Abstract
Automated Planning & Scheduling Systems are nowadays applied in a wide range of spacecraft, from satellites to Mars rovers. The planner is responsible for the generation of valid plans that determine the activities to be performed by the spacecraft, given a set of goals and constraints (the problem), and taking into consideration the status of the spacecraft and environment. Therefore, it represents a critical system that needs to be strictly validated and verified. This paper presents a benchmarking tool called RoBen intended to characterize the performance of timeline planning systems. Using a number of metrics and heuristics, RoBen can generate synthetic problems of a given complexity in order to stress planners at different levels. At the same time, we are looking for properties that could help us to determine when a problem is unsolvable. © 2012 by Juan Delfa Victoria, TU Darmstadt, University of Surrey, European Space Agency.