Thanks to the advances in Artificial Intelligence (AI), and in particular in automated planning & scheduling and execution, goal-oriented controllers have being developed to test degrees of autonomy for robotics systems in challenging scenarios. Despite these efforts, there is a lack of methodology for approaching the design of deliberative systems or the choice of the critical parameters or metrics under which the control systems can be compared during execution or deliberation. This paper presents the first initial results of the On-Ground Autonomy Test Environment (OGATE) over a year after its initiation. It is an ESA funded project that aims to facilitate accurate experiments on planning and execution systems for robotics. We present features of an initial instance of such system built to support the GOAC robotic software, an ESA project to demonstrate key concepts in autonomy for ESA missions.
First steps on an on-ground autonomy test environment
Contributo in atti di convegno
SMC-IT, IEEE Int. Conf. on Space Mission Challenges for Information Technologies, pp. 30–37, Laurel, Maryland, September 2014