Georgia Robotics and Intelligent Systems (GRITS) Lab, Center for Robotics and Intelligent Machines at Georgia tech (RIM@GT), Georgia Institute of Technology (Georgia Tech), Atlanta, Georgia, USA

[Airicist]

Website - gritslab.gatech.edu (http://gritslab.gatech.edu)

youtube.com/GRITSlab (https://www.youtube.com/GRITSlab)

twitter.com/GTrobotics (https://twitter.com/GTrobotics)

Magnus Egerstedt (https://pr.ai/showthread.php?16493)

Projects:

Tarzan (https://pr.ai/showthread.php?16497), robot gibbon

[Airicist]

https://youtu.be/se318w2LXD0

Multi-Robot Assignment and Formation Control

Uploaded on May 6, 2011


15 Khepera robots executing an assignment and formation control algorithm developed by Edward Macdonald for his Master's thesis at Georgia Tech.

Initially, the formation translation and rotation is unknown, nor do the robots know to what role they are assigned in the formation. The goal of the algorithm is to have a network of mobile robots build formations while minimizing the total distance traveled by all robots. The only information available to each robot are the relative positions of all other robots. There is no communication between robots. Since each robot has access to the same information (relative positions between robots), they independently come to the same conclusion.

Robots know their position via an overhead camera system that tracks each robot and broadcasts its position over wifi.

[Airicist]

https://youtu.be/zbIs7hS-OMs

Robot Landing Platform Formation

Uploaded on Jul 27, 2011


The Khepera robots put on their hats to give their quadrotor friend a place to land.

This is an extension on the algorithm. The difference is that here we are building moving formations, with a leader robot that acts independently. The followers use the same assignment and formation control algorithm to build and maintain formations with the leader.

By making a tight box formation, the ground robots build a mobile landing platform that the quadrotor can land on.

[Airicist]

https://youtu.be/Qi3r8QrQpL8

Robotic Swarm Control Using Clay

Published on May 3, 2013


Imagine that you are surrounded by a million robot mosquitos and you have a single "joystick" that you can use for interacting with the swarm. What should this "joystick" be?

A swarm of robots (Khepera III) is controlled using the clay interface in such a way that no particular skills are required by the operator. Specifically, decentralized and distributed shape controllers allow the operator to form a desired shape presented by molding the clay interface. The abstraction level of the swarm avoids most of the interaction problems that could arise when considering the swarm dynamics, its scale or the communication medium.

[Airicist]

https://youtu.be/4HRSmaeMu2o

Robotics at Georgia Tech - GRITS Lab

Published on Aug 4, 2014


Check out the Georgia Robotics and Intelligent Systems (GRITS) Lab at Georgia Tech!

[Airicist]

https://vimeo.com/103947874

The GRITS Lab at Georgia Tech specialized in swarm robotics.
August 20, 2014

[Airicist]

https://youtu.be/xNvsZ8sQp70

Control Barrier Certificates for Safe Swarm Behavior

Published on Apr 28, 2015


This video illustrates how control barrier certificate can be used to generate provably safe swarm behavior. Control barrier certificate combines the idea of multi-robot collision avoidance with minimal interference to nominal coordination controller. The practical significance of this method is that swarm robotics controllers can be developed without considering collision avoidance, the control barrier certificate will automatically taking care of it when collision is truly imminent.

[Airicist]

https://youtu.be/gsNHJwA7V-U

Controlling swarm robots with touch of finger

Published on May 8, 2015


Using a smart tablet and a red beam of light, Georgia Institute of Technology researchers have created a system that allows people to control a fleet of robots with the swipe of a finger. A person taps the tablet to control where the beam of light appears on a floor. The swarm robots then roll toward the illumination, constantly communicating with each other and deciding how to evenly cover the lit area. When the person swipes the tablet to drag the light across the floor, the robots follow. If the operator puts two fingers in different locations on the tablet, the machines will split into teams and repeat the process.

[Airicist]

https://youtu.be/2uujKTU0TYE

Published on Jul 29, 2016


Swarm of robots might collide with each other when performing complicated tasks. It is often hard to plan swarm behaviour with non-intrusive collision avoidance. This video shows how a minimally invasive safety controller can be added such that safety and higher level objectives can be achieved simultaneously.

[Airicist]

"Creating the next in robotics (http://www.news.gatech.edu/features/creating-next-robotics)"

by Jason Maderer
April 10, 2017