 Hello everyone, welcome back to our channel. I hope you all are safe and sound. We have made robots and have controlled them using keyboard, smart phone, joystick and what not. This time we are going to level up and control them with Hengistus. In this video we will see how we can command a two wheel drive robot to move forward, turn left or right and stop in Hengistus using Pictoblock's machine learning extension. The robot should move forward if we keep our palms straight. It should turn left if we tilt our hand left. And the robot should stop if we close our fist. Three requisites are an assembled two wheel drive robot, a laptop or a computer with a camera, latest version of Pictoblock's downloaded and a good internet connection. Click on the guide above to know how to make the robot. Let's begin by training the models. Go to the Teachable Machines website. Click the get started button. A new page will open up. Click the image project style. Let's begin by adding the first class. As we will be adding a sample image using webcam, click on the webcam button to start the camera. We'll first make the class for the robot to move forward. Thus keep our palm open and record the images. The robot should move forward if we keep our palms straight. It should turn right if we tilt our hand right. It should turn left if we tilt our hand left. And the robot should stop if we close our fist. Your training data is complete. Now that we have included the sample image, we need to train the model accordingly. Thus click the train model button and wait for the model to get trained. You can have a look or test the trained model. Now that the model is perfect, let's export the model. Click on the export model button. A popup will open. Click the upload my model button. A shareable link will appear. Copy it. Now that the models are loaded, let's begin by writing the script. Open Victor blocks. We will first add the machine learning extension. To work with the all new AI and ML extensions, you need to keep two things in mind. First, that you must sign in or log in into Victor blocks from Chrome. Second, you must have a good internet connection. Now click on the board button and select evide. If you are using the evide board for the first time, you need to upload the firmware. Click on the card above to know how. We have already uploaded the firmware to our robot. We now need to add the machine learning extension. Click on the add extension button. Choose the machine learning extension. Now we need to load our model into Victor blocks. Thus click on load model. A dialog box will appear. Paste the copied link into the space given and click on load button. Wait for a little while till the models get loaded. Let's first set up the stage. Drag and drop the when flag click HUD block from the events palette to execute the program when the green flag is clicked. As we need to recognize the hand gestures from the camera feed, place the turn on video on stage with 0% transparency block from the machine learning palette. We will set the evides display to black color. Thus place build screen with black color from the display palette. It's a forever block to make the code run continuously. Display palette drag and drop the set cursor at 10x10 block into the forever block. Next we will recognize the gestures from the stage and perform actions accordingly. Thus let's make a few custom function blocks. Go to my blocks palette. Click on make a block button. First we will make the function to make the robot move forward. Thus right go straight into the name and click on OK. You will notice a HUD block onto the scripting area. Place the run motor 1 in direction forward with speed 100% block from the actuators palette. Deplicate the above block and place it below and choose to from the first drop down. Finally we will make the custom blocks to turn left, turn right and break one by one. Deplicate the two motor blocks and place them below the turn left and turn right custom block. Make a few changes into these blocks. Into the turn left block select reverse from the second drop down of the first block. Into the turn right block select reverse from the second drop down of the second block. Finally into the break block drag and drop the free motor 1 block from the actuators palette. Deplicate it and choose to from the second drop down. Now let's move on to the main script. Place an effects block from the controls palette below the set cursor block. Drag and drop the is identified class from webcam is forward block from the machine learning palette and choose stage from the first drop down. Select forward from the second drop down. Let us recognize the forward class from the train model. Place the go to straight block into the if arm. Next we will write straight on the evive screen using the right block from the display palette. Deplicate the effects block and place it into the else arm. Select left from the is identified class block and replace go to straight block with the turn left block. Right left on the evives display. Repeat the same process to turn right and stop. The script is now complete. Don't forget to share your creations and queries with us in our picture blocks community on Facebook. If you like this video, give it a thumbs up, subscribe to STEMpedia and follow us on Facebook, Instagram and Twitter. Bye bye, stay safe.