Aerospace & Automotive.
We design customized software products for aerospace applications. These platforms offer dynamic route planning and optimization, reducing operating costs and increasing delivery efficiency. Representative platforms include freight optimization software and global flight planning tracking and capabilities.
The rise of autonomous vehicles will cause a tectonic shift in the automotive industry. Tech companies, soon followed by traditional auto manufacturers, have been investing big into the category. Rails Reactor works closely with several tech startups helping them to productize the most innovative ideas.
We implemented a complex flight planning tool which computes optimal aircraft routes over various geographical objects of interest, such as: points, lines, polygons, and pipelines, while taking into account fueling time, number of aircraft in a fleet, fuel consumption, no-fly zones, and other special conditions.
Since the number of objects can be extremely large and custom conditions should be taken into account (e.g. refueling time, number of aircraft in a fleet, fuel consumption etc.), an advanced and efficient algorithm was implemented which solves a modification of the Vehicle Routing Problem.
Our tool benefits from parallel execution and optimized instructions and performs cutting-edge data preprocessing that helps to normalize heterogeneous objects, including density-based clustering of closely located objects, recursive decomposition of large objects and a few other computational geometry algorithms. It also queries the Google Geolocation API in order to generate precise coordinates of a computed flight.
- Google OR-Tools
- Google Geolocation API
- Normalization of heterogeneous objects
- Recursive decomposition of objects
- Density-based clustering
- Computational geometry
LIDAR and cameras are some of the critical hardware sensors supporting the success of self-driving autonomous vehicle systems. These “eyes” of the autonomous vehicle system pull in raw data, which must then be safely and accurately interpreted.
We achieved state-of-the-art results in odometry estimation by applying machine learning algorithms for object detection and segmentation (cars, pedestrians, road markup, etc). In order to refine the estimations obtained from algorithms based on LIDAR data, we added fusion with data obtained from GPS/IMU/telemetry, and made it full 3D (6-DOF) by using cameras as an additional input. Moreover, we applied generative adversarial network and capsule network models to learn POV-invariant descriptors of local surface features. This helped to safely detect road signs and signals during inclement conditions, such as a rainy night.
- Sensor fusion
(LIDAR, IMU, GPS, Camera)
- Odometry Estimation
- Object Segmentation
- Capsule Network
- Robot Operating System(ROS)
- Object Recognition
- Generative Adversarial Network
- Performance Optimization
- Real Time Systems
- Tensorflow Serving
Virtual Dispatch Assistant automatically handles scheduling caregivers for assignment, taking into consideration various conditions and criteria, while maximizing the efficiency and utilization of caregivers. Factors taken into account include caregiver shift schedules; caregiver tasks before and after a new assignment; match/mismatch of caregiver-patient “special conditions” (allergy to animals, ability to handle the obese, etc.); and a match between caregiver certifications and patient conditions/medical history.
- .NET Core
- ASP.NET Core
- Entity Framework
- Google OR-Tools
- Azure Service Fabric
- Apache Spark & Luigi
We are highly skilled across a wide variety of technologies and can leverage our diverse and broad skill sets to achieve tailored software products. Our engineers are expert technologists focused on client delivery.
- Digital Ocean
- Google Cloud
- AWS S3
- MS SQL Server
- Angular JS
with User Experience
Investing in a properly structured UX process at the development stage helps identify the factors that can lead to project failure, and also reduces the likelihood of rework.
Our commitment to developing the best applications begins well before a single line of code is written.
Planning, testing, and an overall commitment to creating a product that addresses its users’ real needs lead to greater profitability over time and a clearer path to growing your business.
Our Engagement Models
You tell us your problem and challenge. We form a team (PM, BA, designers, engineers, QAs etc.) and they work till the issue is solved.
You have your team in place, but need a few additional people with specific skill set? We have them. Tell us whom you need and we’ll bring the right people.