Autonomous Systems and Robots

Teaching Staff

Meeting Times

  • The class meets Monday and Wednesday 9:30 AM to 10:45 AM In Person: Engineering Hall B106.B6
  • The class counts for 4 credits, and includes guided readings of a selection of papers and individual or team projects.
Instructor's Office Hours
  • Half hour before and after class or by appointment
TA's Office Hours
  • Location: online
  • Times: TBA

Course Description

The objective of this course is to prepare students in advanced topics in mobile robotics. Mobile robots are capable of dynamically interacting with their environments through relocation and environment manipulation. The next age in robotics will be enabled by rapid and profound advances in autonomous mobile robotics. This course will prepare students for research and development of autonomy algorithms and software mobile robots. Topics covered include robotic system design; perception, mapping and localization; planning under uncertainty; and learning for robotics. Each topic will be accompanied by paper reading and presentation by students. Student chosen applied projects, involving real aerial and ground robots, are a key element of this course.


This course is based on paper reading. We will also use the below text to guide our thinking:

  • Murphy R., Introduction to AI for Robotics

Course Motivation

This section of the syllabus explains the motivation behind the creation of this course and what you can expect to get out of it.

This course was developed to prepare students in advanced topics in robotics, with a particular emphasis on mobile robots. The course will teach students to apply concepts from machine learning, AI, control, and programming to synthesize algorithms for robots that operate in harsh, unstructured, and changing environments. Mobile robots are complex Cyber-Physical systems characterized by strong interdependency between hardware and software, and the need to perceive, reason over, and control physical dynamics at multiple scales. Cyber components include software, embedded computers, sensors, and other electronic and computational artifacts; while physical components include hardware (cars, airplanes, power lines) that is subject to the rules of physics (dynamics, kinematics, electromechanics, fluid flows).

As an advanced graduate level course, this course is also designed to train students to think critically and understand the literature landscape in mobile robotics. We will achieve this through reading of instructor and student selected papers, and presentations on those papers in the class.

The interplay between perception, planning, and control is central to many autonomous systems and robots. Recent advances to mobile robotics have focused on different ways of achieving this interaction, in many cases through the addition of learning. Therefore, we will put a special emphasis on learning based methods for mobile robotics.

List of topics

  • Overview of various mobile robot systems
  • The autonomy triad: Perception, Planning and Control
  • Behavioral robotics
  • Classical SLAM
  • SLAM in dynamic environments
  • Multi robot SLAM
  • Learning based SLAM
  • Semantic and spatial SLAM
  • Topological map navigation
  • Traversibility mapping
  • Privileged learning
  • Variants of MPC for learning
  • Model based RL
  • Self supervised learning in robotics
  • Domain randomization for sim2real
  • Model based Meta RL
  • Learning uncertainty in dynamics
  • Learning based control adaptation
  • End to end imitation learning
  • Trends in bioinspired robotics
  • Soft robots
  • Neuro inspired architectures

List of papers