turn () video on stage with () transparency

Introduction

As we start learning artificial intelligence, let’s make it more engaging by incorporating a fun activity. One of the most popular topics in AI is face detection, and we can make it even more exciting by learning it with the help of Humanoid robots. Are you interested in learning it together?

Code

Logic

1. Simply drag and drop the RHip(), LHip(), RFoot(), LFoot(), RHand(), LHand() block from the Humanoid extension.
2. Start the program by initializing the sprite and face detection library parameters.
3. Use the forever loop block to create a continuous loop.
4. If the camera detects more than one face, the Humanoid will move forward with a specific time, speed, and dance move with do() motion() times at () speed() block.
5. If no face is detected, the Humanoid will move backward at a specific time and speed using do() motion() times at () speed() block.

Output

Introduction

A face-tracking robot is a type of robot that uses sensors and algorithms to detect and track human faces in real time. The robot’s sensors, such as cameras or infrared sensors, capture images or videos of the surrounding environment and use computer vision techniques to analyze the data and identify human faces.

Face-tracking robots have many potential applications, including in security systems, entertainment, and personal robotics. For example, a face-tracking robot could be used in a museum or amusement park to interact with visitors, or in a home as a companion robot that can recognize and follow the faces of family members.

One of the most fascinating activities is face tracking, in which the Humanoid can detect a face and move its head in the same direction as yours. How intriguing it sounds, so let’s get started with the coding for a face-tracking Humanoid robot.

Logic

1. If the face is tracked at the center of the stage, the Humanoid should be straight.
2. As the face moves to the left side, the Humanoid will also move to the left side.
3. As the face moves to the right side, the Humanoid will also move to the right side.

Code Explained

1. Drag and drop the when green flag clicked block from the Events palette.
2. Then, add a turn () video on stage with () % transparency block from the Face Detection extension and select one from the drop-down. This will turn on the camera.
3. Add the set head pin () FLeft () FRight () BLeft () BRight () block from the Humanoid extension.
4. Click on the green flag and your camera should start. Make sure this part is working before moving further.
5. Add the forever block below turn () video on stage with () % transparency from the Control palette.
6. Inside the forever block, add an analyzed image from the () block. This block will analyze the face the camera detects. Select the camera from the dropdown.
   
7. Create a variable called Angle that will track the angle of the face. Based on the angle, the robot will move to adjust its position.
   
8. Here comes the logical part as in this, the position of the face on the stage matters a lot. Keeping that in mind, we will add the division () / () block from the Operator palette into the scripting area.
9. Place get () of the face () at the first place of addition () + (), and 3 at the second place. From the dropdown select X position.
10. If the angle value is greater than 90, the Humanoid will move left at a specific speed. If the angle is less than 90, the Humanoid will move right at a specific speed. If the angle is exactly 90, the Humanoid will return to its home position.

Block Explained

1. Create a variable called Angle and assign it the value of the face’s position.
2. At the center of the stage, we will get the X position value which is zero.
3. As we move to the left side the X position value will give you the negative value and as we move to the right side the X position value will give you the positive value.
4. The x position value is divided by 3 which gives precise positioning.
5. To set the angle at 90 when the face is at the center of the stage we have added 90 to the X position value.
6. As we move to the left side the angle value will get decreased as the X position value is going in negative.
7. As we move to the right side the angle value will get increased as the X position value is going in positive.

Code

Output

Our next step is to check whether it is working right or not. Whenever your face will come in front of the camera, it should detect it and as you move to the right or left, the head of your  Humanoid robot should also move accordingly.

This project demonstrates how to use Machine Learning Environment to make a machine–learning model that identifies hand gestures and makes the humanoid move accordingly.

We are going to use the Hand Classifier of the Machine Learning Environment. The model works by analyzing your hand position with the help of 21 data points.

Hand Gesture Classifier Workflow

Follow the steps below:

1. Open PictoBlox and create a new file.
2. Select the coding environment as appropriate Coding Environment. you can click on “Machine Learning Environment” to open it.
   
3. Select the “Open ML Environment” option under the “Files” tab to access the ML Environment.
   
4. Click on “Create New Project“.
5. A window will open. Type in a project name of your choice and select the “Hand Gesture Classifier” extension. Click the “Create Project” button to open the Hand Pose Classifier window.
   
6. You shall see the Classifier workflow with two classes already made for you. Your environment is all set. Now it’s time to upload the data.

Class in Hand Gesture Classifier

There are 2 things that you have to provide in a class:

1. Class Name: The name to which the class will be referred.
2. Hand Pose Data: This data can be taken from the webcam or uploaded from local storage.

Note: You can add more classes to the projects using the Add Class button.

Adding Data to Class

You can perform the following operations to manipulate the data into a class.

1. Naming the Class: You can rename the class by clicking on the edit button.
2. Adding Data to the Class: You can add the data using the Webcam or by Uploading the files from the local folder.
   1. Webcam:

Note: You must add at least 20 samples to each of your classes for your model to train. More samples will lead to better results.

Training the Model

After data is added, it’s fit to be used in model training. To do this, we have to train the model. By training the model, we extract meaningful information from the hand pose, and that in turn updates the weights. Once these weights are saved, we can use our model to predict previously unseen data.

The accuracy of the model should increase over time. The x-axis of the graph shows the epochs, and the y-axis represents the accuracy at the corresponding epoch. Remember, the higher the reading in the accuracy graph, the better the model. The range of accuracy is 0 to 1.

Testing the Model

To test the model, simply enter the input values in the “Testing” panel and click on the “Predict” button.

The model will return the probability of the input belonging to the classes.

Export in Block Coding

Click on the “Export Model” button on the top right of the Testing box, and PictoBlox will load your model into the Block Coding Environment if you have opened the ML Environment in the Block Coding.

Logic

The Humanoid will move according to the following logic:

1. When the forward gesture is detected – the Humanoid will move forward.
   
2. When the backward gesture is detected – the Humanoid will move backward.
   
3. When the left gesture is detected – the Humanoid will turn left.
   
4. When the right gesture is detected – the Humanoid will turn right.
   

Code

Logic

Output