ENG100/400 — Course Materials

Quick links to lectures and interactive pages

Lectures

Engineering 100-400: Introduction (Autonomous Vehicles)

Overview of course themes and the autonomy stack.

Lecture 1: Autonomous Vehicles: Abstraction → Automation

Lecture 1 slides with interactive elements.

Lecture 2: Software, Compilers, Interpreters & Debugging

Slides generated from l12.software.av.pptx (Reveal.js).

Lecture 3: Robotics Overview (PPTX)

Direct link to roboticsoverview.av.pptx.

Lecture 4: Technical Projects in Teams

Getting started: challenges, best practices, planning and execution.

Lecture 5: Control and Filters

Filter demo and control resources for ENG100.

Lecture 7: Computer Vision for Robots

Slides with interactive apps: filters, edges, convolution, point clouds, YOLO, and neural nets.

Extras

Interactive FSM

Build and step through a finite‑state machine.

Kalman Gain Interactive

Explore intuition behind Kalman gain and updates.

Circuit Intro: Voltage, Current, and Elements

Interactive introduction to voltage, current, and resistance.

Autonomy Learning Modules

Hands‑on modules for planning, vision, graphs, and design trade‑offs.

Wokwi Arduino App

Interactive Blink example embedded via Wokwi.

Brython Maze Demo

Write a right-wall follower in Python; runs in the browser.

PID Demo

Demonstration of PID control.

Lecture 7: Interactive Apps

Line Following Simulator

Position the line and robot; tune threshold and controller; animated sensor LEDs.

Filter Lab

Grayscale, brightness/contrast, box/Gaussian blur, sharpen, threshold, and morphology.

Convolution Kernel Playground

Edit 3×3 kernels; try blur, sharpen, edge, and emboss with proper normalization.

Sobel Edge Detector

Gradient magnitude or thresholded edges; optional pre‑blur.

Point Cloud Demo (RANSAC Plane)

Fit a plane, highlight inliers, and view a shaded plane patch; auto‑fit view.

YOLO Object Detection — Showcase

Pre‑canned detections on local images (no heavy model in‑browser).

HSV Threshold — Orange Ball

HSV sliders with a color wheel to isolate the orange ping‑pong ball.

Tiny Neural Net — Forward & Backprop

Train a 2→3→1 MLP on XOR/AND/OR with live weights and loss plot.