Publication: Improving the Sequence of Robotic Tasks with Freedom of Execution
The workflow of industrial robots consists of a series of tasks that have to be repeated several times. The efficiency with which the robot performs its tasks is important for most production areas. The more tasks a robot can complete in a time interval, the more benefits it offers the company. Most tasks have a certain degree of freedom in their execution. For example, closed contour tasks can be started and finished at any point on the curve, or there are a number of possible start orientations of the end effector. We propose a method to improve the given sequence of robot tasks by providing some freedom to (i) the starting point along the curve, (ii) the orientation of the end effector, and (iii) a robot configuration. The proposed approach does not depend on the production domain or the algorithm used to construct the initial task sequence.
We propose to apply hierarchical optimization. Its goal is to perform a fast local search on each nested stage instead of applying slow global optimization techniques to the whole problem. We define three nested stages. Each outer level depends on the results of the optimization at the inner level.
The algorithm showed a significant improvement in production time for the cutting-deburring test instances, i.e. it improved the time by 38% for the instances with 15 holes in 68 seconds. The evaluation results are available online in MS Excel 2007 format here. Further details can be found in the publication.