Methods of swarm SLAM are becoming increasingly prevalent in academic literature. So far, the bulk of research in SLAM has focused on single-robot or centralized SLAM approaches. These systems are capable of producing accurate maps, but miss the opportunities for parallelism and robustness offered by swarm robotic systems. In this work, we present an end-to-end solution for decentralized map synchronization with occupancy grids for swarm robotic systems. The algorithms presented are packaged in a ROS node alongside a custom communication network to facilitate inter-robot map merges

• This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator

• McLaughlin, Connor
• Ferrara, Tyler
• Nikopoulos, Peter

Publisher

• Worcester Polytechnic Institute

Identifier

• E-project-032322-234653
• 53351

Keyword

• Computer Vision
• Robotics
• Computer Networking
• Peer-to-Peer
• SWARM Robotics
• SLAM

Advisor

• Pinciroli, Carlo

Year

• 2022

Sponsor

• BAE Systems

Date created

• 2022-03-23

Resource type

• Major Qualifying Project

Major

• Computer Science
• Robotics Engineering

Rights statement

• In Copyright