Introduction to robotics and AI
What a robot is, how AI differs from machine learning, where you already meet both in daily life, and the parts every robot is built from. Day 1 of the AIBOMECH Ramadan series.
Assalamu alaikum and welcome to AIBOMECH! This Ramadan we are running a 30-day series on robotics and artificial intelligence. We start from the very basics, what robots are made of and how they move, and work up to the ideas behind today's intelligent machines. No background is needed. Along the way we also talk about privacy, bias and using AI responsibly.
What is robotics?
Robotics is the field that designs, builds and programs robots. It brings together mechanical engineering, electronics and computer science.
A robot is a programmable machine that can sense its surroundings, decide what to do and act in the physical world. Robotics is the science; the robot is the machine.
Every robot, from a vacuum cleaner to a Mars rover, repeats the same loop many times per second:
$$ \text{Sense} \;\longrightarrow\; \text{Think} \;\longrightarrow\; \text{Act} \;\longrightarrow\; \text{Sense} \;\longrightarrow\; \cdots $$
A short history. People imagined mechanical helpers for centuries, but the modern era began in 1954, when George Devol filed a patent for the first programmable robot arm, Unimate. In 1961 it went to work at a General Motors plant, lifting hot die-cast metal parts that were dangerous for people to handle. Today robots weld cars, explore Mars, assist surgeons and clean floors.
What is artificial intelligence?
Artificial intelligence (AI) is software that does tasks we normally link to human intelligence: recognising patterns, understanding language, learning from experience and making decisions.
Machine learning (ML) is the part of AI that learns from data instead of following hand-written rules. There are three main ways a machine can learn:
| Type | How it learns | Robot example |
|---|---|---|
| Supervised learning | From examples with the right answer attached | Recognising a cup in a camera image |
| Unsupervised learning | Finds structure in data without answers | Grouping similar places in a map |
| Reinforcement learning | By trial and error, guided by rewards | Learning to walk or to grasp |
How robotics and AI fit together
AI on its own is code running on a computer. A robot on its own can only repeat what it was programmed to do. Together they become something more:
- AI gives the robot a "mind": it can see with computer vision, understand speech, plan a path and adapt when something changes.
- The robot gives AI a "body": sensors to perceive the world and motors to change it.
Not all AI needs a robot (think of film recommendations or translation apps), and not all robots use AI: many factory arms follow the same pre-programmed path all day. The interesting part is where the two meet: robots that work safely next to people, move through messy environments and learn new tasks.
Where you already meet them
- At home: robot vacuum cleaners and lawn mowers, voice assistants, smart thermostats.
- In hospitals: robots that carry medicine and supplies, and surgical robots that help doctors make precise movements.
- In shops and warehouses: robots that pick orders, move shelves and scan stock.
- In factories: arms that weld, paint, assemble electronics and pack goods.
- On farms: robots that harvest fruit, weed and monitor crops.
- In dangerous places: disaster zones, the deep sea and space, where robots go so people don't have to.
The parts of a robot
Whatever its shape, a robot is built from the same main parts:
| Part | Human equivalent | What it does |
|---|---|---|
| Controller (computer) | Brain | Runs the software and makes decisions |
| Sensors | Eyes, ears, skin | Measure the world and the robot itself |
| Actuators (motors) | Muscles | Turn electrical signals into motion |
| Body and joints | Skeleton | Hold everything together and define how it can move |
| End effector | Hand | The gripper or tool that touches the world |
| Power supply | Food and energy | Batteries or mains power |
| Communication | Voice | Wi-Fi, cables or radio links to people and other machines |
Sensors come in two groups:
- Internal sensors watch the robot itself: encoders for joint angles, IMUs for tilt and acceleration, current sensors for motor load.
- External sensors watch the world: cameras, depth cameras and LiDAR to see, ultrasonic and infrared sensors to measure distance, force and touch sensors to feel, and temperature or gas sensors to monitor the environment.
What's next
In the coming days we look deeper at the history of robots, the different types of robots and sensors, how machine learning works and the ethical questions around AI.
Question for today: what excites you most, building robots, learning about AI or exploring what the future could bring? Share your answer on our channels under the name AIBOMECH, where we post daily videos and discussions throughout Ramadan.