Authors:
Stefan-Octavian Bezrucav
;
Yifan Liu
and
Burkhard Corves
Affiliation:
Institute of Mechanism Theory, Machine Dynamics and Robotics, RWTH Aachen University, Eilfschornsteinstrasse 18, 52062 Aachen, Germany
Keyword(s):
Task Planning, Mobile Manipulators, MILP, CP, Temporal AI Planning.
Abstract:
Task planning has become one of the most important components of the control system for teams of cooperating robotic systems in complex scenarios. It plays such a critical role, as it must determine, order and assign a high variety of different tasks to the involved actors, such that at the end, the goals are reached while some metric, as the total execution time, is minimized. In this paper the analysis of three task planning approaches, mixed-integer linear programming (MILP), constraint programming (CP) and automated temporal planning (TP), with respect to three criteria is targeted. These criteria are the CPU time for plan generation, the plan makespan and the flexibility of the modelling approach. For the analysis, an intricate scenario in a kitchen environment with a team of multiple mobile manipulators is developed. The models and results are then compared to derive the advantages and disadvantages of each strategy.