Defense

Shaping tomorrow’s defense technologies

To respond to today’s strategic and military challenges, defense-industry stakeholders need partners who master both technology and security.

Probayes is helping the defense industry navigate digital transformation with artificial intelligence tools.

Probayes develops tools that respond to the defense industry’s main challenges:

Algorithms tailored to the defense industry

Probayes uses computational geometry for rapid collision detection, optimization algorithms to generate trajectories that do not conflict with the kinematics of the platforms used, deep learning to detect behaviors, ontological approaches to interpret tactical situations, and probabilistic inference. Our algorithms have been in use in a wide range of defense-industry scenarios for more than fifteen years. Here are some of the defense-industry use cases. Probayes can address:

In-service support

  • Preventive maintenance of military assets (aircraft, armored vehicles, etc.)
  • Mission-based vehicle assignment forecasting
  • Logistics optimization
  • Spare parts supply optimization

Sensor fusion

  • Verification of operational incompatibilities in an engagement plan to ensure that the weapons systems used do not present any temporal, spatial, or electromagnetic incompatibilities
  • Route planning based on heterogeneous sensor data fusion, field and sensor uncertainty modeling, simulation of physical processes, time filters (e.g, Kalman, particles), and constrained quadratic optimization for planning under kinematic constraints
  • Decision-assistance for combat based on sensor fusion and probabilistic inference

Neural networks

  • Behavior identification utilizing deep recurrent neural networks to deduce behavior from noisy sensor time-series data

Machine learning

  • Operator-machine collaboration in target allocation systems with reinforcement learning

Bayesian networks

  • Probabilistic trajectory prediction using Markov chain Monte Carlo methods
  • Terrain uncertainty modeling for route planning and probabilistic computation of intervisibility using Gaussian processes

Ontologies

  • Synthetic description of operational situations using ontologies

Better results, together

We work hand in hand with your business experts

The defense industry is particularly complex. Generally speaking, defense projects are characterized by a large number of data sources. At Probayes, we work hand in hand with our customers’ experts to understand the many moving parts of the challenge at hand so that we can develop the best possible solution. We make communication a priority to ensure that we learn from each other throughout the project. Our customers come away with a better understanding of AI implementation in defense scenarios, and our people acquire a deep understanding of the issues our customers face. Each project strengthens our long-lasting customer relationships.

Success stories

FraudIA™

Detecting credit card fraud

Churn

Detecting customers that are likely to leave

Vehicule autonome connecté

Navigation par SOP

Géolocalisation de véhicule autonome par SOP (Signal of OPportunity)

RMPR_UPCAT_recadree_1080

Création de trajectoires missiles, en temps réel - MCM ITP

Évaluer les marges de sécurité anti-collision et calculer les trajectoires optimum de missile

MAN MACHINE TEAMING - RECO project

Success story

The RECO project

Challenge

The objective of this project was to classify the behaviors of an enemy aircraft or group of aircraft from their trajectories and generate clusters of probable trajectories that correspond to the behaviors.

The project

The purpose of the RECO project was to replace conventional trajectory classification techniques with recurrent deep neural network approaches.

Results

The artificial intelligence developed for this project:

  • to improved the reliability of the predictions made 
  • sped up computation for operational implementation
  • significantly increased the number of recognizable behaviors
  • extended the analysis in the event of multiple attacking aircraft
“Lorem ipsum dolor sit amet, consectetur adipiscing elit. Fusce eu lacus diam. Cras congue, neque ac mattis efficitur, nibh ipsum fringilla nunc, sed iaculis neque odio non orci. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia Curae; Praesent lacinia, urna quis rhoncus lobortis, urna neque tempus tellus, quis auctor justo lectus vitae libero. Nulla non porta odio. Donec diam est, varius id ullamcorper a, efficitur nec libero”

First name Last name

Position – Company

Our customers*

*We take confidentiality seriously. Some of our customers’ names and other identifying information have been removed.

Our customers*

*We take confidentiality seriously. Some of our customers’ names and other identifying information have been removed.