NASA SBIR 2021-II Solicitation

Proposal Summary

Proposal Information

Proposal Number:
21-2- H9.03-2520
Phase 1 Contract #:
80NSSC21C0093
Subtopic Title:
Flight Dynamics and Navigation Technologies
Proposal Title:
Real-time Hazard Detection via Deep Learning

Small Business Concern

   
Firm:
          
Astrobotic Technology, Inc.
          
   
Address:
          
1016 North Lincoln Avenue, Pittsburgh, PA 15233
          
   
Phone:
          
(412) 682-3282                                                                                                                                                                                
          

Principal Investigator:

   
Name:
          
Kori Macdonald
          
   
E-mail:
          
kori.macdonald@astrobotic.com
          
   
Address:
          
1016 North Lincoln Avenue, 15233 - 2132
          
   
Phone:
          
(412) 682-3282                                                                                                                                                                                
          

Business Official:

   
Name:
          
Andrew Horchler
          
   
E-mail:
          
andrew.horchler@astrobotic.com
          
   
Address:
          
1016 N Lincoln Ave, PA 15233 - 2132
          
   
Phone:
          
(216) 272-3882                                                                                                                                                                                
          

Summary Details:

   
Estimated Technology Readiness Level (TRL) :                                                                                                                                                          
Begin: 3
End: 5
          
          
     
Technical Abstract (Limit 2000 characters, approximately 200 words):

HazNet is a robust hazard detection solution that leverages deep learning and hardware acceleration to achieve mission-speed performance on path-to-flight hardware. The HazNet solution seeks to maximize data use while maintaining flexibility by leveraging the independent strengths of LiDAR and camera data to produce a single hazard map. Flexibility is maintained by using two independent convolutional neural networks for computation, one for LiDAR data and one for image data, which are combined into an existing hazard map to improve knowledge, resolve unknown regions, and increase hazard map resolution. This method de-risks the transition from traditional hazard detection to deep learning-based algorithms by leveraging well-proven, rather than experimental models to identify hazards. It improves upon these traditional methods by acting on the strengths of complimentary sensors, enabled by hardware acceleration. Astrobotic proposes the development of a prototype sensor package for HazNet, while further advancing developed hazard detection models and techniques. This Phase II effort will entail five major efforts: working in collaboration with NASA and Astrobotic stakeholders to develop a reference mission and associated requirements; advancement of models developed in the Phase I effort to incorporate uncertainty and combine hazard map outputs; development and testing of custom sensor package; demonstration in a series of relevant simulations; and a final technology demonstration across a descent-like scenario in a lunar-relevant environment. 

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

Generally speaking, as NASA targets increasingly complex and challenging landing scenarios on the Moon, asteroids, Mars, icy moons, and beyond, the Agency and its commercial contractors will be looking for flexible systems like HazNet which utilize as much data as possible and as little hardware as possible to produce accurate landing solutions. HazNet will be a valuable tool not only for future CLPS missions, but also for NASA’s forthcoming Artemis landings, which are also targeting rugged polar sites.

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

HazNet’s generation of real-time maps would benefit the Department of Defense (DOD) in identifying and tracking hazards in real time. It would benefit the Department of the Interior (DOI) and Department of Agriculture (USDA), as terrain models aid in the understanding of agricultural needs, geological impacts of climate change, and improved understanding of forests, oceans, and remote regions.

          
          
     
Duration:     24
          
          

Form Generated on 02/18/2022 18:03:21