A scalable method for parallelizing sampling-based motion planning algorithms

This paper describes a scalable method for parallelizing sampling-based motion planning algorithms. It subdivides configuration space (C-space) into (possibly overlapping) regions and independently, in parallel, uses standard (sequential) sampling-based planners to construct roadmaps in each region. Next, in parallel, regional roadmaps in adjacent regions are connected to form a global roadmap. By subdividing the space and restricting the locality of connection attempts, we reduce the work and inter-processor communication associated with nearest neighbor calculation, a critical bottleneck for scalability in existing parallel motion planning methods. We show that our method is general enough to handle a variety of planning schemes, including the widely used Probabilistic Roadmap (PRM) and Rapidly-exploring Random Trees (RRT) algorithms. We compare our approach to two other existing parallel algorithms and demonstrate that our approach achieves better and more scalable performance. Our approach achieves almost linear scalability on a 2400 core LINUX cluster and on a 153, 216 core Cray XE6 petascale machine.

Authors

• Sam Ade Jacobs
• Kasra Manavi
• Juan Burgos
• Jory Denny
• Shawna L. Thomas
• Nancy M. Amato

Keywords

• Planning
• Robots
• Libraries
• Joining processes
• Standards
• Scalability
• Probabilistic logic
• Scalable
• Parallelization
• Path Planning
• Motion Planning Algorithms
• Sampling-based Motion Planning
• Adjacent Regions
• Performance Scale
• Parallel Algorithm
• Rapidly-exploring Random Tree
• Increase In Size
• Running Time
• K-nearest Neighbor
• Object Motion
• Regional Connectivity
• Neighboring Regions
• Communication Cost
• High-dimensional Problems
• Components In Region
• Motion Sequences
• Sampling-based Approach
• Triple Store
• Uniform Random Sampling