Proposal Number:          21-1- T10.05-2174

          

          

   

Subtopic Title:
      Integrated Data Uncertainty Management and Representation for Trustworthy and Trusted Autonomy in Space

          

          

   

Proposal Title:
      Multi-agent and Optimization Reasoner for Space Exploitation (MORSE)

          

          

   

Firm:

          

XAnalytix Systems

          

   

Address:

          

9424 Pinyon Court, Clarence Center, NY 14032 - 9136

          

   

Phone:

          

(716) 741-6395                                                                                                                                                                                

          

   

Name:

          

Rochester Institute of Technology

          

   

Address:

          

Rochester Institute of Technology, NY 14623 -

          

   

Phone:

          

(585) 475-6062                                                                                                                                                                                

          

   

Name:

          

Dr. Katie McConky

          

   

E-mail:

          

katie.mcconky@rit.edu

          

   

Address:

          

Rochester Institute of Technology, NY 14623 -

          

   

Phone:

          

(585) 475-6062                                                                                                                                                                                

          

   

Name:

          

Mrs. Pamela Crassidis

          

   

E-mail:

          

pcrassidis@gmail.com

          

   

Address:

          

9424 Pinyon Court, NY 14032 - 9136

          

   

Phone:

          

(716) 741-6395                                                                                                                                                                                

          

   

Estimated Technology Readiness Level (TRL) :                                                                                                                                                          
Begin: 2
End: 4

          

          

     

Technical Abstract (Limit 2000 characters, approximately 200 words):

Future space missions will rely heavily on automated multi-agent cyber-physical-human teams to perform a number of tasks, such as robotic servicing, habitat maintenance, health management, etc. In order for these multi-agents to become a reality, trust in them and uncertainty quantification will need to be factored into decision making policies by the system participants. Even if one assumes perfect information the problem is NP-Hard, thus timely optimal solutions are unachievable. The central objective of the proposed technology is to provide near optimal mission planning for autonomous multi-agents with uncertain and possibly untrustworthy data sources using a hybrid deep reinforcement learning-optimization approach. A new architecture will be developed under this optimization approach that will allow for consideration of uncertainty and trustworthiness in planning decisions. A use-case that incorporates realistic uncertainties will be employed to provide metrics on the proposed approach. The use-case involves multiple satellites working in coordination to provide vital information to ground agents, each with a task of resupplying outlying bases. Past results by the investigators provide a basis-for-optimism that the proposed approach is viable.

 

The Phase I effort will focus on extensive simulation studies and analyses.  This will build a foundation to develop benchmark testing at the onset of Phase II, with the end of this work being a fully functional demonstration unit.

          

          

     

Potential NASA Applications (Limit 1500 characters, approximately 150 words):

NASA’s Cyber-Physical Systems Modeling and Analysis Initiative was developed to support future space exploration missions.  Autonomous multi-agent cyber-physical-human teams will be a vital aspect of this initiative. Past realizations to minimize the impact of costly validation and verification (V&V) processes resulted in minimally scoped autonomous operations. Current V&V processes for autonomous space operations will clearly require a much high level of trustworthiness than ever before, which will be provided by the proposed technology.

          

          

     

Potential Non-NASA Applications (Limit 1500 characters, approximately 150 words):

An obvious example involves the intelligent manufacturing sector, which integrates information technology and manufacturing technology.  A large sector that has led to a disruptive impact is the driverless automobile sector. Both sectors will rely heavily on multi-agent cyber-physical-human teams. The proposed technology is easily extendable to these and other non-NASA sector applications.

          

          

     

Duration:     13