Efficient GPU-based Construction of OGs Motivation Occupancy Grids Bayesian Model Sensor Model From range information to 2D grid Previous Work GPU Imple- mentation General Algorithm Architecture Dirac model Gaussian model Results Evaluation Algorithms Evaluation Fusion results Summary and perspectives Efficient GPU-based Construction of Occupancy Grids Using several Laser Range-finders M. Yguel 1 O. Aycard 2 C. Laugier 3 1 Institut National Polytechnique de Grenoble ProBayes S.A. 2 University of Joseph Fourier 3 Institut National de Recherche en Informatique et Automatique International Conference on Intelligent Robots and Systems, 2006 1 / 33
47
Embed
Efficient GPU-based Construction of Occupancy Grids Using ...
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
EfficientGPU-basedConstruction
of OGs
Motivation
OccupancyGridsBayesian Model
Sensor Model
From rangeinformation to2D gridPrevious Work
GPU Imple-mentationGeneral AlgorithmArchitecture
Dirac model
Gaussian model
ResultsEvaluationAlgorithms
Evaluation
Fusion results
Summary andperspectives
Efficient GPU-based Construction ofOccupancy Grids Using several Laser
Range-finders
M. Yguel1 O. Aycard2 C. Laugier3
1Institut National Polytechnique de GrenobleProBayes S.A.
2University of Joseph Fourier
3Institut National de Recherche en Informatique et Automatique
International Conference on Intelligent Robots andSystems, 2006
1 / 33
EfficientGPU-basedConstruction
of OGs
Motivation
OccupancyGridsBayesian Model
Sensor Model
From rangeinformation to2D gridPrevious Work
GPU Imple-mentationGeneral AlgorithmArchitecture
Dirac model
Gaussian model
ResultsEvaluationAlgorithms
Evaluation
Fusion results
Summary andperspectives
Outline
1 Motivation
2 Occupancy GridsBayesian ModelSensor Model
3 From range information to 2D gridPrevious Work
4 GPU ImplementationGeneral Algorithm ArchitectureDirac modelGaussian model
Enforce vehicle safety by• percieving the whole robot
surroundings,• being robust to false
measurements,• having precise map,• providing real-time map.
3 / 33
EfficientGPU-basedConstruction
of OGs
Motivation
OccupancyGridsBayesian Model
Sensor Model
From rangeinformation to2D gridPrevious Work
GPU Imple-mentationGeneral AlgorithmArchitecture
Dirac model
Gaussian model
ResultsEvaluationAlgorithms
Evaluation
Fusion results
Summary andperspectives
Occupancy Grids (OGs)
DefinitionAn OG is a stochastic tessellatedrepresentation of spatial informa-tion that maintains probabilistic es-timates of the occupancy state ofeach cell in a lattice [1].
Features:• no assumption about
environment geometry,• simple fusion process,• occultation information,• each cell is independent.
4 / 33
EfficientGPU-basedConstruction
of OGs
Motivation
OccupancyGridsBayesian Model
Sensor Model
From rangeinformation to2D gridPrevious Work
GPU Imple-mentationGeneral AlgorithmArchitecture
Dirac model
Gaussian model
ResultsEvaluationAlgorithms
Evaluation
Fusion results
Summary andperspectives
Occupancy Grids (OGs)
Features:• no assumption about
environment geometry,• simple fusion process,• occultation information,• each cell is independent.
4 / 33
EfficientGPU-basedConstruction
of OGs
Motivation
OccupancyGridsBayesian Model
Sensor Model
From rangeinformation to2D gridPrevious Work
GPU Imple-mentationGeneral AlgorithmArchitecture
Dirac model
Gaussian model
ResultsEvaluationAlgorithms
Evaluation
Fusion results
Summary andperspectives
Occupancy Grids (OGs)
Features:• no assumption about
environment geometry,• simple fusion process,• occultation information,• each cell is independent.
4 / 33
EfficientGPU-basedConstruction
of OGs
Motivation
OccupancyGridsBayesian Model
Sensor Model
From rangeinformation to2D gridPrevious Work
GPU Imple-mentationGeneral AlgorithmArchitecture
Dirac model
Gaussian model
ResultsEvaluationAlgorithms
Evaluation
Fusion results
Summary andperspectives
Occupancy Grids (OGs)
Features:• no assumption about
environment geometry,• simple fusion process,• occultation information,• each cell is independent.
4 / 33
EfficientGPU-basedConstruction
of OGs
Motivation
OccupancyGridsBayesian Model
Sensor Model
From rangeinformation to2D gridPrevious Work
GPU Imple-mentationGeneral AlgorithmArchitecture
Dirac model
Gaussian model
ResultsEvaluationAlgorithms
Evaluation
Fusion results
Summary andperspectives
Occupancy Grids (OGs)
Features:• no assumption about
environment geometry,• simple fusion process,• occultation information,• each cell is independent.
4 / 33
EfficientGPU-basedConstruction
of OGs
Motivation
OccupancyGridsBayesian Model
Sensor Model
From rangeinformation to2D gridPrevious Work
GPU Imple-mentationGeneral AlgorithmArchitecture
Dirac model
Gaussian model
ResultsEvaluationAlgorithms
Evaluation
Fusion results
Summary andperspectives
OGs drawback
Grids have image-like structures:• huge amount of data
e.g. 100mx100m grid with cell side of 5cm→ 4M cells
• enlarging the field of view→ increases the amount of data
• increasing precision→ increases the amount of data
5 / 33
EfficientGPU-basedConstruction
of OGs
Motivation
OccupancyGridsBayesian Model
Sensor Model
From rangeinformation to2D gridPrevious Work
GPU Imple-mentationGeneral AlgorithmArchitecture
Dirac model
Gaussian model
ResultsEvaluationAlgorithms
Evaluation
Fusion results
Summary andperspectives
OGs drawback
Grids have image-like structures:• huge amount of data
e.g. 100mx100m grid with cell side of 5cm→ 4M cells
• enlarging the field of view→ increases the amount of data
• increasing precision→ increases the amount of data
5 / 33
EfficientGPU-basedConstruction
of OGs
Motivation
OccupancyGridsBayesian Model
Sensor Model
From rangeinformation to2D gridPrevious Work
GPU Imple-mentationGeneral AlgorithmArchitecture
Dirac model
Gaussian model
ResultsEvaluationAlgorithms
Evaluation
Fusion results
Summary andperspectives
The Graphical Hardwares
Graphical processor units (GPUs):
• dedicated to work with images,• high level of parallelism,• easy to program with shading languages,• cheap.
Objective:accurate implementation of OG fusion with the GPU
6 / 33
EfficientGPU-basedConstruction
of OGs
Motivation
OccupancyGridsBayesian Model
Sensor Model
From rangeinformation to2D gridPrevious Work
GPU Imple-mentationGeneral AlgorithmArchitecture
Dirac model
Gaussian model
ResultsEvaluationAlgorithms
Evaluation
Fusion results
Summary andperspectives
The Graphical Hardwares
Graphical processor units (GPUs):
• dedicated to work with images,• high level of parallelism,• easy to program with shading languages,• cheap.
Objective:accurate implementation of OG fusion with the GPU
6 / 33
EfficientGPU-basedConstruction
of OGs
Motivation
OccupancyGridsBayesian Model
Sensor Model
From rangeinformation to2D gridPrevious Work
GPU Imple-mentationGeneral AlgorithmArchitecture
Dirac model
Gaussian model
ResultsEvaluationAlgorithms
Evaluation
Fusion results
Summary andperspectives
Outline
1 Motivation
2 Occupancy GridsBayesian ModelSensor Model
3 From range information to 2D gridPrevious Work
4 GPU ImplementationGeneral Algorithm ArchitectureDirac modelGaussian model