Name: Autonomy Foundations
SKU: Autonomy-Foundations-W2-3-26
Price: 1169.1 USD
Availability: InStock

Autonomy Foundations

Camper's Age: Ages 15-18

Camp Topic: Robotics

Camp Week: Weeks 2-3 (June 8-12 & 15-19)

Gaming: No gaming

Ages 13–15 | 5-Day Full-Day or 10-Day Half-Day

Build and program an autonomous JetBot using the NVIDIA Jetson Nano. Train neural networks for collision avoidance, code path-following with regression models, navigate with AprilTags and ROS, and map environments with SLAM. Curriculum developed by the Carnegie Mellon Robotics Academy.

Full-Day Schedule (5 Days, 4 sessions/day)

Day 1 — JetBot Assembly & First Programs

Session	Project
AM 1	Assemble the JetBot chassis, camera module, and Jetson Nano; flash the SD card and boot the system
AM 2	Configure WiFi networking; connect to the JetBot via Jupyter Notebook and run diagnostic checks
PM 1	Write Python code in Jupyter to drive motors — forward, reverse, spin; test with live execution
PM 2	Program precise turns and distances; complete the 100 cm Traverse challenge

Day 2 — Motion Control & Teleoperation

Session	Project
AM 1	Code a teleoperation interface — control the JetBot in real time from a browser gamepad widget
AM 2	Program a Lawnmower Pattern: systematic area-coverage algorithm using motor timing and turns
PM 1	Combine pre-programmed routines with teleoperation — code a hybrid navigation mode
PM 2	Navigation challenge: program the JetBot to autonomously traverse a taped course with turns and stops

Day 3 — Supervised Learning: Collision Avoidance

Session	Project
AM 1	Capture and label training images (blocked / free) using the JetBot camera; build a dataset of 200+ samples
AM 2	Train a classification neural network on the dataset using PyTorch on the Jetson Nano
PM 1	Deploy the trained model — code a real-time collision avoidance loop that steers the JetBot away from obstacles
PM 2	Tune the model: collect additional edge-case data, retrain, and test in increasingly complex environments

Day 4 — Path Following & AprilTag Navigation

Session	Project
AM 1	Collect path-following data using regression labels (x, y target coordinates); train a regression model in PyTorch
AM 2	Deploy the path-following model — JetBot autonomously follows a line/track using camera input and predicted steering
PM 1	Calibrate the camera for AprilTag detection; write ROS nodes to read tag position and orientation
PM 2	Program waypoint navigation — JetBot autonomously drives to a sequence of AprilTag markers using ROS

Day 5 — SLAM & Final Challenge

Session	Project
AM 1	Configure SLAM on the JetBot — drive through an environment while the robot simultaneously builds a map and tracks its position
AM 2	Refine the SLAM map; program the JetBot to navigate to coordinates within the mapped environment
PM 1	Final challenge: combine collision avoidance, path following, and AprilTag navigation into one autonomous mission
PM 2	Demo day — teams present their JetBot capabilities; discuss real-world applications in logistics, manufacturing, and healthcare

Half-Day Schedule (10 Days, 2 sessions/day)

Days	Content
Days 1–2	JetBot Assembly & First Programs (Full-Day 1 content)
Days 3–4	Motion Control & Teleoperation (Full-Day 2 content)
Days 5–6	Supervised Learning: Collision Avoidance (Full-Day 3 content)
Days 7–8	Path Following & AprilTag Navigation (Full-Day 4 content)
Days 9–10	SLAM & Final Challenge (Full-Day 5 content)

What You'll Build

Fully assembled and configured NVIDIA Jetson Nano JetBot
Python motor-control programs and teleoperation interface
Collision avoidance neural network (classification) trained on custom data
Path-following model (regression) with real-time steering
ROS-based AprilTag waypoint navigation system
SLAM-generated environment map with autonomous navigation
Combined autonomous mission integrating all systems

Tools & Technologies

NVIDIA Jetson Nano & JetBot platform
Python, Jupyter Notebooks, PyTorch
ROS (Robot Operating System)
AprilTags, SLAM