PI-in-a-Box: A Knowledge-Based System for Space Science Experimentation (original) (raw)

I-in-a-Box: A Knowledge-Based System for Space Science Experimentation

Proceedings of the the Fifth Conference on Innovative Applications of Artificial Intelligence, 1993

The Principal Investigator (PI) in-a-Box knowledge-based system (KBS) helps astronauts perform science experiments in space. These experiments are typically costly to devise and build, and often difficult to perform. Further, the space laboratory environment is unique, ever-changing, hectic, and therefore stressful. The environment requires quick, correct reactions to events over a wide range of experiments and disciplines, including ones distant from an astronaut's main science specialty. This suggests the use of advanced techniques for data collection, analysis, and decision-making to maximize the value of the research performed. PI-in-a-Box aids astronauts with "quick look" data collection, reduction and analysis, and also with equipment diagnosis and troubleshooting, procedural reminders, and suggestions for high-value departures from the pre-planned experiment protocol. The astronauts have direct access to the system, which is hosted on a portable computer in the Spacelab module. The system is in use on the ground for mission training, and has been delivered to NASA for in-flight use on the Space Life Sciences (SLS) 2 Shuttle mission scheduled for August, 1993.

An expert system to advise astronauts during experiments: The protocol manager module

1990

Perhaps the scarcest resource for manned flight experiments-on Spacelab or on the Space Station Freedom-will continue to be crew time. To maximize the efficiency of the crew, and to make use of their abilities to work as scientist collaborators as well as equipment operators, normally requires more training in a wide variety of disciplines than is practical. The successful application of on-board expert systems, as envisioned by the "Principal Investigator in a Box" program, should alleviate the training bottleneck and provide the astronaut with the guidance and coaching needed to permit him or her to operate an experiment according to the desires and knowledge of the PI, despite changes in conditions. This report covers the Protocol Manager module of the system. The Protocol Manager receives experiment data that has been summarized and categorized by the other modules. The Protocol Manager acts on the data in real-time, by employing expert system techniques. Its recommendations are based on heuristics provided by the Principal Investigator in charge of the experiment. This prototype has been developed on a Macintosh II by employing CLIPS, a forward-chaining rule-based system, and HyperCard as an object-oriented user interface builder.

Knowledge servers: Applications of artificial intelligence to advanced space information systems

We have begun a transition from passive information systems which act only to facilitate the storage and retrieval of stereotyped data to far more active and responsive systems which can deal with widely differing forms of human knowledge. Edward Feigenbaum has coined the term 'knowledge servers' to describe this next generation of active information management systems. Among the functions of a knowledge server will be: the ability to store enormous varieties of knowledge; the ability to determine, through natural discourse, the needs of its users; the ability to summarize and pursue complex relationships in its knowledge; the ability to test and critique user hypotheses and suggest previously unseen connections resulting from those hypotheses; and the ability to communicate and collaborate with other autonomous knowledge servers. Because of complexity and variety of information relevant to future major space missions like the Space Station, these missions will act as a driv...

On the Study of the Space Environment: A Test-Bed Configuration

2013

In the context of the Space Situational Awareness (SSA) programme of ESA, it is foreseen to deploy several large robotic telescopes in remote locations to provide surveillance and tracking services for man-made as well as natural near-Earth objects (NEOs). The present project will implement a test-bed for the validation of an autonomous optical observing system in a realistic scenario, consisting of two telescopes located in Spain and Australia, to collect representative test data for precursor SSA services. It is foreseen that this test-bed environment will be used to validate future prototype software systems as well as to evaluate remote monitoring and control techniques. The test-bed system will be capable to deliver astrometric and photometric data of the observed objects in near real-time. This contribution describes the current status of the project.

The EO-1 autonomous science agent

2004

An Autonomous Science Agent, part of the New Millennium Space Technology 6 Project is currently flying onboard the Earth Observing One (EO-1) Spacecraft. This software enables the spacecraft to autonomously detect and respond to science events occurring on the Earth. The package includes software systems that perform science data analysis, deliberative planning, and run-time robust execution. This software has demonstrated the potential for space missions to use onboard decision-making to detect, analyze, and respond to science events, and to downlink only the highest value science data. As a result, ground-based mission planning and analysis functions have been greatly simplified, thus reducing operations cost. We will describe several technology infusions applications being developed. We will also describe how the software has been used in conjunction with other satellites and ground sensors to form an autonomous sensor-web.

Onboard science software enabling future space science and space weather missions

2002

On the path towards an operational Space Weather System are science missions involving as many as 100 spacecraft (Magnetospheric Constellation, DRACO, 2010). Multiple spacecraft are required to measure the macro, meso, and micro scale plasma physics that underlies Geospace phenomea. Simultaneous multi point in situ measurements enable the determination of electric current in space and the discrimination of temporal and spatial phenomena. From these quantities, the structure and dynamics of Geospace may be modeled and better understood. We work towards the day when multi point, real time data might be gathered on Earth to produce maps and forecasts of Space Weather conditions.

Onboard Science Data Analysis: Opportunities, Benefits, and Effects on Mission Design

2000

Much of the initial focus for spacecraft autonomy has been on developing new software and systems concepts to automate engineering functions of the spacecraft: guidance, navigation and control, fault protection, and resource management, However, the ultimate objectives of NASA missions are science objectives, which implies that we need a new framework for perfcmrning science data evaluation and observation planning autonomously

The Autonomous Sciencecraft Embedded Systems Architecture

2005 IEEE International Conference on Systems, Man and Cybernetics

An Autonomous Science Agent has been flying onboard the Earth Observing One Spacecraft since 2003. This software enables the spacecraft to autonomously detect and responds to science events occurring on the Earth such as volcanoes, flooding, and snow melt. This agent includes AI-based software systems that perform science data analysis, deliberative planning, and run-time robust execution. This software is in routine use to fly the EO-1 mission. In this paper we discuss the architecture used to integrate these systems and lessons learned from its multi-year flight on EO-1.

PI-in-a-box: Intelligent onboard assistance for spaceborne experiments in vestibular physiology

1988

We are constructing a knowledge-based system that will aid astronauts in the performance of vestibular experiments in two ways: it will provide realtime monitoring and control of signals and it will optimize the quality of the data obtained, by helping the mission specialists and payload specialists make decisions that are normally the province solely of a principal investigator, hence the name PI-in-a-box. An important and desirable sideeffect of this tool will be to make the astronauts more productive and better integrated members of the scientific team. The vestibular experiments are being planned by Prof. Larry Young of MIT, whose team has already performed similar experiments in Spacelab missions SL-1 and D-1, and has experiments planned for SLS-1 and SLS-2. The knowledge-based system development work, performed in collaboration with MIT, Stanford University and the NASA-Ames Research Center, addresses six major related functions: a) signal quality monitoring; b) fault diagnosis; c) signal analysis; d) interesting-case detection; e) experiment replanning; and f) integration of all of these functions within a real-time data acquisition environment. Initial prototyping work has been done in functions a) through d).