Teaching

Teaching Philosophy

My teaching philosophy is grounded in the belief that students learn engineering most effectively when they are encouraged to build, test, question, and iterate. Robotics and intelligent systems are inherently hands-on disciplines, and students gain true understanding when they can see algorithms controlling real hardware, observe sensors responding to the environment, and diagnose how mechanical or electrical design choices influence system performance. I strive to create learning environments that are supportive, practice-oriented, and inclusive—where students feel confident experimenting, asking questions, and learning through iteration.

Across my teaching roles at Purdue University and the Hong Kong University of Science and Technology (HKUST), I have found that students develop the strongest technical intuition when they are asked to move beyond idealized assumptions and confront real system constraints such as noise, calibration drift, timing delays, mechanical tolerances, and failure modes. My goal is to help students connect foundational theory to the messy realities of real-world engineering—while also developing the communication, teamwork, and engineering judgment required to succeed in research and industry.

Teaching Experience

Purdue University

Industrial Robotics and Flexible Assembly (IE 574)
In IE 574, I led laboratory modules involving CoppeliaSim, TMFlow robotic programming, and Python-based perception. Students implemented sensing–control pipelines, integrated multiple sensing modalities, and deployed algorithms on physical robotic platforms. I also mentored student teams through semester-long projects that required end-to-end system integration, debugging, and iterative improvement.

Manufacturing Processes (IE 370)
I assisted in instructional support and labs focusing on manufacturing workflows, process planning, and automation-relevant concepts, helping students connect materials, processes, and production constraints to engineering decision-making.

Imagine, Model, and Make (IE 472)
In Purdue’s design studio setting, I supported student teams in CAD-based design iteration, prototyping, and fabrication, with emphasis on turning conceptual designs into tested physical systems.

Hong Kong University of Science and Technology (HKUST)

At HKUST, I taught SolidWorks modeling and mentored teams through iterative design, material selection, rapid prototyping, and fabrication. These experiences strengthened my belief that extended, open-ended engineering challenges are among the most effective ways for students to build resilience and design intuition.

Representative Student Projects (IE 574)

In IE 574, I supervised multiple semester-long team projects where students developed complete perception–manipulation systems. These projects required students to integrate sensing, control, and decision-making into robust robotic workflows—mirroring the development cycle used in real industrial automation and robotics research. Below are representative examples (videos from student demonstrations).

Vision-Guided Pick-and-Place System

A perception-driven pick-and-place pipeline using RGB-based classification and closed-loop robot execution.

Perception-Driven Industrial Automation Pipeline

An end-to-end workflow combining perception, motion planning, and execution on a robotic platform.

Mobile Manipulation with Vision Integration

A mobile manipulation workflow integrating TMFlow behaviors with Python-based perception and task logic.

Feedback-Driven Robotic Assembly Task

A robotic assembly behavior demonstrating feedback, correction, and robust task completion.

These projects reflect the teaching environment I strive to create: students learn core concepts through implementation, confront real-world constraints, and develop confidence through iterative refinement and system-level thinking.

Mentorship and Student Development

Mentoring is central to my teaching identity. I have supervised undergraduate researchers and mentored student teams working on tactile sensing, robotic manipulation, perception pipelines, simulation workflows, and mechanical design. Many of these students were engaging with robotics research for the first time. I supported them through the full cycle of technical growth—defining goals, structuring experiments, debugging failures, interpreting results, and presenting outcomes clearly.

I am especially committed to supporting students from diverse backgrounds and students who may not initially see themselves as “robotics people.” I aim to make engineering feel approachable by normalizing iteration, uncertainty, and failure as part of the learning process.

Teaching Evaluations

My teaching effectiveness is reflected in strong student evaluations from Purdue’s Industrial Robotics and Flexible Assembly course:

• 4.55/5 – clarity of explanations
• 4.50/5 – effectiveness in answering questions
• 4.58/5 – availability and willingness to help
• 4.50/5 – fostering an inclusive and supportive learning environment

Students frequently commented that I explained challenging robotics concepts in accessible ways and created a lab environment where they felt comfortable asking questions, debugging openly, and exploring alternative solutions.

Courses I Am Prepared to Teach

My teaching interests lie at the intersection of robotics, intelligent systems, sensing, and mechanical design. I am prepared and excited to teach courses such as:

• Robotics and Robot Programming
• Mechatronics
• Dynamics and System Modeling
• Control Systems
• Manufacturing Automation
• Embedded Sensing and Perception for Robotics
• Human–Robot Interaction (project/lab components)

Future Teaching Directions

I am interested in developing new project-driven electives that connect physical systems with modern AI. One example is a course on Multimodal Sensing and Embodied Intelligence, where students design sensing systems, implement perception pipelines, and build robust robot behaviors through experimental evaluation. Another potential elective would focus on Tactile Sensing for Robotic Manipulation, introducing students to sensing architectures, data-driven inference, and task-level decision-making in contact-rich scenarios.

Ultimately, my goal as an educator is to help students build technical fluency, engineering judgment, and confidence—so they can contribute meaningfully to robotics, intelligent systems, and interdisciplinary engineering challenges.