Carnegie Mellon Robotics Academy Training for Jetson Nano with Jetbot AI (On Demand)
In this face-to-face teacher training, you will work with the world leaders in robotics education to learn how to teach Artificial Intelligence in a robotics context using the Nvidia Jetson Nano and Jetbot platform. Carnegie Mellon Robotics Academy's specialized training program for the Nvidia Jetson Nano and Jetbot AI has been specifically designed for high school and college educators who wish to infuse their curriculum with an innovative and practical approach to teaching artificial intelligence (AI) and mobile robotics.
Why AI and Mobile Robotics? AI is transforming industries from healthcare to finance, agriculture to entertainment, and many more. Concurrently, mobile robotics is evolving at a rapid pace, with robots playing increasingly significant roles in manufacturing, logistics, healthcare, and even personal assistance. In this ever-changing landscape, there is a pressing need for students to understand AI and robotics from a fundamental level.
Value of Our Training Our comprehensive training program provides educators with the knowledge and tools to successfully teach AI and mobile robotics using the Nvidia Jetson Nano on the Jetbot robotics platform. The Jetson Nano is a small, powerful computer designed specifically for AI and machine learning, making it an ideal tool for teaching these subjects. The Jetbot, a mobile robot powered by the Jetson Nano, provides a hands-on, tangible application of AI, making it a perfect companion tool.
Our training program includes:
- Introduction to AI, machine learning, and robotics fundamentals
- Hands-on experience with the Nvidia Jetson Nano and Jetbot AI
- Strategies to effectively teach these complex subjects in an engaging and accessible way
- Continued support and access to classroom teaching materials
Upon completion of the training, participants will receive a certificate of completion stating 36 professional development hours in areas including artificial intelligence, robotics, and coding.
Alignment with Standards
The Jetson Nano with Jetbot AI training course is aligned to the 5 Big Ideas in AI (Perception, Representation & Reasoning, Learning, Natural Interaction, and Societal Impact) and K-12 AI Guidelines defined by AI4K12.org.
Topic 1: Getting Started with Jetson Nano
- What is the Jetson Nano?
- System Comparison: Jetson Nano / Raspberry Pi / Arduino
- Nature of Edge Computing
- Features and Applications
- Setting up the Jetson Nano
- Image Classification
- Object Detection
Topic 2: Basic Motion with the Jetson Nano
- Mobile Robotics
- Jetbot Platform Assembly
- Basic Motion Jupyter Notebook
- Moving Forward, Backward, Left, and Right
- Behavior-Based Programming & Pseudocode
- Python Programming
- Basic Motion Challenges
- Basic Motion Interactive Control
Topic 3: GPIO (LED & Bumper) on Jetson Nano
GPIO (General Purpose Input & Output):
- Introduction to GPIO on Jetson Nano
- GPIO Software Setup
- Introduction to LEDs
- Controlling LEDs
- Introduction to Bumper Switches
- Bumper Switches
- Python Programming
- GPIO Practice Challenges
Topic 4: Teleoperation with Jetson Nano
- What is Teleoperation?
- What is the Internet of Things (IoT)?
- Jetson Nano and IoT
- Teleoperation Configuration
- Teleoperation Jupyter Notebook
- Teleoperation Practice Challenges
- Configuring Remote Camera Feed
- Cybersecurity Threats in Robotics
- Understanding AIoT (Artificial Intelligence of Things)
- Defense in Depth
- What is Collision Avoidance?
- Collision Avoidance on Jetbot
- Virtual Safety Bubble
- Collision Avoidance Jupyter Notebook
- Obstacle Data Collection
Training the Road Follower Model:
- Road Follower: RESnet-18
- Road Following Video Feed (TensorRT)
- Road Following (TensorRT) Model Optimization
- Troubleshooting Road Following
- Road Following Practice Challenges
Topic 6: Road Following with Jetson Nano
- What is Road Following?
- Road Following on Jetbot
- Road Following Jupyter Notebook
- Road Data Collection
Training the Neural Network
- Convolutional Neural Networks (CNNs): RESnet-18
- Training the RESnet-18 model
- Model Optimization for Jetson Nano
- Running Collision Avoidance
- Troubleshooting Collision Avoidance
- Collision Avoidance Practice Challenges
Road Following + Collision Avoidance:
- What is Road Following with Collision Avoidance?
- Road Following with Collision Avoidance Jupyter Notebook
- Road Following with Collision Avoidance Practice Challenges
Topic 8: Reinforcement Learning with Jetson Nano
- Introduction to Reinforcement Learning
- Components of Reinforcement Learning
- Training the Reinforcement Learning Agent
- Real-World Applications
- Reinforcement Learning Game
- Reinforcement Learning with the Jetbot
- Practice Challenges with Reinforcement Learning
Topic 9: JetRacer and AI Racing Overview
- What is JetRacer
- JetRacer Hardware and Software Setup
- JetRacer Basic Motion
- JetRacer TeleOperation
Interactive Regression (AI Racing):
- What is Interactive Regression?
- JetRacer Data Collection
- Interactive Regression Model Training
- JetRacer Racing Demonstration
- Jetson Nano Developer Kit: https://developer.nvidia.com/buy-jetson?product=jetson_nano&location=US
- 2x Micro SD Cards (at least 64 GB, 128 recommended) and Micro SD Card Reader
- Waveshare Jetbot AI Kit: https://www.waveshare.com/product/robotics/mobile-robots/jetson-nano-ai-robots/jetbot-ai-kit-acce.htm
- Note: alternative kits are available: https://jetbot.org/master/third_party_kits.html
- 5x 18500 Rechargeable Batteries
- Micro-USB Power Supply: https://www.amazon.com/Raspberry-Supply-SoulBay-Adapter-Android/dp/B07CVH21NC
- Note: alternatives available
- USB Keyboard
- USB Mouse
- HDMI Monitor and Cable
- Laptop (up-to-date Windows PC or Mac)
- Internet access for Laptop and Jetson Nano
The following is required in order to complete the GPIO module:
- Small Breadboard, Male-to-Female Prototyping Jumper Cables, Male-to-Male Prototyping Jumper cables, 1x 1k Ohm resistor, 1x 200 Ohm resistor, 1x LED, 1x Bumper Sensor
The following is recommended in order to take this course:
- Building Block City Street Plates: https://www.amazon.com/Plates-Building-Attached-Double-Sided-Baseplates/dp/B096MJX2WF
- Note: alternatives available
- USB Video Capture Card to HDMI: https://www.amazon.com/Capture-Fulfalic-Editing-Streaming-Teaching/dp/B0BJ2YDV7Q
- Note: alternatives available
- Certificate of Completion
- May be used to apply for Continuing Education Credits
- ACT 48 credits / 36 hours per class (for Pennsylvania teachers only)
Classes at the Carnegie Mellon Robotics Academy are available to individuals who are at least 18 years of age to enroll. The Carnegie Mellon Robotics Academy reserves the right to restrict, suspend or terminate any student for violation of these policies. In consideration of your involvement with the Carnegie Mellon Robotics Academy, you agree to provide true, accurate and current information about yourself when you register. If you provide any information that is inaccurate or if the Carnegie Mellon Robotics Academy has reasonable grounds to suspect the information is inaccurate, the Carnegie Mellon Robotics Academy has the right to terminate your account.
Purchasing a seat gives access to one participant only. Resources distributed as part of the class are for use of the participant only. Purchase Orders are also acceptable. Please contact the Carnegie Mellon Robotics Academy at email@example.com for information about registering for the course and payment for the course. Please email if you have questions about the content of the course.
The Carnegie Mellon Robotics Academy will offer partial refunds for tuition expenses only if class registrants contact us prior to the class filling up. To be fair to the registrants in the sessions, we cannot give refunds once a class is full.
Copyrighted Class Material
All course documents are owned by the Carnegie Mellon Robotics Academy. These materials may not be reprinted in any form except those specified for instructional purposes. The course documents and presentations may be displayed and printed for personal, non-commercial use only. Only students registered for this course may access this material. The Carnegie Mellon Robotics Academy makes every effort to provide accurate and up-to-date content. However, we have no liability for the accuracy, content, or accessibility of the hyperlinks included with class material.
Use of Student Material
The Carnegie Mellon Robotics Academy reserves the right to use coursework done by students for the purpose of advancing the educational mission of the Academy. When this occurs, students will be given the option to have their name credited to the material. This includes, but is not limited to, text, graphics, multimedia and other material created as part of the Carnegie Mellon Robotics Academy online course assignments.
You agree to indemnify and hold the Carnegie Mellon Robotics Academy harmless from any and all losses, actions, controversies, suits, demands, claims, liabilities or any causes of action whatsoever. You expressly agree that the Carnegie Mellon Robotics Academy is not responsible or liable for any infringement of another’s rights, including intellectual property rights.
Note: Policies are subjected to occasional revisions.