A Framework For Parallelizing Sampling-Based Motion Planning Algorithms
Abstract
Motion planning is the problem of finding a valid path for a robot from a start position to a goal position. It has many uses such as protein folding and animation. However, motion planning can be slow and take a long time in difficult environments. Parallelization can be used to speed up this process. This research focused on the implementation of a framework for the implementation and testing of Parallel Motion Planning algorithms. Additionally, two methods were implemented to test this framework. The results showed a reasonable amount of speed-up and coverage and connectivity similar to sequential methods.
Subject
Robotic Motion PlanningSampling-based Motion Planning
Parallel Algorithms
Distributed Algorithms
Citation
Bulluck, Matthew James (2017). A Framework For Parallelizing Sampling-Based Motion Planning Algorithms. Master's thesis, Texas A & M University. Available electronically from https : / /hdl .handle .net /1969 .1 /169642.