Fast online collision avoidance for mobile service robots through potential fields on 3D environment data processed on GPUs

Resource type
Conference
Author(s)
Juelg, Christian and Hermann, Andreas and Roennau, Arne and Dillmann, Ruediger
Year
2017
Note
unpublished, approved for publication
Book title
2017 IEEE International Conference on Robotics and Biomimetics (ROBIO)
School
Karlsruher Institut für Technologie
Abstract
This paper demonstrates the fitness of massively parallel exact Euclidean distance transform (EDT) computation for fast 3D online motion planning with potential field and wavefront planners. We combine point-cloud sensor data to gather detailed 3D voxel maps of complex environments. Unlike other approaches, we do not use 3D polygon meshes or reduce the environment to 2D or 2.5D models to improve planning times. The evaluation shows that fast sub-second local and global planning times on the basis of GPU EDT are possible.
Online Sources
https://www.researchgate.net/publication/324024262_Fast_online_collision_avoidance_for_mobile_service_robots_through_potential_fields_on_3D_environment_data_processed_on_GPUs
DOI
10.1109/ROBIO.2017.8324535
Research focus
Service Robotics and Mobile Manipulation
Project
HORSE – Smart integrated Robotics system for SMEs controlled by Internet of Things based on dynamic manufacturing processes
Download .bib
Download .bib
Published by
Christian Juelg