6533b827fe1ef96bd1286e6f

RESEARCH PRODUCT

Real-time human collision detection for industrial robot cells

Petter S. EppelandGeir HovlandAtle AalerudErind Ujkani

subject

0209 industrial biotechnologyComputer sciencebusiness.industryPoint cloudProcess (computing)02 engineering and technologyBenchmarkingCollisionlaw.inventionIndustrial robot020901 industrial engineering & automationlawCollision detectionComputer visionSegmentationArtificial intelligencebusinessCollision avoidance

description

A collision detection system triggering on human motion was developed using the Robot Operating System (ROS) and the Point Cloud Library (PCL). ROS was used as the core of the programs and for the communication with an industrial robot. Combining the depths fields from the 3D cameras was accomplished by the use of PCL. The library was also the underlying tool for segmenting the human from the registrated point clouds. Benchmarking of several collision algorithms was done in order to compare the solution. The registration process gave satisfactory results when testing the repetitiveness and the accuracy of the implementation. The segmentation algorithm was able to segment a person represented by 4–6000 points in real-time successfully.

yearjournalcountryeditionlanguage
2017-11-012017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)
https://doi.org/10.1109/mfi.2017.8170368