Learn and remember, one concept at a time
Short cards with a demo you can play with. Find what you want to explain or review.
Learning paths
Session 1: Robotics fundamentals
The full map of a robot: actuators, communication, sensors, mechanics, kinematics and learning. Each piece once, with its demo.
Flexible manufacturing cell
How an automated line works from start to finish: sensing, actuating, controlling and storing, with the model's interactive guide.
By category
Actuators
How motors work
Current inside a magnetic field = force. Three families depending on what switches the current: brushes (DC), a controller that counts steps (stepper) or electronics that read the rotor (brushless).
Pneumatic cylinders and solenoid valves
Compressed air moves the cylinders; solenoid valves are the bridge to the PLC. A monostable valve springs back to rest on its own when it loses the signal; a bistable one needs a signal for each movement and remembers its last position.
Suction cups and the venturi effect
When compressed air is forced through a narrowing, it speeds up and its pressure drops: this creates a vacuum in the suction cup, which holds the part. A vacuum without a pump.
Sensors
IMU and sensor fusion
The accelerometer knows where down is but gets confused when moving; the gyroscope is smooth but drifts. A complementary filter trusts the gyroscope in the short term and the accelerometer in the long term.
Inductive and capacitive proximity sensors
The capacitive sensor detects any material because it changes its capacitance; the inductive one only detects metals because currents are induced in them. Using both, you know whether a part is metallic.
Lidar and SLAM
Counting wheel turns accumulates error (drift). A lidar measures distances in many directions at once; SLAM builds the map and locates itself in it by aligning each scan, which corrects the drift.
Load cell
Strain gauges glued to a piece of metal change their resistance slightly when it bends. A Wheatstone bridge gives a few millivolts, an ADC turns them into counts and calibration converts those to grams.
Presence detectors and limit switches
To know whether a part or a piston is in place: contact limit switches, magnetic reed sensors on the cylinders and optical sensors that detect whether the part breaks a light beam.
Rotary encoders
An encoder tells the motor where it is. With two phase-shifted channels (A and B) you know how far it has turned and in which direction.
Stereo depth
Two cameras set apart see the same object shifted; nearby things shift more. Depth comes from Z = f · B / d.
Ultrasonic distance sensor
It sends a pulse and measures how long the echo takes: d = c · t / 2. The speed of sound depends on temperature, so if you don't compensate for it the reading drifts.
Voltage divider to read a resistive sensor
A PLC can't read a resistance, but it can read a voltage. Put the sensor in series with a fixed resistor and the voltage at the midpoint changes with the sensor: Vout = Vcc · RS / (RS + Rfixed).
Communication
Addressing on the servo bus
If six servos share one cable, each needs an ID. They all hear everything and only the matching one replies; two servos with the same ID talk over each other.
How chips talk (UART, I2C, SPI, CAN)
A bus is a set of shared wires. Each protocol has its own way of deciding who talks, to whom and when: UART point to point, I2C by address, SPI with a select wire and CAN by message ID.
Mechanics
Backlash
There is a little play between gear teeth. When the direction reverses, the motor turns without moving the output, and the error at the tip grows with the length of the arm.
Gearboxes for joints
A gearbox with ratio N divides speed by N and multiplies torque by N. Planetary, harmonic drive or spur gears: each family trades off precision, robustness and how easily it can be moved from outside.
Kinematics
Coordinate frames and transforms
A point only has coordinates relative to a frame (origin + axes). To go from the robot's frame to the world's: p_world = R(θ) · p_robot + t.
Forward and inverse kinematics
FK: from angles to hand position, always one answer. IK: from position to angles; there can be two solutions (elbow up or down) or none if the point is out of reach.
The Jacobian
The Jacobian maps joint velocities to hand velocity (v = J·ω). When its determinant is zero, the arm is at a singularity and loses a direction of motion.
Control
Learning
Imitation learning
A person teleoperates the robot, observation-action pairs are recorded and a policy is trained to copy them. It fails in states it has never seen; the fix is more varied demos and predicting several actions in a row.
Reinforcement learning
Nobody tells the robot how to do it, only whether it did well: the agent tries actions, gets a reward and learns a policy that maximises it. In simulation, thousands of copies train at once.
Vision-language-action models (VLA)
A VLA starts from a model that already links images and text and adds an action output: it takes camera images, an instruction and the robot's state, and returns a chunk of movements.
Industrial automation
Flexible manufacturing cell
An automated line in three phases: feeding and sorting, machining and storage. Two PLCs coordinate sensors, pneumatic cylinders and servomotors to handle each part according to its material and colour.
PLC and GRAFCET
A PLC cyclically reads all its inputs, runs the program and updates the outputs. GRAFCET describes the process as a sequence of steps and transitions: each step waits for a condition before moving to the next.
Safety in automated machines
A mushroom-head emergency stop halts the whole machine, light curtains stop the movement if someone enters the area and a signal tower shows the status at a glance.
X-Y Cartesian manipulator and servomotors
Two perpendicular axes driven by servomotors with encoders. At start-up it finds the zero of each axis; then it converts coordinates in millimetres into pulses to reach each position exactly.