Aerospace & Defense Technology - October 2021 - 7
Unmanned Vehicles & Robotics
Debris
Rock
Detection: Mine
Type: M1
Confidence: 0.997
Rock
AutoTRap Onboard processes sonar data in real time to accurately differentiate between objects of interest,
such as mines, and other objects, such as rocks and debris.
the ground. However, CNNs must be
trained on mass quantities of imagery
to detect objects of interest, where different
images show the objects at different
angles, lighting conditions, and so
on. Since sonar data is much less abundant,
the training and development of
accurate networks requires more customization,
according to Camille Monnier,
Principal Scientist at Charles River
and lead computer vision developer for
AutoTRap Onboard.
Networks also face qualitative differences
for sonar detection, such as the
unique behavior of sonar shadowing.
Consider a typical sonar imaging workflow.
A surveying AUV sweeps over the
seafloor at a controlled 5 meters in altitude,
emitting acoustic pulses and receiving
reflected signals in return. For
System View
Swarm
Assets
Command &
Control
Stations
Onboard Autonomy Architecture
Environment
Forescast Models
Landmark
Models
an AUV using side scan sonar, the resultant
picture stretches out 50 meters
either side of the vehicle's track. Objects
such as rocks on a sandy seafloor are indicated
by bright spots in the image.
Each rock blocks acoustic waves from
hitting the region behind it, creating a
shadow. A rock 50 meters away from
the track casts a shadow much longer
than a rock 5 meters away.
Acoustic shadowing gives the same
types of objects drastically different appearances
in different parts of a sonar
image. These differences complicate the
success of object detection systems.
However, the unique shadowing of an
object also provides information on its
shape. AutoTRap Onboard processes
this shadowing to increase the robustness
and accuracy of detection.
HMI
Operational View
Creating the underlying software for
AutoTRap Onboard has at times involved
just as much work as the detection
model. Sonar remains a relatively
niche technology that lacks the same
level of standardization as digital optical
photography. In fact, it was the standardization
of camera hardware interfaces
that (partially) enabled the rapid development
of optical deep learning software
in the early 2010s, according to Andrey
Ost, Senior Software Engineer at Charles
River and lead software developer for AutoTRap
Onboard. By contrast, standardization
for sonar data can be nonexistent,
and software solutions must each pave
their own way through the data. Sonar
systems can also lack output APIs. AutoTRap
Onboard reads the bytes directly
off of raw sonar output files.
UAV
Communication
Handler
Communication
Modems
Onboard Mission
Monitoring
External
Sensors
Sensoring for
Situational Awareness
World
Model
Mission Planning
and
Dynamic Replanning
Powered by
HAP
Navigation
Sensors
Positioning,
Navigation, & Timing
Behavior Engine
Vehicle Native
Auto-pilot
USV
Actuators
IN
Monitor
Process
Model
Learned
Meta-Strategies
Health and Status Monitoring
OUT
Adjustments
Performance Manager/Coach
Whale Detected!
Autonomy architecture by
charles river analytics
Ost recently redesigned the data processing
pipeline for AutoTRap Onboard
to be more swappable to different sonar
systems with different data interfaces.
Also, the product now constructs its
own sonar imagery from raw sonar
data, based on standard assumptions.
These changes have addressed and anticipated
some of the basic software engineering
issues around sonar.
Advances will be needed in many
areas in addition to software engineering
and computer vision for AUVs to
reach a truly autonomous state. Scientists
and engineers at a number of companies
are working on many of these
associated autonomy technologies, including
integration between computer
vision and navigation, dynamic adaptation
for changing environments, cooperation
between autonomous vehicles,
and explainable and robust AI.
All these technologies must come together
to simplify and advance the understanding
of the seafloor. But computer
vision and object detection will
play a key role. Using them, AUVs will
look to the bottom, where the sands
move, the seasons change, and vegetation
grows only to recede once again.
They will find what is there, the good
things and the bad. They will make the
depths known.
This article was written by Mordechai
UUV
A truly autonomous architecture requires the integration of many sophisticated technologies.
Aerospace & Defense Technology, October 2021 www.aerodefensetech.com
Intro
Cov
ToC
+
-
A
µ
Rorvig, Science Writer, Charles River Analytics
(Cambridge, MA). For more information,
visit http://info.hotims.com/79418-500.
7
È
http://info.hotims.com/79418-500
http://www.aerodefensetech.com
http://info.hotims.com/79418-967
Aerospace & Defense Technology - October 2021
Table of Contents for the Digital Edition of Aerospace & Defense Technology - October 2021
Aerospace & Defense Technology - October 2021 - Intro
Aerospace & Defense Technology - October 2021 - Sponsor
Aerospace & Defense Technology - October 2021 - Cov1
Aerospace & Defense Technology - October 2021 - Cov2
Aerospace & Defense Technology - October 2021 - 1
Aerospace & Defense Technology - October 2021 - 2
Aerospace & Defense Technology - October 2021 - 3
Aerospace & Defense Technology - October 2021 - 4
Aerospace & Defense Technology - October 2021 - 5
Aerospace & Defense Technology - October 2021 - 6
Aerospace & Defense Technology - October 2021 - 7
Aerospace & Defense Technology - October 2021 - 8
Aerospace & Defense Technology - October 2021 - 9
Aerospace & Defense Technology - October 2021 - 10
Aerospace & Defense Technology - October 2021 - 11
Aerospace & Defense Technology - October 2021 - 12
Aerospace & Defense Technology - October 2021 - 13
Aerospace & Defense Technology - October 2021 - 14
Aerospace & Defense Technology - October 2021 - 15
Aerospace & Defense Technology - October 2021 - 16
Aerospace & Defense Technology - October 2021 - 17
Aerospace & Defense Technology - October 2021 - 18
Aerospace & Defense Technology - October 2021 - 19
Aerospace & Defense Technology - October 2021 - 20
Aerospace & Defense Technology - October 2021 - 21
Aerospace & Defense Technology - October 2021 - 22
Aerospace & Defense Technology - October 2021 - 23
Aerospace & Defense Technology - October 2021 - 24
Aerospace & Defense Technology - October 2021 - 25
Aerospace & Defense Technology - October 2021 - 26
Aerospace & Defense Technology - October 2021 - 27
Aerospace & Defense Technology - October 2021 - 28
Aerospace & Defense Technology - October 2021 - 29
Aerospace & Defense Technology - October 2021 - 30
Aerospace & Defense Technology - October 2021 - 31
Aerospace & Defense Technology - October 2021 - 32
Aerospace & Defense Technology - October 2021 - 33
Aerospace & Defense Technology - October 2021 - 34
Aerospace & Defense Technology - October 2021 - 35
Aerospace & Defense Technology - October 2021 - 36
Aerospace & Defense Technology - October 2021 - 37
Aerospace & Defense Technology - October 2021 - 38
Aerospace & Defense Technology - October 2021 - 39
Aerospace & Defense Technology - October 2021 - 40
Aerospace & Defense Technology - October 2021 - 41
Aerospace & Defense Technology - October 2021 - 42
Aerospace & Defense Technology - October 2021 - 43
Aerospace & Defense Technology - October 2021 - 44
Aerospace & Defense Technology - October 2021 - Cov3
Aerospace & Defense Technology - October 2021 - Cov4
https://www.nxtbook.com/smg/techbriefs/24ADT09
https://www.nxtbook.com/smg/techbriefs/24ADT08
https://www.nxtbook.com/smg/techbriefs/24ADT06
https://www.nxtbook.com/smg/techbriefs/24ADT05
https://www.nxtbook.com/smg/techbriefs/24ADT04
https://www.nxtbook.com/smg/techbriefs/24ADT02
https://www.nxtbook.com/smg/techbriefs/23ADT12
https://www.nxtbook.com/smg/techbriefs/23ADT10
https://www.nxtbook.com/smg/techbriefs/23ADT09
https://www.nxtbook.com/smg/techbriefs/23ADT08
https://www.nxtbook.com/smg/techbriefs/23ADT06
https://www.nxtbook.com/smg/techbriefs/23ADT05
https://www.nxtbook.com/smg/techbriefs/23ADT04
https://www.nxtbook.com/smg/techbriefs/23ADT02
https://www.nxtbook.com/smg/techbriefs/22ADT12
https://www.nxtbook.com/smg/techbriefs/22ADT10
https://www.nxtbook.com/smg/techbriefs/22ADT09
https://www.nxtbook.com/smg/techbriefs/22ADT08
https://www.nxtbook.com/smg/techbriefs/22ADT06
https://www.nxtbook.com/smg/techbriefs/22ADT05
https://www.nxtbook.com/smg/techbriefs/22ADT04
https://www.nxtbook.com/smg/techbriefs/22ADT02
https://www.nxtbook.com/smg/techbriefs/21ADT12
https://www.nxtbook.com/smg/techbriefs/21ADT10
https://www.nxtbook.com/smg/techbriefs/21ADT09
https://www.nxtbook.com/smg/techbriefs/21ADT08
https://www.nxtbook.com/smg/techbriefs/21ADT06
https://www.nxtbook.com/smg/techbriefs/21ADT05
https://www.nxtbook.com/smg/techbriefs/21ADT04
https://www.nxtbook.com/smg/techbriefs/21ADT02
https://www.nxtbookmedia.com