Using Artificial Intelligence Planning to Automate Science Image Data Analysis
In recent times, improvements in imaging technology have made available an incredible array of information in image format.
Engineering topics
Publications and source records attributed to Chien, S..
In recent times, improvements in imaging technology have made available an incredible array of information in image format.
Automated planning and scheduling technology - we'll call it automated planning systems, for the sake of brevity-is applicable to a wide spectrum of spaceflight missions, from those with limited onboard computational capabilities, such as Lunar Prospector, to those with highly sophisticated software, such as Cassini.
In recent times, improvements in imaging technology have made available an incredible array of information in image format.
One important approach to enhancing software re-use is through the creation of large-scale software libraries.
This paper describes an architecture being implemented for an autonomous Deep Space Tracking System (DS-T).
In order to scale-up to real-world problems, planning systems must be able to replan in order to deal with changes in problem context. In this paper we describe hierarchical task network and operatorbased re-planning techniques which allow adaptation of a previous plan to account for problems associated with executing plans in real-world domains with uncertainty, concurrency, changing objectives.
This paper describes the DATA-CHASER Automated Planner/Scheduler (DCAPS) system which automated generation and repair of command sequences for the DATA-CHASER shuttle payload.
This paper describes the Deep Space Network Antenna Operations Planner (DPLAN), a system for automatically generating antenna tracking plans for an automated set of highly sensitive radio science and telecommunications antennas. DPLAN accepts current equipment configuration information and a set of requested track services and uses a knowledge base of antenna operations procedures to produce a plan of activities to provide the services using the allocated equipment.
The Deep Space One (DS1) mission, scheduled to fly in 1998, will be the first NASA spacecraft to feature an on-board planner. The planner is part of an artificial intelligence based control architecture that comprises the planner/scheduler, a plan execution engine, and a model-based fault diagnosis and reconfiguration engine...This paper describes the on-board planning and scheduling component of the DS1 autonomy architecture.
This paper describes tha Demand Access Network Scheduler (DANS) system for automatically scheduling and rescheduling resources for a network of communication antennas. DANS accepts a baseline schedule and supports rescheduling of antenna and subsystem resources to satisfy tracking goals in the event of changing track requests, equipment outages, and inclement weather.
This paper describes the application of Artificial Intelligence techniques for plan generation, plan execution, and plan monitoring to automate a Deep Space Communication Station. This automation allows a Communication station to respond to a set of tracking goals by appropriately reconfiguring the communications hardware and software to provide the requested communications services.
In February 1995, sequence-of-events (SOE)-driven automation technology was demonstrated for a Voyager telemetry downlink track at DSS 13. This demonstration entailed automated generation of an operations procedure (in the form of a temporal dependency network) from project SOE information using artificial intelligence planning technology and automated execution of the temporal dependency network using the link monitor and control operator assistant system. This article describes the overall approach to SOE-driven automation that was demonstrated, identifies gaps in SOE definitions and project profiles that hamper automation, and provides detailed measurements of the knowledge engineering effort required for automation.
In February 1995, sequence-of-events (SOE)-driven automation technology was demonstrated for a Voyager telemetry downlink track at DSS 13. This demonstration entailed automated generation of an operations procedure (in the form of a temporal dependency network) from project SOE information using artificial intelligence planning technology and automated execution of the temporal dependency network using the link monitor and control operator assistant system. This article describes the overall approach to SOE-driven automation that was demonstrated, identifies gaps in SOE definitions and project profiles that hamper automation, and provides detailed measurements of the knowledge engineering effort required for automation.
The Multimission VICAR Planner (MVP) system is an AI planning system which constructs.
ract describes work in developing knowledge base editing and debugging tools for the Multimission VICAR Planner (MVP) system. MVP uses artificial intelligence planning techniques to automatically construct executable complex image processing procedures (using models of the smaller constituent image processing requests made to the JPL Multimission Image Processing Laboratory.
This paper describes several major obstacles to the fielding of planning systems.
This paper describes the Multimission VICAR Planner [Chien 1994] (MVP) system, which use Artificial Intelligence (AI) Planning techniques [Iwasaki & Friedland, 1985, Pemberthy & Weld, 1992, Stefik, 1981] to automatically construct executable complex image processing procedures.
This article shows how rational analysis can be used to minimize learning cost for a general class of statistical learning problems. We discuss the factors that influence learning cost and show that the problem of efficient learning can be cast as a resource optimization problem. Solutions found in this way can be significantly more efficient than the best solutions that do not account for these factors. We introduce a heuristic learning algorithm that approximately solves this optimization problem and document its performance improvements on synthetic and real-world problems.