Ulteriori informazioni
This bookis devoted to one of the most famous examples of automation handling tasks -the "bin-picking" problem. To pick up objects, scrambled in a box is aneasy task for humans, but its automation is very complex. In this book threedifferent approaches to solve the bin-picking problem are described, showinghow modern sensors can be used for efficient bin-picking as well as how classicsensor concepts can be applied for novel bin-picking techniques. 3D pointclouds are firstly used as basis, employing the known Random Sample Matchingalgorithm paired with a very efficient depth map based collision avoidancemechanism resulting in a very robust bin-picking approach. Reducing thecomplexity of the sensor data, all computations are then done on depth maps.This allows the use of 2D image analysis techniques to fulfill the tasks andresults in real time data analysis. Combined with force/torque and accelerationsensors, a near time optimal bin-picking system emerges. Lastly, surfacenormalmaps are employed as a basis for pose estimation. In contrast to knownapproaches, the normal maps are not used for 3D data computation but directlyfor the object localization problem, enabling the application of a new class ofsensors for bin-picking.
Sommario
Introduction - Automation and the Need for Pose Estimation.- Bin-Picking - 5 Decades of Research.- 3D Point Cloud Based Pose Estimation.- Depth Map Based Pose Estimation.- Normal Map Based Pose Estimation.- Summary and Conclusion.
Riassunto
This book
is devoted to one of the most famous examples of automation handling tasks –
the “bin-picking” problem. To pick up objects, scrambled in a box is an
easy task for humans, but its automation is very complex. In this book three
different approaches to solve the bin-picking problem are described, showing
how modern sensors can be used for efficient bin-picking as well as how classic
sensor concepts can be applied for novel bin-picking techniques. 3D point
clouds are firstly used as basis, employing the known Random Sample Matching
algorithm paired with a very efficient depth map based collision avoidance
mechanism resulting in a very robust bin-picking approach. Reducing the
complexity of the sensor data, all computations are then done on depth maps.
This allows the use of 2D image analysis techniques to fulfill the tasks and
results in real time data analysis. Combined with force/torque and acceleration
sensors, a near time optimal bin-picking system emerges. Lastly, surfacenormal
maps are employed as a basis for pose estimation. In contrast to known
approaches, the normal maps are not used for 3D data computation but directly
for the object localization problem, enabling the application of a new class of
sensors for bin-picking.
