• Aucun résultat trouvé

IRET - Multimodal interactive simulator for public safety and defence training

N/A
N/A
Protected

Academic year: 2021

Partager "IRET - Multimodal interactive simulator for public safety and defence training"

Copied!
9
0
0

Texte intégral

(1)

Publisher’s version / Version de l'éditeur:

Vous avez des questions? Nous pouvons vous aider. Pour communiquer directement avec un auteur, consultez la

première page de la revue dans laquelle son article a été publié afin de trouver ses coordonnées. Si vous n’arrivez pas à les repérer, communiquez avec nous à PublicationsArchive-ArchivesPublications@nrc-cnrc.gc.ca.

Questions? Contact the NRC Publications Archive team at

PublicationsArchive-ArchivesPublications@nrc-cnrc.gc.ca. If you wish to email the authors directly, please see the first page of the publication for their contact information.

https://publications-cnrc.canada.ca/fra/droits

L’accès à ce site Web et l’utilisation de son contenu sont assujettis aux conditions présentées dans le site LISEZ CES CONDITIONS ATTENTIVEMENT AVANT D’UTILISER CE SITE WEB.

Heidelberg Innovation Forum, April 12, 2011, Heidelberg, Germany [Proceedings], 2011-09-01

READ THESE TERMS AND CONDITIONS CAREFULLY BEFORE USING THIS WEBSITE.

https://nrc-publications.canada.ca/eng/copyright

NRC Publications Archive Record / Notice des Archives des publications du CNRC :

https://nrc-publications.canada.ca/eng/view/object/?id=d2e37bf4-734a-4911-992f-bca756a1ec35 https://publications-cnrc.canada.ca/fra/voir/objet/?id=d2e37bf4-734a-4911-992f-bca756a1ec35

NRC Publications Archive

Archives des publications du CNRC

This publication could be one of several versions: author’s original, accepted manuscript or the publisher’s version. / La version de cette publication peut être l’une des suivantes : la version prépublication de l’auteur, la version acceptée du manuscrit ou la version de l’éditeur.

Access and use of this website and the material on it are subject to the Terms and Conditions set forth at IRET - Multimodal interactive simulator for public safety and defence training

(2)

Institute for Information Technology

IRET - Multimodal interactive simulator

for public safety and defence training

Dr. Cosmin Munteanu

Cosmin.Munteanu@nrc-cnrc.gc.ca

Heidelberg Innovation Forum – 12 April 2011

(3)

Multimodal Interaction for Mixed-Reality Training: the IRET-MINT Platform 2 Cosmin Munteanu

Old-school training

● Training for urban combat operations requires soldiers to learn

procedures for dealing with numerous real-life situations

● This involves the set up and use of many “props”

● Thousands of plastic or paint bullets

● CO2 area weapons (e.g. flash bangs)

● Paper targets

● Physical rooms / buildings

(4)

Cost, efficiency, safety

● High cost

● Current training resources are not always reusable (e.g. CO2

cartridges, plastic bullets, broken doors)

● Inefficient

● Layouts are not easily reconfigurable (wooden rooms requiring

carpentry work to reconfigure or even concrete buildings)

● Lack of realism

● Paper targets are static

● Safety needs

● Certain operations require extreme caution (e.g. breaching a door

(5)

Multimodal Interaction for Mixed-Reality Training: the IRET-MINT Platform 4 Cosmin Munteanu

Virtual training with the

IRET-MINT environment

● The IRET-MINT training platform addresses issues of cost,

efficiency, realism, and safety faced by current urban operations training

● It is a mixed-reality, immersive

environment and gaming platform supporting customizable training scenarios for defence, public

safety, and law enforcement, in a realistic and controlled setting

● Developed by researchers in HCI, ASR, NLP, SysEng at the

National Research Council in collaboration with the Department of National Defence / Combat Training School

(6)

The IRET-MINT system

● Flexible training platform for easy reconfiguration of the

immersive environment to support different training scenarios

● Universal communication protocol facilitating integration of

external components and network-enabled remote training

● Multimodal interaction

(speech, gestures, etc.)

● Electronic simulated

area weapons

● Integration of other weapons

(7)

Multimodal Interaction for Mixed-Reality Training: the IRET-MINT Platform 6 Cosmin Munteanu

Multimodal interaction in IRET-MINT

● Plug-in interface for speech recognition and language

processing for natural interaction with virtual characters – flexible and robust processing of speech under stress

● Domain-specific electronic devices simulating lethal and

non-lethal weapons that interact with the IRET platform

● Cost-effective and safe ● Increased efficiency and

effectiveness of training

● Example: flashbang, explosive

door breacher, etc.

● Tablet-based control interface for

(8)

Solutions for current and future needs

● We have developed IRET-MINT:

● Immersive, interactive environment for urban ops training ● Platform enabling natural interactions between users and

intelligent, mixed-reality environments

● Flexible, cost-effective, safe solution

● Our core technologies provide R&D and licensing opportunities

in a wide range of industries (public safety, law enforcement, defence training)

● We continually seek industry partners to:

● Develop the next iterations of the system ● Broaden the scope of this technology

(9)

Thank you!

● Acknowledgments:

● NRC IIT Research Team: Irina Kondratova, Cosmin Munteanu,

Haozheng Li, Muhammad Al-Digeil, Brian McKinnon, Ilia Goldfarb, Rene Richard, Cedric Martin, Nathan Langton, Joanna Lumsden, Ryan Nielson, Yasaman Sanaee

● Department of National Defence (DND)

● CFB Gagetown – Combat Training Center Tactical School

Références

Documents relatifs

This section details the multimodal HMM and the speci- ficities of our implementation, designed to fit the context of real-time music performance. In the remainder of this

This thesis was devoted to the strengthening of this very body, through a study of architectures for multimodal interaction, the definition of eight guidelines

We propose to illustrate the relevance of the aforementioned criteria through the reassem- bly of fractured objects. In particular, we deal with a real-world dataset composed of

• 3 PCs: one under Windows for the driving simulator, one under Linux for capturing and predicting the driver’s states (focus of attention and state of fatigue), and one on Windows

To further assess the aggravated cartilage breakdown in GPR40 knock-out mice compared to wild-type mice, we analyzed the expression of a wide range of key markers implicated in OA

Interindividual variability in response to consumption of plant food bioactives Despite the accumulative scientific evidence supporting the interest in eating plant food bioactives

The objectives of this study are four-fold: 1) to better understand the external aerodynamics of canine olfaction using an anatomically-similar 3D printed model of the dog’s nose;

Acceleration signals stored in ASCII format (acquired with other systems) can also be analyzed with TOM. Digital filtering is employed directly in the time domain to decompose