Home > Automotive

Automotive

Quick links:

Technology for tomorrow’s vehicles

Probayes has been helping automotive-industry stakeholders navigate digital transformation for years.

Artificial intelligence is one way the industry can continue to meet consumers’ constantly-growing appetite for innovation.

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

Algorithms tailored to the automotive industry

Probayes has been developing, testing, and implementing a wide range of algorithmic tools on automotive-industry use cases for fifteen years. Our core approaches include:

Autonomous vehicles:

Machine learning & deep learning

Object detection in images
Image generation using generative adversarial networks (GAN)
Image segmentation

Sensor fusion (images, LiDAR, IMU)

Object tracking (Kalman filter)
Predicting environment and vehicle behaviors

Embedded algorithm development

Point cloud clustering

Automated camera calibration

Allows new data to be collected
Domain adaptation for autonomous vehicles (learn from data and adapt models to work on new databases)

Other uses:

Hybrid engine optimization
Learning driver behavior
Predictive maintenance and general maintenance

Better results, together

We work hand in hand with your business experts

The automotive industry is particularly complex. Generally speaking, automotive 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 automotive scenarios, and our people acquire a deep understanding of the issues our customers face. Each project strengthens our long-lasting customer relationships.

Eramet

Success story

Eramet is one of the world’s leading metal alloy producers. The Eramet plant in Knivesdal, Norway, produces silicomanganese alloys.

Challenge

When manufacturing processes are optimized, premium raw materials can be replaced with less-expensive alternatives without affecting product quality. Eramet turned to Probayes for a real-time solution capable of detecting exactly when to switch out the more expensive raw material for the cheaper one and of generating recommendations for when to switch back in the event of drift.

The project

We applied an unsupervised classification algorithm to a set of around 50 process variables to discern the different process operating behaviors. We then had Eramet process experts annotate the behaviors and trained a classifier to recognize them. Finally, we added an explainability module that generates, in real time, the parameters that characterize non-optimal behaviors.

Results

Our analysis resulted in a family of five process behaviors, which were annotated by several process experts from Eramet. The characteristics of the optimal process and of the non-optimal behaviors were clearly identified. An initial release of the solution was implemented at Eramet’s Knivesdal, Norway plant.

“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

Success stories:

The automotive industry is undergoing an unprecedented digital transformation. Car manufacturers are investing massively in R&D, innovating not only in autonomous and connected vehicles, but also in new drivetrain solutions.

Autonomous vehicles

Project to improve autonomous vehicle driving systems

Predictive maintenance for heavy vehicles

Project to predict the risk of a breakdown depending on vehicle usage classification

Making hybrid vehicle engines more efficient

Project to optimize the energy consumption of a hybrid engine

Watch a product demo

Probayes demo - Autonomous vehicles and environmental perception

For autonomous vehicles to be safe, they have to be able to “see” their immediate surroundings in real time. Probayes has been working on environmental perception since 2005.

Probayes demo - Autonomous vehicles and environmental perception

For autonomous vehicles to be safe, they have to be able to “see” their immediate surroundings in real time. Probayes has been working on environmental perception since 2005.

Register for a webinar or watch the recordings

Applying artificial intelligence to sensor data

If you take a look around you, you will see that sensors are already widely used to capture images, videos, sounds, temperature, and other data.

When it comes to the digital revolution, the transportation sector is on the front lines. Currently, the term “autonomous vehicle” does not necessarily mean driverless car, but rather the assistance systems developed around the vehicle. According to Gartner, however, by 2030 nearly 25% of all passenger cars will be autonomous vehicles.