Optimization for Solving Workcell Layouts using Gaussian Penalties for Escaping Local Minima

摘要

The main contribution of this paper is a method for optimizing the layout of workcells taking into consideration both the reachability of the robot as well as the expected cycle time. To analyse the reachability for systems using sensors to pose estimate objects, the method uses a combination of discrete samples over the space in which objects are located and a manipulability measure based on the determinant of the manipulator Jacobian. Tocomputetheexpectedcycletimefortherobot,themethodincludesasimulatedcontroller,which isoptimizedtoestimatetheperformanceofthephysicalrobot. Fortheoptimizationoftheworkcelllayoutthe proposedmethodbasedonapplyingGaussianpenaltiesinlocalminimaiscomparedtothreeexistingmethods for global optimization. For the optimization of the simulated controller three different local methods are compared along with one global.