From merrittk at cmu.edu  Thu Oct  2 12:43:12 2025
From: merrittk at cmu.edu (Merritt Kowaleski)
Date: Thu, 2 Oct 2025 12:43:12 -0400
Subject: dgx2 home directory is low
In-Reply-To: <CAPN5EvMcKaGff46Hu=efozUFHm5OE04QiTzCbc2+_Au4RUgqcQ@mail.gmail.com>
References: <CAPN5EvMcKaGff46Hu=efozUFHm5OE04QiTzCbc2+_Au4RUgqcQ@mail.gmail.com>
Message-ID: <CAFbOC13NW4e_yZSdu-T8U3b5gm1N7U_XF=jrTsc70A=_jxBtKQ@mail.gmail.com>

Hi all,
I have a couple questions related to space on dgx2.  What are the /raid and
/raid2 dirs for?  /raid appears to be its own partition, which has more
space than /, most of it unused, while /raid2 is in the same partition as
/.  Are there any guidelines or restrictions on how to use these dirs?
Best,
Merritt

On Mon, Sep 29, 2025 at 4:30?PM Daniel Howarth <dhowarth at andrew.cmu.edu>
wrote:

> Hello all,
>
> Please remove any files you no longer need on dgx2's home directory.
>
> Thanks,
> Dan
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20251002/78efd1ab/attachment.html>

From pbartosi at andrew.cmu.edu  Thu Oct  2 13:55:53 2025
From: pbartosi at andrew.cmu.edu (Piotr Bartosiewicz)
Date: Thu, 2 Oct 2025 13:55:53 -0400
Subject: Computing nodes maintenance (gpu29)
In-Reply-To: <CAN_-bZK+9nQYYMWn=JzYjuYZG_7jk_z-=sdG+VxKeSM8vxyiQg@mail.gmail.com>
References: <CAN_-bZK+9nQYYMWn=JzYjuYZG_7jk_z-=sdG+VxKeSM8vxyiQg@mail.gmail.com>
Message-ID: <CAN_-bZLgEzW8W0-xArJHBUinT34WJ8gmnJqd11kUePD+OjXmiw@mail.gmail.com>

Hi,
  Gpu29 is up and running again.

Piotr.


On Tue, Sep 30, 2025 at 10:26?AM Piotr Bartosiewicz <pbartosi at andrew.cmu.edu>
wrote:

> Hi,
>
>   Node: gpu29 will be taken offline for maintenance and OS replacement on
> Thursday, 10/02/2025.
> Please save all your important work on the listed node before Thursday
> morning.
>
> Estimated down time is 1 day.
>
> Piotr.
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20251002/623c1561/attachment.html>

From pbartosi at andrew.cmu.edu  Mon Oct  6 16:10:26 2025
From: pbartosi at andrew.cmu.edu (Piotr Bartosiewicz)
Date: Mon, 6 Oct 2025 16:10:26 -0400
Subject: Computing nodes maintenance (gpu30, 31)
In-Reply-To: <CAN_-bZLKdoHUKoO1fNwhe9sOOHJP3XpJC0z-Qe5Z21UUhK67VQ@mail.gmail.com>
References: <CAN_-bZLKdoHUKoO1fNwhe9sOOHJP3XpJC0z-Qe5Z21UUhK67VQ@mail.gmail.com>
Message-ID: <CAN_-bZJeZ8r+gMeWT3VXARiis5iuQFSKe5HfwwhZ1iqarLXFVg@mail.gmail.com>

Hi,
 nodes: gpu30 and 31 are up and running again.

Piotr.

On Tue, Sep 30, 2025 at 10:28?AM Piotr Bartosiewicz <pbartosi at andrew.cmu.edu>
wrote:

> Hi,
>
>   Nodes: gpu30 and 31 will be taken offline for maintenance and OS
> replacement on Monday, 10/06/2025.
> Please save all your important work on the listed nodes before Monday
> morning.
>
> Estimated down time is 1 day.
>
> Piotr.
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20251006/60965c2c/attachment.html>

From awd at cs.cmu.edu  Wed Oct  8 17:15:54 2025
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Wed, 8 Oct 2025 17:15:54 -0400
Subject: Fwd: RI PhD Thesis Defense - Ceci Morales
In-Reply-To: <CABKA2NXH7x6Srtdrd9AiwAB_kRkhkaWHOC=HWBvnvteXdEgoyg@mail.gmail.com>
References: <CABKA2NXH7x6Srtdrd9AiwAB_kRkhkaWHOC=HWBvnvteXdEgoyg@mail.gmail.com>
Message-ID: <CAJvAoytWhy=5t99bXatWDT4DVrdwomSSxzDs1Xw=UATrWFc=gQ@mail.gmail.com>

Dear Autonians,

Please mark your calendars and join Ceci in celebration of her
doctoral thesis defense on Tuesday next week!

Cheers,
Artur

---------- Forwarded message ---------
From: RI PhD Program Manager <ri-phd-manager at andrew.cmu.edu>
Date: Wed, Oct 8, 2025 at 4:19?PM
Subject: RI PhD Thesis Defense - Ceci Morales
To: RI People <ri-people at andrew.cmu.edu>


RI EVENT CALENDAR

Who: Ceci Morales

Date: Tuesday, October 14th

Time: 2:00PM ET

Location: NSH 4305

Zoom Link: https://cmu.zoom.us/j/8982402813

Title: Embodied Artificial Intelligence for Emergency Care in
Unstructured Environments

Abstract:

In mass casualty events and resource-constrained scenarios, limited
responder capacity leads to preventable deaths. Time is of the essence
particularly in severe trauma: the sooner individuals receive care,
the higher their chances of survival. Yet a single responder can only
manage a few patients simultaneously, leaving others unattended. This
thesis addresses this capacity constraint by developing intelligent
robotic systems that serve as medical force multipliers, enabling
effective emergency response when casualties outnumber available help.

This work presents two embodied Artificial Intelligence (AI) platforms
for emergency medical response in unstructured field environments. The
first performs multipatient automated assessment, which uses
contactless multimodal sensors to identify qualitative (e.g., wounds,
amputations, hemorrhage, respiratory distress) and quantitative vital
signs (e.g., heart rate) to rapidly assess and prioritize the most
critically injured. The second automates fluid resuscitation,
targeting hemorrhage, the leading cause of preventable death in
trauma. The pipeline comprises multiple stages: vessel localization
and segmentation, visualization and uncertainty quantification for
safe decision-making, bifurcation detection for anatomically-informed
needle placement, and real-time needle tracking.

To address the scarcity of training data in emergency medicine
robotics, this research embeds expert clinical knowledge and applies
weak supervision techniques, enabling robust performance with limited
labeled examples. All algorithms execute in real time on
resource-constrained platforms, with key components designed to adapt
to changing environmental conditions.

This thesis contributes to autonomous medical systems and offers new
methodologies for developing AI solutions for life-critical
applications in unstructured environments where traditional
data-driven approaches may fail. By augmenting human responders, we
show how robotic systems can expand treatment capacity when it matters
most, potentially saving lives that would otherwise be lost.

Thesis Committee:

Artur Dubrawski, Chair

Jean Oh

Fernando de la Torre Frade

Daniel McDuff, Google

Laura Brattain, University of Central Florida


Document Link


From awd at cs.cmu.edu  Mon Oct 13 15:25:47 2025
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Mon, 13 Oct 2025 15:25:47 -0400
Subject: REMINDER: RI PhD Thesis Defense - Ceci Morales
In-Reply-To: <CAJvAoytWhy=5t99bXatWDT4DVrdwomSSxzDs1Xw=UATrWFc=gQ@mail.gmail.com>
References: <CABKA2NXH7x6Srtdrd9AiwAB_kRkhkaWHOC=HWBvnvteXdEgoyg@mail.gmail.com>
 <CAJvAoytWhy=5t99bXatWDT4DVrdwomSSxzDs1Xw=UATrWFc=gQ@mail.gmail.com>
Message-ID: <CAJvAoyu2yMd0f5AK-SM5BW7v2aeguQgoV81f7RARTOOyLuXuJw@mail.gmail.com>

This happens tomorrow!

On Wed, Oct 8, 2025 at 5:15?PM Artur Dubrawski <awd at cs.cmu.edu> wrote:
>
> Dear Autonians,
>
> Please mark your calendars and join Ceci in celebration of her
> doctoral thesis defense on Tuesday next week!
>
> Cheers,
> Artur
>
> ---------- Forwarded message ---------
> From: RI PhD Program Manager <ri-phd-manager at andrew.cmu.edu>
> Date: Wed, Oct 8, 2025 at 4:19?PM
> Subject: RI PhD Thesis Defense - Ceci Morales
> To: RI People <ri-people at andrew.cmu.edu>
>
>
> RI EVENT CALENDAR
>
> Who: Ceci Morales
>
> Date: Tuesday, October 14th
>
> Time: 2:00PM ET
>
> Location: NSH 4305
>
> Zoom Link: https://cmu.zoom.us/j/8982402813
>
> Title: Embodied Artificial Intelligence for Emergency Care in
> Unstructured Environments
>
> Abstract:
>
> In mass casualty events and resource-constrained scenarios, limited
> responder capacity leads to preventable deaths. Time is of the essence
> particularly in severe trauma: the sooner individuals receive care,
> the higher their chances of survival. Yet a single responder can only
> manage a few patients simultaneously, leaving others unattended. This
> thesis addresses this capacity constraint by developing intelligent
> robotic systems that serve as medical force multipliers, enabling
> effective emergency response when casualties outnumber available help.
>
> This work presents two embodied Artificial Intelligence (AI) platforms
> for emergency medical response in unstructured field environments. The
> first performs multipatient automated assessment, which uses
> contactless multimodal sensors to identify qualitative (e.g., wounds,
> amputations, hemorrhage, respiratory distress) and quantitative vital
> signs (e.g., heart rate) to rapidly assess and prioritize the most
> critically injured. The second automates fluid resuscitation,
> targeting hemorrhage, the leading cause of preventable death in
> trauma. The pipeline comprises multiple stages: vessel localization
> and segmentation, visualization and uncertainty quantification for
> safe decision-making, bifurcation detection for anatomically-informed
> needle placement, and real-time needle tracking.
>
> To address the scarcity of training data in emergency medicine
> robotics, this research embeds expert clinical knowledge and applies
> weak supervision techniques, enabling robust performance with limited
> labeled examples. All algorithms execute in real time on
> resource-constrained platforms, with key components designed to adapt
> to changing environmental conditions.
>
> This thesis contributes to autonomous medical systems and offers new
> methodologies for developing AI solutions for life-critical
> applications in unstructured environments where traditional
> data-driven approaches may fail. By augmenting human responders, we
> show how robotic systems can expand treatment capacity when it matters
> most, potentially saving lives that would otherwise be lost.
>
> Thesis Committee:
>
> Artur Dubrawski, Chair
>
> Jean Oh
>
> Fernando de la Torre Frade
>
> Daniel McDuff, Google
>
> Laura Brattain, University of Central Florida
>
>
> Document Link