Instructor: Ramviyas N. Parasuraman

Time and Location of Lectures:

Tuesday & Thursday (3:30-4:45 PM) at Boyd #201, Wednesday (3.35-4.25 PM) at Boyd #210.

Office Hours and Location

Tuesday & Thursday 1-2 PM or by an email appointment  

Course Overview

This is primarily a research oriented, seminar-style course covering the topics of control, communication, cooperation, and coordination aspects in multi-robot systems. It enables students to understand, devise, and solve problems in multi-robot systems and the course will have project-based assignments.

Multi-robot systems have potential in applications such as search and rescue, autonomous exploration, sensing and communication infrastructure, transportation, etc. Specifically, coordinating a group of robots involves repetitive tasks of rendezvous, formation control, and flocking of the distributed robots. Multi-robot systems are finding synergies in multiple relevant research areas such as self-driving connected cars and industrial/logistic robotics. Therefore, it is important to understand and advance the robotics literature in the field of multi-robot systems and their applications, which is the main objective of this course.

This course will primarily be research oriented, with most lectures presented in a seminar-type format, and there will be a simulation/hardware project assignment. First, the instructor will present the initial few lectures and covers the fundamental concepts in networked multi-robot systems. In turn, each student will present the analysis of a research paper selected from top robotics conferences or relevant journals. All participants will be required to write a short review of the assigned readings before each lecture. In addition, the course requires each student to formulate and address a relevant research problem in networked multi-robot systems through simulation/hardware experiments either individually or in teams (depending on the course enrolment). The analysis of the chosen research problem, proposed solution, and experimental evaluation should be completed and reported in a conference-style paper by the end of the term (this is the equivalent of the final exam).

Course Topics

The course topics presented here is a general plan for the course; deviations announced to the class by the instructor may be necessary.

General topics to be covered:
1. Multi-robot Rendezvous and Formation Control
2. Multi-agent Cooperation and Coordination
3. Security and adversarial actions
4. Applications of Multi-Robot Systems

Specific topics to be covered/discussed in this course:
1. Multi-agent consensus algorithms using coordinate-based and bearing-based methods
2. Multi-robot formation control and swarming algorithms
3. Reinforcement learning for adaptation in teams of robots
4. Gaussian Processes algorithm for integrating sensor data from multiple robots
5. Multi-robot localization and navigation, SLAM, and map merging
6. Motion coordination algorithms in robots and connected vehicles
7. Distributed cooperative perception and action algorithms
8. Algorithms to measure performance in teams of robots
9. Methods in routing and communication using wireless sensor networks in multi-robot systems
10. Communication and energy aware path planning and motion planning algorithms in the context of multi-robot systems
11. Active perception using touch (tactile), vision, and environmental assessment sensors from multiple robots
12. Vision-based and LIDAR-based sensing algorithms for heterogenous (UAV, UGV, USV) robotic systems

Grading