Title :
GPU-based real-time collision detection for motion execution in mobile manipulation planning
Author :
Hermann, Andreas ; Klemm, Sebastian ; Zhixing Xue ; Roennau, Arne ; Dillmann, Rudiger
Author_Institution :
Dept. of Intell. Syst. & Production Eng. (ISPE - IDS), Res. Center for Inf. Technol. (FZI), Karlsruhe, Germany
Abstract :
In this paper we present a parallel collision checking approach as an essential building block of a reactive online planning framework, that allows to continuously monitor the execution of planned trajectories against dynamic changes in the environment. The software is optimized for massively parallel hardware architectures, namely CUDA GPUs and offers constant runtime regardless of the occupancy density in the environment.
Keywords :
collision avoidance; graphics processing units; manipulators; mobile robots; parallel architectures; real-time systems; CUDA GPU; GPU-based real-time collision detection; building block; massively parallel hardware architectures; mobile manipulation planning; motion execution; occupancy density; parallel collision checking approach; planned trajectory execution monitoring; reactive online planning framework; Collision avoidance; Graphics processing units; Instruction sets; Planning; Robot kinematics; Robot sensing systems;
Conference_Titel :
Advanced Robotics (ICAR), 2013 16th International Conference on
Conference_Location :
Montevideo
DOI :
10.1109/ICAR.2013.6766473
