Understanding the AI System (10 minutes)

Have students turn to Module 2, Lesson 3 in their Field Notebooks and begin on the <a href="https://docs.google.com/document/d/1kD1sVlrot3gr-rwe5XYA31gDBvEZL-eLaukZAT4mec/edit?usp=sharing">Planning & Coding Your AI System_ page. They will use this page to record their work throughout the lesson.

Today students are simulating how AI systems are used in autonomous vehicles. Self-driving systems use cameras and AI to understand what is happening around them and decide how to move.

Explain that these systems constantly capture visual data from cameras and analyze it to recognize patterns such as lanes, obstacles, or signs. The AI then outputs information, such as a direction or decision, which the program uses to control the vehicle’s movement.

Connect this to the lesson by explaining that Ari will act like a simplified autonomous system. The camera will capture what is on the track, the AI will analyze the image to identify the correct crop, and the program will use that output to decide which direction Ari should travel.

Explain the Coding Challenge (10 minutes)

The Challenge: Program Ari to follow directions on a track towards a specific crop, using AI and computer vision to identify the crop based on its color and health.

Overview

1. This lesson uses section B of the Agriculture Mat.
2. Explain that Ari will travel down the track, reach the intersection, and use AI output to decide which direction to turn.
3. Show students the crop cards and describe what each card represents:
   1. Green - Healthy Crop
   2. Blue - Dehydrated Crop
   3. Red - Dead Crop
4. Place three different crop cards in each box.
5. Model placing the camera above the mat so the AI system can clearly see the track and crop cards.

Guide a discussion around how the AI system will work using Input → Processing → Output → Action. Encourage students to define the roles of humans and AI using precise language.

1. Input: Students write a prompt such as, “Turn to the blue, dehydrated crop.” Simultaneously the camera captures an image of the crop cards on the track.
2. Processing: The AI analyzes the image and looks for patterns to identify the requested crop.
3. Output: The AI outputs a direction such as “left,” “straight,” or “right,” based on the prompt.
4. Action: The program uses that output to determine which direction Ari should turn at the intersection.

Group Strategy & Planning (10 minutes)

Students move into their groups and examine the mat. Ask students to discuss how their AI system should work and talk through possible program structures before coding.

Discussion prompts:

• What crop condition will your AI system be asked to identify?
• How will the AI output determine which direction Ari turns?
• What blocks will you use to move Ari to the intersection?
• How will your program signal when the task is complete?

Students should write their steps in pseudocode or sketch their program flow before coding. Groups should leave this step with a clear plan for how their program will work.

Setup (5 minutes)

1. Turn on Ari and open the Computer Science folder. Open the Blockly app.
2. Place the mat on a flat surface.
3. Launch the Editor on a coding device.
4. Connect the camera to the coding device and position it above the mat section.
5. Under Devices, connect the camera, Ari and LLM bot.
6. Place a different crop card in each box.
7. Check the camera preview to make sure it is aligned correctly.

Code, Test, Iterate, and Improve (30 minutes)

Students move to the Ozobot Editor and begin building their program. Each student codes their own version of the solution based on their group discussion.

Students run their programs on the mat and observe the results. If the system does not behave as expected, students revise their code and test again. Encourage multiple iterations to improve system accuracy.

• Continue testing the program by swapping out crop card types and changing the placement in the boxes.

By the end of the lesson, students should have a working version of their AI system that completes the challenge. Students need to save their program and write down the 7-digit share code so they can reopen the same workspace in the next lesson.

Explanation of Possible Solution

The steps below outline one possible program that completes the objective. Because coding allows for many valid approaches, students’ programs may look different. Use the breakdown below if you would like to guide students through this example solution.

Share Code: s4drr98

1. Set the AI system rules. Type in an initial prompt, such as “There are three types of crop cards: red crop cards, blue crop cards, and green crop cards.”
2. Drive Ari to the intersection. Set Ari’s movement speed and add a line navigation block to move forward along the track.
3. Use AI to process the camera image. Use an LLM block with the camera enabled. Ask for a direction output, which limits responses to: left, right, straight, back.
4. Type a prompt. Prompt Ari to turn towards a specific crop such as, “Turn to the blue, dehydrated crop.”
5. Store the AI output. Create a variable titled “direction,” which will contain the direction Ari should turn. Set the “direction” variable to the LLM response.
6. Display the AI output. Print the “direction” variable to the console so students can see the direction output.
7. Navigate to the crop. Use a pick direction block with a “direction” variable block to move Ari towards the specific crop. Then move Ari to the end of the track.
8. Signal completion. Program Ari to flash its lights to match the crop color and show that the task is complete.

Exit Ticket - Explain Your Thinking (10 minutes)

Conclude the lesson by presenting the “Explain Your Thinking” question and having students independently complete a written response in their Field Notebook.

Explain Your Thinking:

Describe what your AI system did and what you decided as the programmer. What advantages did the AI system provide compared to the farmer making the navigation decision manually?