Skip to content

AuE-4930/6930 @ Clemson University

AuE-X930 @ Clemson University

About

AuE-4930/6930: Autonomous Vehicles: Racing Application is a mixed undergraduate/graduate-level course at Clemson University, which introduces the principles, strategies and implementation of AI/ML-enhanced vehicle autonomy (perception, localization, planning and control) deployments within an autonomous racing context. Real-world challenges/constraints from the racing context are used to motivate the systematic application of fundamental knowledge; modular hierarchical decomposition; comparative evaluation and down-selection at the component, subsystem, and system-levels; and scaffolded homeworks, sub-projects, and end-to-end capstone project realization with contemporaneous technologies.

  • Course Overview

    Course Level: 4000/6000 Level Technical Elective (3 cr)

    Department: Automotive Engineering (AuE)

    Institution: Clemson University (CU-ICAR)

    Modality: On-Campus + Online (Asynchronous)

  • Course Motifs

    • Motif 1: Autonomous Systems

    • Motif 2: Mechatronics Principles

    • Motif 3: Design Thinking

    • Motif 4: Digital Engineering

  • Learning Outcomes

    • Learn core concepts of the fundamental autonomy sub-modules (perception, localization, planning, and control) for autonomous racing.

    • Analyze alternate design choices (within the sub-modules as well as the overall composed system) to inform the most effective end-to-end realization.

    • Work on scaffolded labs using the racecar digital twin to build theoretical understanding and practical skills for various implementation strategies.

    • Integrate and deploy autonomy algorithms onto the racecar physical twin to build theoretical understanding and practical skills for sim2real transfer.

    • Develop end-to-end autonomous racing stacks through rigorous capstone projects, and demonstrate, document and present them to a technical audiance.

  • Course Content

    • M00: Autonomous Systems Engineering Onramp
      Linux, Git/GitHub, Docker, ROS 2, AutoDRIVE, NeoRacer

    • M01: Cyber-Physical Systems Engineering
      Setup, Calibration, Telemetry, Teleoperation

    • M02: Reactive Autonomous Driving Algorithms
      AEB, Wall Following, Follow-the-Gap, Disparity Extender

    • M03: Mapping, Localization, and SLAM
      Odometry, Scan Matching, Pose Graph, Particle Filter

    • M04: Path Planning and Raceline Optimization
      Min. Distance, Min. Curvature, Min. Time Planning

    • M05: Trajectory Tracking and Motion Control
      PID, Pure-Pursuit, Stanley, MPC, MPPI, MPCC, etc.

    • M06: Autonomous Racing Competition
      Project Demonstration, Documentation, Presentation

Instructors
Dr. Venkat Krovi
vkrovi@clemson.edu
Course Instructor		 Tanmay Samak
tsamak@clemson.edu
Teaching Assistant		 Chinmay Samak
csamak@clemson.edu
Teaching Assistant		 Pranav Korrapati
pkorrap@clemson.edu
LMS Support

Resources

AutoDRIVE is envisioned to be an open, comprehensive, flexible and integrated cyber-physical ecosystem for enhancing autonomous driving research and education. It bridges the gap between software simulation and hardware deployment by providing the AutoDRIVE Simulator and AutoDRIVE Testbed, a well-suited duo for real2sim and sim2real transfer targeting vehicles and environments of varying scales and operational design domains. It also offers AutoDRIVE Devkit, a developer's kit for rapid and flexible development of autonomy algorithms using a variety of programming languages and software frameworks.

NeoRacer is a 1:12 scale autonomous racecar platform for research and education by the Neobotics Foundation Inc. It integrates onboard compute, sensing (LiDAR, global-shutter camera, IMU, and motor encoder), actuation (drive-by-wire and steer-by-wire), and vehicle interfaces into a compact Ackermann-steered 4WD chassis, providing the hardware foundation for autonomous vehicle development. The platform is accompanied by open-source documentation covering the setup, hardware, software, interfaces, and development workflows.

For this course, students will develop their autonomous racing algorithms using the AutoDRIVE Devkit (ROS 2), safely prototype them within the AutoDRIVE Simulator (digital twin), and deploy them onto the AutoDRIVE Testbed (physical twin). Here, NeoRacer serves as the reference vehicle platform for AutoDRIVE, with the corresponding high-fidelity, real2sim-calibrated digital twin represented in AutoDRIVE Simulator and the physical twin integrated into AutoDRIVE Testbed, which enables sim2real transfer and fielded deployment in the real world. AutoDRIVE Devkit provides a common ROS 2 interface across the digital and physical twins, allowing students to develop and validate their autonomous racing algorithms in simulation and subsequently deploy them on the physical NeoRacer with consistent vehicle behavior and interfaces. Together, these components provide a unified development-to-deployment workflow spanning software, simulation, and hardware.