NASA SBIR 2020-I Solicitation

Proposal Summary

 20-1- A2.02-5722
 Unmanned Aircraft Systems (UAS) Technologies
 PreSound: UAV Diagnostic System Enabled by Acoustics and Vibration-Based Machine Learning
SMALL BUSINESS CONCERN (Firm Name, Mail Address, City/State/Zip, Phone)
GreenSight Agronomics, Inc.
12 Channel Street, Suite 605
Boston, MA 02210
(617) 633-4919

Principal Investigator (Name, E-mail, Mail Address, City/State/Zip, Phone)

James Peverill
12 Channel St, Suite 605 Boston, MA 02210 - 2318
(339) 237-1291

Business Official (Name, E-mail, Mail Address, City/State/Zip, Phone)

Joel Pedlikin
12 Channel St, Suite 605 Boston, MA 02210 - 2318
(617) 633-4919
Estimated Technology Readiness Level (TRL) :
Begin: 2
End: 5
Technical Abstract (Limit 2000 characters, approximately 200 words)

A small, inexpensive UAV that takes off, performs a mission, lands, recharges, and safely stows itself has myriad applications.  But such systems require pre-flight inspections conducted by humans. This requirement is a major barrier to fully automated UAV operations.  To address this, we propose “PreSound”: a system that uses vibration and acoustic data, combined with machine learning, to replace preflight visual inspections.  PreSound does not add any significant equipment to the UAV, but intelligently repurposes hardware already on most UAVs: accelerometers, computers, and small microphones. Combined with the vehicle’s motors and propellers, this is all the hardware necessary to create a vibration and acoustic stimulus and measurement device to conduct a pre-flight test and determine whether the airframe is safe to fly.  Each UAV motor, running in reverse, will cycle through its entire range of speeds. An accelerometer and microphone will collect data from each of the motors. Defects such as loose screws, frame cracks, and broken propellers will change how the airframe vibrates and the resulting sounds. Analyzing these samples to determine whether they come from a defect falls to a pre-trained machine learning classification network that runs on the on-board computer after data collection is complete.

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

NASA has taken a leading role in sUAS integration, urban air mobility and the NextGen Airspace management program. PreSound fits into these efforts, representing a means to verify the integrity of any unmanned airframe without a hands-on inspection. As such, it will be a crucial enabler to future UAV systems that will operate on a day-to-day basis without the intervention of humans, and is a key driver to the safe adoption of autonomous vehicles in the national airspace. 

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

GreenSight already maintains a fleet of over 100 aircraft which fly daily autonomous missions  and would make immediate use of Presound for automated pre-flight inspections.  Many other companies are also developing fully autonomous UAV systems, both for commercial and military application, and would happily pay for a PreSound system to electronically ‘inspect’ their UAV before takeoff.  

Duration: 6

Form Generated on 06/29/2020 21:09:59