Talk

14-Novitzky

Talk.14-Novitzky History

Hide minor edits - Show changes to output

Changed lines 20-21 from:
* AUVs
* Payload Autonomy
to:
* Behavior Development
* Simulation
* Aquaticus
Changed lines 5-6 from:
!!!! %color=#7777BB% [[Talk.13-Robinette | Prev-Talk]]%%  | \
%color=#7777BB%[[Talk.15-Novitzky | Next-Talk]]%% | \
to:
!!!! %color=#7777BB% [[Talk.13-Novitzky | Prev-Talk]]%%  | \
%color=#7777BB%[[Talk.15-SeaMachines | Next-Talk]]%% | \
Changed lines 8-19 from:
%color=#7777BB%[[Talk.ListingSorted|Talks-Sorted]]%% 


!! Talk-14:
''OceanServer Iver3-580 EP Autonomous Underwater Vehicle Remote Helm Functionality''

!!!!%color=#449944% '''Bob Anderson, Daryl Slocum, Hunter Brown, L3 Ocean Server'''


Historically most Autonomous Underwater Vehicles (AUVs) have been closed systems. Any changes require contracting the manufacturer for a custom design change, which are costly in time and money. In addition, the expanding role of AUVs has users looking for a more reliable
and versatile vehicle to perform various tasks. The OceanServer Remote Helm on the Iver3 AUV provides a fully functional and open system where the users can install their hardware and make software extensions to the vehicle without the requirement of a custom design. OceanServer provides physical space inside the forward section for user electronics as well as hull penetrators to make connections to external sensors. The remote helm design model requires a separate CPU, which allows the users to install their own operating system that can connect to the added hardware. This split design provides isolation of the main vehicle and inherent protection during development of custom behaviors and sensor integration by leveraging years of experience and successful vehicle implementation through UVC (Underwater Vehicle Control). The second CPU communicates with the Iver3 UVC controller CPU through a serial port via a rich set of commands for remote helm control (serial API).

The remote helm API provides all the necessary commands when interfacing
the Iver3 to a user control program. This paper will describe the remote helm commands of this serial bus API and the software tools that can aid in
implementing a system
.
to:
%color=#7777BB%[[Talk.ListingSorted|Talks-Sorted]]%%  | \
%color=#7777BB%[[Main.HomePage|MOOS-DAWG
'19]]%%


!! Talk
-14: ''pLearn: Behavior Learning with Tensor Flow, Keras, and MOOS-IvP''

!!!!%color=#449944% '''Michael Novitzky, MIT'''

The goal of this work is to introduce behavior learning in the MOOS-IvP ecosystem. This work was initially started to support learning behaviors in the complex domain of capture the flag for our Project Aquaticus Testbed. Manually authoring and testing behaviors for autonomous marine vehicles can become tedious
and impractical when faced with complex or rapidly changing adversarial situations. We address this problem by learning autonomous behaviors using deep reinforcement learning. We apply deep reinforcement learning, an approach that learns behaviors without relying on explicit vehicle models, to a game of capture the flag with multiple competing vehicles. We have previously presented our integration of deep reinforcement learning with MOOS-IvP, a software suite for marine robotics communication, control, and simulation, that allows the development and execution of behaviors for both underwater and surface vehicles.  We extended MOOS-IvP to create and train a neural net to learn autonomous behaviors for reaching the opponent’s flag while avoiding an adversary exhibiting a defense behavior in simulation.  However, the setup requires serious dependencies — Python and integration with c++ and pHelmIvP….which lead to difficulties on making it portable for other students and colleagues to leverage. We will present our latest integration of pLearn in a Docker container along with simplified installation instructions for greater portability for the research community.
Changed line 13 from:
!!!!%color=#449944% '''Bob Anderson, Daryl Slocum, L3 Ocean Server'''
to:
!!!!%color=#449944% '''Bob Anderson, Daryl Slocum, Hunter Brown, L3 Ocean Server'''
Added lines 1-27:
(:notitle:)
(:notitlegroup:)
(:nofooter:)

!!!! %color=#7777BB% [[Talk.13-Robinette | Prev-Talk]]%%  | \
%color=#7777BB%[[Talk.15-Novitzky | Next-Talk]]%% | \
%color=#7777BB%[[Talk.Listing|All-Talks]] | \
%color=#7777BB%[[Talk.ListingSorted|Talks-Sorted]]%% 


!! Talk-14: ''OceanServer Iver3-580 EP Autonomous Underwater Vehicle Remote Helm Functionality''

!!!!%color=#449944% '''Bob Anderson, Daryl Slocum, L3 Ocean Server'''


Historically most Autonomous Underwater Vehicles (AUVs) have been closed systems. Any changes require contracting the manufacturer for a custom design change, which are costly in time and money. In addition, the expanding role of AUVs has users looking for a more reliable and versatile vehicle to perform various tasks. The OceanServer Remote Helm on the Iver3 AUV provides a fully functional and open system where the users can install their hardware and make software extensions to the vehicle without the requirement of a custom design. OceanServer provides physical space inside the forward section for user electronics as well as hull penetrators to make connections to external sensors. The remote helm design model requires a separate CPU, which allows the users to install their own operating system that can connect to the added hardware. This split design provides isolation of the main vehicle and inherent protection during development of custom behaviors and sensor integration by leveraging years of experience and successful vehicle implementation through UVC (Underwater Vehicle Control). The second CPU communicates with the Iver3 UVC controller CPU through a serial port via a rich set of commands for remote helm control (serial API).

The remote helm API provides all the necessary commands when interfacing the Iver3 to a user control program. This paper will describe the remote helm commands of this serial bus API and the software tools that can aid in
implementing a system.

!!!!%color=#4444BB% '''Categories:''' \

* AUVs
* Payload Autonomy


%%