Basic Autonomous Cars Design using ROS (Level 3)

Basic Autonomous Cars Design using ROS (Level 3)

Target Audience: Undergraduate Mechatronics Students
Total Duration: 50 hours (10 sessions × 5 hours)
Delivery Mode: Lab-based + Classroom Theory

Course Objective:
To provide students with foundational knowledge and hands-on skills in building and programming basic autonomous vehicles using the Robot
Operating System (ROS), including sensor integration, robot navigation, and perception systems.

Lecture 1: Introduction to Autonomous Vehicles & ROS
Theory:
• Levels of driving automation (SAE levels)
• Role of Mechatronics in AVs
• Introduction to ROS architecture (nodes, topics, services, messages)
Practical:
• Installing Ubuntu & ROS Noetic
• Creating ROS workspace & simple ROS node communication

Lecture 2: Linux & ROS File System
Theory:
• ROS filesystem structure (packages, nodes, launch files)
• Catkin build system and dependencies
• ROS communication protocols: Topics, Services, Actions
Practical:
• Create simple ROS packages
• Publisher/subscriber examples (Python or C++)
• Launch files demonstration

Lecture 3: Robot Sensors and Actuators
Theory:
• Overview of LIDAR, Camera, IMU, Wheel Encoders
• Actuator control concepts (DC motors, servo, steering control)
Practical:
• Add sensors in simulation using Gazebo
• Control simulated robot motors from ROS

Lecture 4: Robot Modeling & Simulation
Theory:
• Understanding URDF (Unified Robot Description Format)
• Coordinate frames and TF tree
• Visualizing robot models in RViz
Practical:
• Creating a URDF model for a 2-wheeled robot
• View the robot in RViz and check joint states

Lecture 5: Mobile Robot Kinematics
Theory:
• Differential drive and Ackermann steering models
• Control laws: PID basics
• Velocity and pose estimation
Practical:
• Drive robot using velocity commands
• Implement PID controller for wheel velocity in simulation

Lecture 6: Sensor Data Processing
Theory:
• Noise filtering and data fusion
• Processing IMU and LIDAR data
• Using ROS tools
Practical:
• LIDAR data collection and visualization
• IMU data analysis and plotting

Lecture 7: SLAM (Simultaneous Localization and Mapping)
Theory:
• SLAM techniques overview (GMapping, Hector, Cartographer)
• ROS navigation stack architecture
Practical:
• Using TurtleBot + GMapping to build a 2D map
• Saving and loading maps with map server

Lecture 8: Path Planning & Navigation
Theory:
• Local/global path planning
• Cost maps, Dijkstra, A*, DWA
• Role of move base and planners
Practical:
• Implement path planning in Gazebo
• Robot navigates a mapped area autonomously

Lecture 9: Obstacle Avoidance & Safety
Theory:
• Detecting static and dynamic obstacles
• Recovery behaviors and dynamic re-planning
Practical:
• Simulate obstacles in Gazebo
• Tune local planner for dynamic avoidance

Lecture 10: Final Integrated Project
Theory:
• System Integration Recap
• Project Assignment Briefing
Practical:
Final Project: “Warehouse Robot Navigation”
Design and implement a mobile robot using ROS that can:
1. Autonomously map a small environment
2. Navigate between 3 different points
3. Avoid both static and dynamic obstacles
4. Provide sensor data visualization in real-time
Teams (2–3 students) must present:
• Robot model
• System diagram
• ROS nodes used
• Recorded navigation performance

if you would like to get our course content please register . . .