This course is an advanced introduction to, and a research investigation of state of the art algorithms required for autonomous driving, and more generally, mobile robots. In the first half of the course, we will cover an essential range of topics related to autononomous driving including time-optimal control, planning, and state estimation. In the second half of the course, teams will lead research projects going beyond the lecture topics, and pushing on the boundaries of the state of the art in autonomous driving. Assignments and the research project will be completed in teams of three students on the UT-AUTOmata scale 1/10 autonomous cars. There will be weekly assignments on implementing each building block culminating in a mid-term project to have your autonomous car autonomously explore an environment and visit prescribed locations to collect points. The final project will explore research along one of four suggested research areas: 1) High-speed motion control and planning; 2) High-speed state estimation; 3) Multi-agent (coperative or adversarial) planning for autonomous driving; 4) Robust semantic-metric situational awareness.
Lectures: Mondays and Wednesdays, 9:00 - 10:00 AM, GDC 1.406
Labs: Fridays, 9:00 - 10:00 AM, GDC 1.310
Joydeep Biswas, firstname.lastname@example.org
Office hours: Wednesdays, 10:00 - 11:00 AM
Arnav Iyer, email@example.com
Office hours: Thursdays, 11:00 - 12:30 AM
Assignments will be completed in groups of three, and must be completed on the real cars unless stated otherwise. There will be three milestones, each with weekly checkpoints. Teams must maintain a report covering:
Final reports are due at the end of each milestone, but each checkpoint submission must include a two-page weekly progress report. In addition to the milestones and checkpoints, each team will submit a document of short-form essay responses for a responsible robotics assignment.
The research project will be completed in groups of three. Research project topics will require instructor approval, and must be selected from one of the following tracks:
Each team will lead a class research discussion on the chosen topic, starting with an overview of the state of the art, challenges, and ideas for going beyond the state of the art. Teams must maintain a research journal with weekly updates, reporting on:
Teams will present live demonstrations of their final projects in the GDC Atrium.
Each team is responsible for taking care of their own car and associated peripherals. You must follow all guidlines and safety instructions in the reference manual.
The computers in the GDC 1.310 lab have the necessary software packages installed for you to run the course software, including the simulator, visualizations, and handout code. We encourage teams to use the lab computers to work on the assignments.
The course infrastructure includes a web-based visualizer and remote monitoring and control - this can be used for interacting remotely with the real cars, as well as interacting with the simulator running remotely (e.g. over SSH on a lab computer). We recommend using Visual Studio Code as an IDE for development, for three reasons: