NASA STTR 2017 Solicitation


PROPOSAL NUMBER: 171 T11.01-9896
RESEARCH SUBTOPIC TITLE: Machine Learning and Data Mining for Autonomy, Health Management, and Science
PROPOSAL TITLE: Flight Director In A Box: Using Learning to Develop Planning Agents For Exploration

STREET: 100 North East Loop 410, Suite 520 STREET: 77 Massachusetts Ave
CITY: San Antonio CITY: Cambridge
STATE/ZIP: TX  78216 - 1234 STATE/ZIP: MA  02139 - 4301
PHONE: (281) 461-7886 PHONE: (617) 253-3922

PRINCIPAL INVESTIGATOR/PROJECT MANAGER (Name, E-mail, Mail Address, City/State/Zip, Phone)
Russell Bonasso
100 North East Loop 410, Suite 520
San Antonio, TX 78216 - 1234
(281) 461-7886 Extension :708

CORPORATE/BUSINESS OFFICIAL (Name, E-mail, Mail Address, City/State/Zip, Phone)
Dr David Kortenkamp
100 North East Loop 410, Suite 520
San Antonio, TX 78216 - 1234
(281) 461-7886 Extension :704

Estimated Technology Readiness Level (TRL) at beginning and end of contract:
Begin: 2
End: 3

Technology Available (TAV) Subtopics
Machine Learning and Data Mining for Autonomy, Health Management, and Science is a Technology Available (TAV) subtopic that includes NASA Intellectual Property (IP). Do you plan to use the NASA IP under the award?

TECHNICAL ABSTRACT (Limit 2000 characters, approximately 200 words)
TRACLabs has developed a procedure integrated development environment called PRIDE that is currently being used by NASA for ISS and Orion procedures. As these procedures execute, they log all the pertinent execution information. Automated planners, developed by NASA over the years will be used to sequence these procedures to achieve goals during exploration flights or for planetary base operations. TRAClabs has successfully integrated planning and procedure execution, but humans manually code the most likely sequence of activities for the planner to use, a practice that is sub optimal and fraught with error. As flight directors and their flight control teams train for exploration using PRIDE in simulated environments, the procedure sequences they develop for exploration can be captured along with all the execution data. TRACLabs proposes to use the resulting logs, along with archived telemetry, as a basis for applying apprenticeship learning to learn what procedures should be used in a given situation and in what order. Automated planners could then ingest these learned policies during explorations operations to yield plans as they would be generated from an experienced flight control team. Further, as the planner executes plans, we contend that the learner can continue to refine its policies during exploration missions.

POTENTIAL NASA COMMERCIAL APPLICATIONS (Limit 1500 characters, approximately 150 words)
Mission planning is at the core of all space missions in order to efficiently employ high cost space assets such as astronauts, equipment, vehicles and communication links. Because of the light distances involved in exploration missions, the need for technologies that adapt over time will be of interest to all exploration activities. The "Proving Ground" and "MARS ready" phases of space exploration suggest this technology will be needed as these missions are designed and simulated. In the past at Johnson Space Center (JSC) we have worked with EVA personnel and flight directors in migrating PRIDE and planning technologies into mission control. These are the same people working on EVAs for the potential asteroid redirect mission as well as planetary base operations. We expect applications of our technology to impact several research programs, such as the new Mission Control Technologies (MCT) software being developed by NASA JSC DS, that is exploring ways to minimize the number of personnel working the flight control stations. This work will also provide a connection to automated planning technology development through NASA ARC's Automation for Operations (A4O) project and its successors.

POTENTIAL NON-NASA COMMERCIAL APPLICATIONS (Limit 1500 characters, approximately 150 words)
TRACLabs is already selling PRIDE as a commercial product to oil field services companies and is providing automation assistance to other companies for drilling operations. The companies involved have already expressed interest in licensing the new capabilities being developed in this project. We will work with them to make sure that this project meets their requirements. TRACLabs expects additional customers in the oil and gas industry will deploy PRIDE once it has been proven effective. Sierra Nevada Corporation has also purchased PRIDE licenses for use in their Dream Chaser program, which was recently selected to deliver cargo to ISS. In all of these cases, we will offer the features developed this proposal as an "add-on" to the existing PRIDE software we deliver. Thus, we can immediately move this research out into industry by leveraging our existing PRIDE user base.

TECHNOLOGY TAXONOMY MAPPING (NASA's technology taxonomy has been developed by the SBIR-STTR program to disseminate awareness of proposed and awarded R/R&D in the agency. It is a listing of over 100 technologies, sorted into broad categories, of interest to NASA.)
Algorithms/Control Software & Systems (see also Autonomous Systems)
Autonomous Control (see also Control & Monitoring)
Health Monitoring & Sensing (see also Sensors)
Process Monitoring & Control
Robotics (see also Control & Monitoring; Sensors)
Sequencing & Scheduling

Form Generated on 04-19-17 12:45