Since the dawn of the space age, unmanned spacecraft have flownblind with little or no ability to make autonomous decisions based onthe content of the data they collect. The Autonomous SciencecraftExperiment (ASE) is operating onboard the Earth Observing-1mission since 2003.The ASE software uses onboard continuous planning, robust task andgoal-based execution, and onboard machine learning and patternrecognition to radically increase science return by enablingintelligent downlink selection and autonomous retargeting. Thissoftware demonstrates the potential for space missions to useonboard decision-making to detect, analyze, and respond to scienceevents, and to downlink only the highest value science data.AI Technology

The ASE onboard flight software includes several autonomy softwarecomponents: Onboard science algorithms that analyzes the image data to detect trigger conditions such as science events, interesting features, changes relative to previous observations, and cloud detection for onboard image editing Robust execution management software using the Spacecraft Command Language (SCL) package to enable event-driven processing and low-level autonomy Continuous Activity Scheduling Planning Execution and Replanning (CASPER) software that replan activities, including downlink, based on science observations in the previous orbit cycles
Tracking Europa Surface Ice
The onboard science algorithms analyzes the images to extractstatic features and detect changes relative to previous observations.Applied to EO-1 Hyperion data, these algorithms automatically identify regions of interest including regions of change (such as flooding, ice melt, and lava flows). Using these algorithms onboard enables retargeting and search, e.g., retargeting the instrument on a subsequentorbit cycle to identify and capture the full extent of a flood. On futureinterplanetary space missions, onboard science analysis will enable capture of short-lived science phenomena at the finest time-scaleswithout overwhelming onboard memory or downlink capacities. Examples include: eruption of volcanoes on Io, formation of jets on comets, and phase transitions in ring systems. Generation of derived scienceproducts (e.g., boundary descriptions, catalogs) and change-based triggering will also reduce data volumes to a manageable level for extended duration missions that study long-term phenomena such as atmospheric changes at Jupiter and flexing and cracking of the ice crust on Europa.The onboard planner (CASPER) generates mission operations plansfrom goals provided by the onboard science analysis module. Themodel-based planning algorithms enables rapid response to a widerange of operations scenarios based on a deep model of spacecraftconstraints, including faster recovery from spacecraft anomalies. Theonboard planner accepts as inputs the science and engineeringgoals and ensure high-level goal-oriented behavior. The robust execution system (SCL) accepts the CASPER-derived planas an input and expands the plan into low-level commands. SCL monitorsthe execution of the plan and has the flexibility and knowledge toperform event-driven commanding to enable local improvements inexecution as well as local responses to anomalies.Problem

Constrained downlink resources limit the science return of current and futurespace missions.Impact


Short-Lived Eruption on Io
Demonstration of these capabilities in a flight environment opensup tremendous new opportunities in planetary science, space physics,and earth science that would be unreachable without this technology.This technology:

• Dramatically increases the science per fixed downlink by enabling downlink of the highest priority science data.
  
• Enables study of short-lived science events (such as volanic eruptions, dust storms, etc.)
  
• Reduces downtime lost to anomalies due to robust execution enabled by autonomy software.
  
• Reduces instrument setup time by using autonomy software take advantage of execution information to streamline operations.
  

Status

			Mission		Last Week		Yesterday				Upcoming
	Images Taken		31199		126		19				21
	Sensorweb		2648		2		1				0
	Science Scenarios Executed		1470		0		0				0
	Positive Triggers		257		0		0
	Ground Contacts		28960		103		14				22
	X-Band		10319		46		6				9
	S-Band		18641		57		8				13

Description


+ ASE Mission Concept Animation
A typical ASE demonstration scenario involves monitoring of activevolcano regions such as Mt. Etna in Italy. Hyperion data have beenused in ground-based analysis to study this phenomenon. The ASEconcept is applied as follows:

1. Initially, ASE has a list of science targets to monitor that have been sent as high-level goals from the ground.
   
2. As part of normal operations, CASPER generates a plan to monitor the targets on this list by periodically imaging them with the Hyperion instrument. For volcanic studies, the IR and near IR bands are used.
   
3. During execution of this plan, the EO-1 spacecraft images Mt. Etna with the Hyperion instrument.
   
4. The onboard science algorithms analyzes the image and detects a fresh lava flow. Based on this detection the image is downlinked. Had no new lava flow been detected, the science software would generate a goal for the planner to acquire the next highest priority target in the list of targets. The addition of this goal to the current goal set triggers CASPER to modify the current operations plan to include numerous new activities in order to enable the new science observation.
   
5. The SCL software executes the CASPER generated plans in conjunction with several autonomy elements.
   
6. This cycle is then repeated on subsequent observations.