|
g-Planner: Real-time
Motion Planning and Global Navigation using GPUs
motion planning
problems that exploit the computational capabilities of many-core GPUs. Our approach uses thread and data parallelism to
achieve high performance for all components of sample-based
algorithms, including random sampling, nearest neighbor
computation, local planning, collision queries and graph search. The overall approach can efficiently solve both
the multi-query and single-query versions of the problem and
obtain considerable speedups over prior CPU-based algorithms. We demonstrate the efficiency of our algorithms by
applying them to a number of 6DOF planning benchmarks in 3D environments. Overall, this is the first algorithm
that can perform real-time motion planning and global navigation using commodity hardware.
AAAI Conference on
Artificial Intelligence, 2010 Efficient Nearest-Neighbor Computation for
GPU-based Motion Planning (PDF) IEEE/RSJ International
Conference on Intelligent Robots and Systems, 2010 GPU-based Parallel Collision Detection for Real-Time
Motion Planning (PDF) The Ninth
International Workshop on the Algorithmic Foundations of Robotics, 2010 GPU-based Parallel Collision Detection for Fast Motion Planning (PDF) International Journal of Robotics Research (IJRR), 2011 Related Links GAMMA Research Group Ray Tracing Research at GAMMA Motion Planning Research at GAMMA Acknowledgements NSF DARPA/RDECOM Intel
|