EDF Scheduling of Industrial Robotic Manufacturing Tasks
Pallovi Romero, Albert M. K. Cheng · 2019
As industry leans more towards automation, there has been an increase in productivity with the integration of industrial robots. Industrial robots are able to provide greater flexibility with stringent timing and reliability in addition to functional correctness. We ask the question whether the traditional task scheduling algorithm-Earliest Deadline First (EDF)-is suitable for robots in an industrial setting. A task set is schedulable under EDF if and only if it satisfies the condition that the total processor utilization due to the task set is less than or equal to 1, for a set of periodic real-time tasks {T1, T2,..., Tn}. The selected scheduling algorithm is optimal for scheduling a set of independent and preemptable tasks, which is heavily applicable to the industrial robotic manufacturing industry. In this paper, we address the scheduling problem for a single processor device that executes preemptable time-critical tasks and evaluate its performance and explore the possibilities of modified EDF in a multiprocessor environment. The full solution to the multi-robot coordination problem relies on an efficient solution to this single robot scheduling problem. For real-time scheduling problems like the one that we are exploring, the criteria will be scheduled in polynomial time of any task set which satisfies some specific conditions. The overall performance of EDF in both uniprocessor and multiprocessor states will be explored.