected hardware failures. In this study, we address the challenge of enabling a robotic manipulator to complete tasks despite joint malfunctions. Specifically, we develop a reinforcement learning (RL) framework to adaptively compensate for a nonfunctional joint during task execution. Our experimental platform is the Franka robot with seven degrees of freedom (DOFs). We formulate the problem as a partially observable Markov decision process (POMDP), where the robot is trained under various joint failure conditions and tested in both seen and unseen scenarios. We consider scenarios where a joint is permanently broken and where it functions intermittently. Additionally, we demonstrate the effectiveness of our approach by comparing it with traditional inverse kinematics-based control methods. The results show that the RL algorithm enables the robot to successfully complete tasks even with joint failures, achieving a high success rate with an average rate of 93.6%. This showcases its robustness and adaptability. Our findings highlight the potential of RL to enhance the resilience and reliability of robotic systems, making them better suited for unpredictable environments.