Robotics × Programming × AI: Embodied Intelligence and Industrial Automation

Why this direction matters#

Robots are moving from isolated production cells into flexible factories, logistics, service, and research. The scarce skill is no longer assembling a machine alone, but connecting perception, planning, control, and real operating constraints.

Three practical application areas#

• ROS 2 navigation and simulation: start by understanding the real workflow, data source, and evaluation rule before choosing a model.
• Vision-guided picking: start by understanding the real workflow, data source, and evaluation rule before choosing a model.
• LLM-based task planning: start by understanding the real workflow, data source, and evaluation rule before choosing a model.

A portfolio project you can finish#

Build a simulated mobile robot that receives a natural-language instruction, converts it into safe steps, and navigates to a target in Gazebo.

A useful project report should explain the problem, the data, the baseline, the result, and what failed. A working small system is more convincing than a large collection of disconnected tools.

Suggested toolkit#

Python, C/C++, ROS 2, Gazebo, OpenCV, PyTorch

Use the smallest stack that completes the experiment. Keep source data, assumptions, evaluation, and limitations visible so another student can reproduce your result.

A 12-week learning route#

1. Weeks 1–2 — Understand the field. Map one real workflow and interview a practitioner or study an authoritative case.
2. Weeks 3–4 — Build data literacy. Learn the Python and data skills needed to inspect, clean, and visualize a small dataset.
3. Weeks 5–7 — Reproduce a baseline. Implement a transparent rule or classical model before using a foundation model.
4. Weeks 8–10 — Build the product loop. Add an interface, error handling, and a way for a human to review the result.
5. Weeks 11–12 — Publish the evidence. Write what worked, what did not, and what you would test next.

What to remember#

AI does not replace domain knowledge. It rewards students who can define a useful problem, work with evidence, and turn a model into a responsible workflow. Start with one small project and let the next question come from real use.