TEACH ARTIFICIAL INTELLIGENCE in a concrete and precise manner, by taming a small robot from Primary 3 onwards to adult.
Experiment Supervised and Reinforcement Learning, visualize and manipulate neural network
AlphAI makes AI within everyone's reach.
See and interact with AI:
Robot, Graphical Neural Networks Interface, AI Learning Scenarios, Competition and Training courses.
AlphAI Robot available in 8 colours
Master Artificial Intelligence by taming a small robot from a visual, graphical interface, through coding and machine learning
- Supervised Learning
- Reinforcement Learning - Simple and Deep Q-Learning
- Ready-made AI Learning Scenario activities
- AI Robot competition
- Student code in Python
- Teachers and student course, by Neurorobotics Professor and Researcher
Created by the Learning Robots team in France:
Learning Robots’ mission is to demonstrate to all audiences how artificial intelligence and neural networks work: from initiation to manipulation, from elementary school to vocational training and high school programming.
Teach artificial intelligence in a concrete manner, explained by Thomas Deneux
Book Thomas for training over Zoom
The AlphAI solution combines 3 important innovations
A robot learning in front your eyes to embody simple or impressive learning.
A graphical interface (the software) to open the “AI black box” and manipulate algorithms, including the famous artificial neural networks.
A pedagogy finally to introduce the concepts one by one, through mini-scenarios proposed to the manipulation; concepts that will echo our own human learning!
To understand more about the concept behind AlphA please visit here at the official site.
Meet a little robot that learns fast.
But, how does he do it?
AlphAI: The small robot with a lot under the hood
The small and friendly AlphAI robot is equipped with multiple sensors that allow it to learn various behaviors, including the camera for image recognition.
Sensors
Wide angle camera
Ultra sound
Infrared line tracking sensors
Outputs
2 drive wheels
Multi-color LEDs
Buzzer
On-board computer
Raspberry Pi Zero (linux, Python)
WiFi connection to PC
Soft shell
Shock absorbing, removable, available in 8 colours
Competences:
AI in Action
Obey
Classical Programming
Like any other robot, AlphAI can be programmed with instructions.
Whether in Python or via the graphical interface, your new robot will obey at a glance. If it bumps into something, you’ll know who to blame!
Imitate
Supervised Learning
Create data to train the robot’s AI, starting with remote control. It will then be able to recognize people, compete in a robot race, or perform a choreography. Hey, looks like it likes you!
Explore
Reinforcement Learning
At the beginning he doesn’t know how to do anything. He bumps, turns around, hesitates… Then, he becomes more confident and develops his interaction skills. Look, he is now able to avoid obstacles, follow a path and even play soccer. Bravo AlphAI!
Environment
An Arena to facilitate Learning
Because the quality of learning also depends on the environment of the robot, we have designed an arena to provide you with an optimized plug & play solution:
- good floor / wall contrast for quick learning
- good detection that the robot is moving
- size 80x80cm, fits on a large classroom table
- modular:possibility to enlarge, mazes, etc.
4 Arenas combined
Order the Modular Arena
But, of course, you can also build your own custom arena!
Open the AI Black Box
Thanks to a unique interface. But how to interact?
Innovation!
A unique solution to see and interact with AI Algorithms
AlphAI is the only software that, thanks to its graphical interface, makes learning algorithms (deep learning, KNN, etc.) accessible. It presents them in a visual and intuitive way, then allows you to take control of them, from beginner mode for a “plug & play” experience to expert mode for programming the AI in Python!
Visualize!
Enter the Deep Learning Network
Simple Network
Understand in Details
On simple learning scenarios, understand and teach step by step how artificial neural networks work.
Draw connections inside the network yourself and observe the consequences on the robot’s movements. Thanks to multiple displays (activity values, thickness of connections, colors for learning, etc.), explain visually the learning equationsthat automatically optimize these connections.
Complex networks
Scale Up
Activate the camera and the intermediate layers of neurons and see how the simple principles detailed above allow the learning of complex behaviors (obstacle avoidance, pushing a ball, etc.) after scaling up to thousands of neurons and hundreds of thousands of connections. You have in front of you all the calculations made, but they are so numerous that we still miss something, isn’t it fascinating?
Other algorithms
Decide like your neighours
Discover – still very visually – other Machine Learning algorithms. In particular, the K-nearest neighbors algorithm, which is part of several high school curricula, is particularly intuitive and adapted to introduce supervised learning. Then compare its results to those of neural networks, on the same training database
Control!
Take the Lead
Beginner
Let us Guide You
Select the beginner display mode to see only the most common settings. Most importantly, load demo configurations to effortlessly run pre-set supervised or reinforcement learning scenarios.
Intermediate
Start your own learning process
Test your own learning by selecting the sensors used as inputs, the allowed actions, the reward mode for reinforcement learning. Finally, select and configure the AI algorithm, for example to test what the intermediate neurons serve to…
Expert
For Professionals
Use the AlphAI platform to debug your learning model, test the most advanced parameters, study the properties of individual neurons, etc.
Code!
Program in Python
"Classical" Programming
Learn to program with AlphAI
A dedicated Python library allows you to take control of the robot from the computer with simple instructionsto direct the motors, retrieve sensor data, and program paths, maze exit, etc., without necessarily requiring AI. It is also possible to run Python code directly on the Raspberry Pi for faster reaction times.
Program the AI
A Modular approach
Choose the “student code algorithm option and code the one of your choice in the popping-up Python window: the AlphAI platform takes care of all the input-output machinery and you focus on the most interesting! Even easier than AI, program your own reward function to make AlphAI learn new behaviors. Our curricula provide examples exercises to practice basic programming skills while coding an AI.
Other systems
AI Everywhere?
We are working on making the AlphAI software compatible with other robots and automated systems, so that they can be driven by machine learning. You will also be able to carry out your own projects to develop new materials to be controlled with AlphAI.
The Software
The software is designed to run on a PC without internet connection. However, it requires a Wi-Fi connection to communicate with the robot. The robot is sold with one license for 30 computers.
The software has a simulated version of the robot, allowing up to 30 students (for the purchase of the first AlphAI), to learn and experience AI when the robot is not connected.
Teach AI
Mini Learning Scenarios
The AlphAI device offers a platform for teaching artificial intelligence in different ways and at different levels. Its approach is very concrete, based on the realization of mini learning scenarios.
A teaching with AlphAI will take these scenarios, or others, and run them according to the age of the audience, either in the form of a teaching by a presenter, or in the form of a workshop involving manipulation, where several groups will each manipulate a different robot.
The configuration of the following scenarios are included in the software.
Manual edition of a mini-neural network
Supervised learning, image recognition
Supervised learning, robot racing
Reinforcement learning in a mini-neural network
Reinforcement learning with camera and more complex network
Reinforcement learning: Following a balloon
AlphAI software Installation and lesson guide
10 mini learning scenarios
Supervised Learning - KNN
Camera
Reinforcement Learning Lab
Discovery of Artificial Intelligence with the AlphAI
Reinforcement Learning Workshop
Manual Editing a simple Neural Network
Supervised Learning - Robot Race
