Representing Spacecraft Mission Planning Knowledge in ASPEN

2003

This paper gives a short overview of a software system developed to support mission planning tasks in the ESA program called Mars-Express. A system named Mexar is described that synthesizes spacecraft operation commands for downlinking the on-board memory according to mission planners requirements. The tool is based on a constraintbased representation, a family of problem solving algorithms and a sophisticated user frontend that allows to understand and manipulate different features of both the current problem and the proposed solution.

2011

Mission planning is central to space mission operations and has benefited from advances in model-based planning software, but developing a planning model still remains a difficult task. Mission planning constraints arise from many sources, including simulators and engineering specification documents. Ensuring that these constraints are correctly represented in the planner’s model is a challenge. As mission constraints evolve, planning domain modelers must add and update model constraints efficiently using the available source data, catching errors quickly, and correcting the model. We describe the current state of the practice in designing model-based mission planning tools and the challenges facing model developers. We then propose an Interactive Model Development Environment (IMDE) to configure mission planning systems by integrating modeling and simulation environments to reduce model editing time, generate simulations automatically to evaluate plans, and identify modeling errors...

2007

Modern planning and scheduling systems are capable of dealing with the size and complexity of many real world problems. However, mission critical planning is still often done by humans. Even if only a couple of plans are produced (“Master Plan” and “Plan B”), human experts evaluate multiple alternatives, think of contingencies, consider the likelihood of failure of various steps, and account for schedule slack and plan flexibility. Computers can evaluate thousands of alternative scenarios, but the solutions they ultimately produce are often not convincing enough for expert decision makers to trust human lives or mission critical operations to computer decisions. Further, automated systems often require significant changes in the way people operate, which in high-stakes high-pressure environments leads to rejection of the system by the users. In this paper we describe the decision support functionality of the Coordinated Multi-source Maintenance on Demand (CMMD) system. CMMD is desig...

1999

On May 17th 1999, NASA activated for the first time an AI-based planner/scheduler running on the flight processor of a spacecraft. This was part of the Remote Agent Experiment (RAX), a demonstration of closedloop planning and execution, and model-based state inference and failure recovery. This paper describes the RAX Planner/Scheduler (RAX-PS), both in terms of the underlying planning framework and in terms of the fielded planner. RAX-PS plans are networks of constraints, built incrementally by consulting a model of the dynamics of the spacecraft. The RAX-PS planning procedure is formally well defined and can be proved to be complete. RAX-PS generates plans that are temporally flexible, allowing the execution system to adjust to actual plan execution conditions without breaking the plan. The practical aspect, developing a mission critical application, required paying attention to important engineering issues such as the design of methods for programmable search control, knowledge acquisition and planner validation. The result was a system capable of building concurrent plans with over a hundred tasks within the performance requirements of operational, mission-critical software.

Proceedings of the International Conference on Automated Planning and Scheduling

In 2013 the Alphasat spacecraft will be launched: in addition to its main commercial payload, four Technology Demonstration Payloads (TDPs) will fly on-board. The different payloads are provided by different research institutes, which will be able to define in-orbit demonstration tests of these new technologies. To optimize this opportunity, coordination of the different, possibly conflicting, payload operations is required. A software system to support the management of the TDP operations has been developed. While this system is intended to be completely automated (i.e., without any human intervention in the nominal case), it has been designed to keep all the different users (system and TDP operators) in the loop. This paper presents this system and in particular focuses on its core: the planning engine.

2002

The New Millennium Remote Agent (NMRA) vSll be the first AI system to control an actual spacecraft. The spacecraft domain raises a number of challenges for planning and execution, ranging from extended agency and long-term planning to dynamic recoveries and robust concurrent execution, all in the presence of tight real-time deadlines, changing goals, scarce resource constraints, and a v-ide variety of possible failures. We believe NMRA is the first system to integrate closed-loop planning and e.xecution of concurrent temporal plans, and the first autonomous system that v-ill be able to achieve a sustained multi-stage multiyear mission v-ithout communication or guidance from earth.

2015

Modern planning and scheduling systems are capable of dealing with the size and complexity of many real world problems. However, mission critical planning is still often done by humans. Even if only a couple of plans are produced (“Master Plan ” and “Plan B”), human experts evaluate multiple alternatives, think of con-tingencies, consider the likelihood of failure of various steps, and account for schedule slack and plan flexibil-ity. Computers can evaluate thousands of alternative scenarios, but the solutions they ultimately produce are often not convincing enough for expert decision makers to trust human lives or mission critical operations to computer decisions. Further, automated systems often require significant changes in the way people operate, which in high-stakes high-pressure environments leads to rejection of the system by the users. In this paper we describe the decision support func-tionality of the Coordinated Multi-source Maintenance on Demand (CMMD) system. CMMD is d...

ICAPS Workshop on Moving Planning and Scheduling Systems into the Real World, 2007

Modern planning and scheduling systems are capable of dealing with the size and complexity of many real world problems. However, mission critical planning is still often done by humans. Even if only a couple of plans are produced (“Master Plan” and “Plan B”), human experts evaluate multiple alternatives, think of contingencies, consider the likelihood of failure of various steps, and account for schedule slack and plan flexibility. Computers can evaluate thousands of alternative scenarios, but the solutions they ultimately produce are ...

2005

This paper describes aspects of our plan validation tool, VAL. The tool was initially developed to support the 3rd International Planning Competition (IPC), but has subsequently been extended in order to exploit its capabilities in plan validation and development. In particular, the tool has been extended to include advanced features of PDDL2.1 that were untested in the 3rd IPC but which have proved important in an application to mixed-initiative planning in a space operations project. The tool has also been extended to keep abreast of developments in PDDL, providing critical support to participants and organisers of the 4th IPC.

AIAA Scitech Forum, 2019

Automation is gaining momentum in spacecraft operations, however, at a much slower pace than comparable application domains. The reasons behind slow adoption is (1) the need for high reliability and (2) the limited interaction between human operators and the automated systems. For automated systems to be adopted and trusted by humans, humans need to gain intuition about the decision making process of the automated system and trust in its execution [1]. In this paper, we present how simulation and visualization can enhance adoption of an automated on-board activity scheduling system, specifically in the context of Mars2020 rover mission [2]. The visualization aims to communicate to the users degree of variance and uncertainty in possible schedule execution. Our preliminary validation results suggest that the proposed visualization increases operators' confidence in-and likelihood of adopting-the automated scheduling system.