Closed Loop Execution and Recovery (CLEaR) is an artificial-intelligence computer program under devel- opment designed for automated command sequence generation, execution, monitoring, and recovery. As a component of the Deep Space Network’s (DSN’s) prototype Common Automation Engine (CAE), CLEaR relieves human operators of much of the burden of setting up, monitoring, and controlling a DSN communication station. CLEaR is also being adapted for automation of other realtime agents, such as robotic spacecraft, robotic land vehicles (rovers), and robotic aircraft. CLEaR enables a control computer at a DSN station to respond to a set of tracking goals by issuing commands to configure station hardware and software to provide requested communication services. CLEaR utilizes operational knowledge encoded into a textual declarative knowledge base to create command sequences, then executes the command sequences while monitoring their progress and dynamically modifying them on the basis of its operational knowledge when necessary. To generate a tracking plan (expressed as a control script) that satisfies the tracking goals, CLEaR utilizes an extended version of CASPER, which was described in “Software for Continuous Replanning During Execution” (NPO-20972) NASA Tech Briefs, Vol. 26, No. 4 (April 2002), page 67. Then CLEaR monitors the execution of the tracking plan and modifies the plan in response to changing requirements and/or unforeseen events.
This program was written by Forest Fisher, Barbara Engelhardt, Colette Wilklow, Steve Chien, Russell Knight, Gregg Rabideau, and Robert Sherwood of Caltech for NASA’s Jet Propulsion Laboratory.
This software is available for commercial licensing. Please contact Don Hart of the California Institute of Technology at (818) 393-3425. Refer to NPO-21040.
This Brief includes a Technical Support Package (TSP).
Software for Automation of Real-Time Agents
(reference NPO-21040) is currently available for download from the TSP library.
Don't have an account?
Overview
The document discusses the development of CLEaR (Closed Loop Execution and Recovery), an artificial intelligence program designed to automate operations at NASA's Deep Space Network (DSN) communication stations. As the number of space missions has increased, managing deep space communications has become increasingly complex. CLEaR aims to enhance the efficiency of these operations by automating the monitoring, control, execution, and recovery processes involved in antenna operations.
CLEaR is a component of the prototype Common Automation Engine (CAE) for the DSN, relieving human operators of much of the burden associated with setting up and managing communication stations. The system is designed to respond to specific tracking goals by issuing commands that configure the necessary hardware and software to provide the required communication services. It utilizes a textual declarative knowledge base to create command sequences, which are executed while monitoring their progress. If necessary, CLEaR can dynamically modify these sequences based on its operational knowledge to adapt to changing conditions or unforeseen events.
To generate tracking plans that meet the specified goals, CLEaR employs an extended version of the Continuous Activity Scheduling, Planning, Execution, and Replanning (CASPER) engine. This engine allows for the automatic production of tailored antenna tracking plans. During execution, CLEaR continuously monitors the tracking plan and makes adjustments as needed to accommodate any changes in requirements or unexpected occurrences.
The document highlights the collaborative efforts of a team from the California Institute of Technology and NASA's Jet Propulsion Laboratory, including notable contributors such as Forest Fisher, Barbara Engelhardt, and Steve Chien. The work is part of a broader initiative to automate real-time agents, which may include robotic spacecraft, land vehicles, and aircraft.
In summary, the document outlines the innovative approach taken by NASA to enhance deep space communications through automation, showcasing the potential of artificial intelligence in improving operational efficiency and adaptability in complex environments. CLEaR represents a significant advancement in the management of deep space missions, enabling more effective communication and data collection from various space exploration endeavors.
