In recent years, multi-robot systems have been widely used in many applications such as warehouse inventory tracking and automatic search and rescue operations. Probability roadmap (PRM) is a typical path planning algorithm that can determine an optimal trajectory once the robot start and goal positions are specified. However, when the number of robots in the system increases, it converges slowly and may even fail to find the solution.
In this thesis, a fuzzy inference system is proposed and combined with the probability roadmap algorithm for robot path planning. Computer simulation results in five different environments show this approach is very effective to reduce computation cost in most cases for multi-robot systems of various sizes. It is able to reduce the number of collision checks by at least 27% with a trade off of increased average path length of 12% at the most. It is also noticed that the proposed fuzzy system is not advantageous when combined with the sub-dimension expansion algorithm. More research will be conducted in the future to further improve the performance of the proposed fuzzy inference system.
Identifer | oai:union.ndltd.org:CALPOLY/oai:digitalcommons.calpoly.edu:theses-3962 |
Date | 01 September 2021 |
Creators | Replogle, Brandon |
Publisher | DigitalCommons@CalPoly |
Source Sets | California Polytechnic State University |
Detected Language | English |
Type | text |
Format | application/pdf |
Source | Master's Theses |
Page generated in 0.0014 seconds