Protostar Labs

Visual Inspection of Lanterns

Quality control in lantern manufacturing is crucial for ensuring product safety and efficacy. Traditional inspection methods often rely on manual checks, which can be time-consuming, inconsistent, and prone to human error. The lantern industry needs more efficient and accurate quality control processes to maintain high standards while increasing production efficiency.

On-Orbit Inspection and Servicing

Satellite maintenance and repair in space are complex and costly operations, often requiring manned missions or sophisticated robotic systems. Traditional methods of detecting and correcting issues like misaligned solar panels or antennas are often done manually which means they are time-intensive and influenced by ability to contact the satellite at all. The space industry needs more efficient, automated solutions to address these challenges and ensure optimal satellite performance.

Visual quality inspection of bottle packaging

Production defects are a common problem in the food and beverage industry, but most of the issues that arise can be fixed using modern solutions such as machine learning and computer vision. These issues can include, but are not limited to, problems with bottle caps, liquid levels, foreign objects in the product, etc. Protostar Vision Box combines machine learning with on-board processing and direct integration into existing production lines to allow an immediate increase in production efficiency and worker satisfaction during which we are also reducing production costs and the rate of product returns. Machine learning allows us to track even the smallest imperfections if the environment demands it while keeping the false positive rate under 0.01%. Finally, we have access to state-of-the-art vision systems that allow us to detect foreign bodies in the liquid even if the packaging is already sealed.

Custom LLM for test automation

Writing test cases based on actions, verifications and requirements from design documents can be time-consuming, especially when there is need for multiple design documents. This is why the usage of LLMs for automating this task can be very useful. It needs to understand the requirements from the documents and provide responses tailored to the users needs whilst adhering to the requirements. This speed up the development time and lightens the workload of test designers to utilize their time more effectivly.