Published: October 15, 2018
Jeffrey Mahler, Rob Platt, Alberto Rodriguez, Matei Ciocarlie, Aaron Dollar, Renaud Detry, Maximo Roa, Holly A. Yanco, Adam Norton, Joseph A. Falco, Karl Van Wyk, Elena R. Messina, Jurgen Leitner, Oliver Brock, Odhner Lael, Andrey Kurenkov, Matthew Matl, Ken Goldberg
Automated grasping has a long history of research that is increasing due to interest from industry. One Grand Challenge for robotics is Universal Picking: the ability to robustly grasp a broad variety of objects in diverse environments for applications from warehouses to assembly lines to homes. Although many researchers now openly share code and data, it is challenging to compare and/or reproduce experimental results to identify which aspects of which approaches work best due to variations in assumptions and experimental protocols, e.g., sensors, lighting, robot arms, grippers, and objects. This editorial discusses one possible metric for grasping, derived from industrial measures of performance: mean picks per minute.
Citation: IEEE Transactions on Automation Science and Engineering
Pub Type: Journals
robotic grasping, performance evaluation, benchmarking
Created October 15, 2018, Updated October 18, 2018