Overview

pContinental AG, commonly known as Continental, is a German automotive manufacturing company specializing in brake systems, interior electronics, automotive safety, powertrain and chassis components, tachographs, tires and other parts for the automotive and transportation industries./p

Supernova Award Category

AI and Augmented Humanity

The Problem

pTo achieve their new program, Vision Zero, which strives for zero fatalities or accidents on roads, Continental needed a framework they describe as SensePlanAct to power the next generation of autonomous vehicles, but found challenges with this type of technology. /p p /p pModern urban environments present a complex mix of buildings, infrastructure, busses, trains, cars and pedestrians - to name a few. Roads and traffic rules vary by country and signs are often in different languages or location specific. Weather conditions, such as rain or snow, and time of day, for example dusk or night time, further complicate the environment vehicles have to interpret and plan for. /p p /p pData generated by sensors, radars, and cameras is complex, multi-structured and changes rapidly based on new configurations or prototypes. Machine learning frameworks rely on iterative feature engineering based on this evolving data to train and tune new models. Restricting the data to a rigid tabular schema, like those used in traditional relational databases, isn’t practical because data scientists do not know up front how each data element will be used in the next model iteration, and the one after that, and so on./p

The Solution

pContinental needed to extract all variable knowledge including all the situations out of data collected all over the world and bring that into the products using deep learning and machine learning technologies. Continental recognized that it was no longer sufficient for its engineers to implement rule-based algorithms they knew to be accurate in the past, nor is it possible to test every scenario and combination of variables for safe driving in modern cities. Continental only planned to use MongoDB to store and label image data, such as scenes from the road, but the team quickly found they can use the same data platform for the analytical image data, the derived metadata and the results of their experiments, significantly increasing productivity. They also found that in order to collaborate effectively their teams needed to share common data sets and platform.  Data soon diverged, making it impossible to calibrate results and merge individual workstreams./p

The results

pWith MongoDB’s flexibility and parallelism, developers can build new models more rapidly, work together without sacrificing speed and accuracy, and quickly build and test new prototypes for the autonomous SensePlanAct framework./p p“In the end we were able to tame this deep learning beast with this flexible database”, says Martin Berchtold-Buschle, who is the subject matter expert for Big Data Infrastructure Deep Learning at Continental. /p

Metrics

pContinental currently manages 17 Terabytes of data and handle millions of large documents in MongoDB. They plan their data size to grow to 100 Terabytes or more in the near term. /p p /p pContinental needed the ability to achieve vertical and horizontal scalability for a successful application development. MongoDB makes scaling easy, so they currently scale their data and applications over nine machines, 3 shards and 3 replicas and streamline automation, scaling and management with MongoDB Ops Manager./p pThere are dozens of developers working on deep learning who need to be able to collaborate effectively and share data and results. In the past they worked with local storage workstations causing data to diverged and no longer making results repeatable. With MongoDB very developer can efficiently collaborate by using centralized data platform which holds metadata, result data, analytical data and more removing barriers to productivity./p

The Technology

pMongoDB Enterprise Advanced/p pMongoDB Ops Manager/p pMongoDB Python Driver (PyMongo)/p

Disruptive Factor

pAs Robert Thiel, the Head of Machine Learning and Test Data Management at Continental, explains: “What we need to do is extract all this knowledge, all these situations out of data we collect all over the world and bring that in to our products using deep learning and machine learning technologies”. In order to collect, store and process massive volumes of complex data Continental needed an intelligent data platform that is flexible, developer friendly, and seamlessly scalable. Data generated by sensors, radars, and cameras is complex, multi-structured and changes rapidly based on new configurations or prototypes while machine learning frameworks rely on iterative feature engineering based on this evolving data to train and tune new models. Restricting the data to a rigid tabular schema, like those used in traditional relational databases, isn’t practical because data scientists do not know up front how each data element will be used in the next model iteration, and the one after that, and so on. With MongoDB’s flexibility and parallelism, developers can build new models more rapidly, work together without sacrificing speed and accuracy, and quickly build and test new prototypes for the autonomous SensePlanAct framework./p

Shining Moment

pContinental is moving toward the cloud and plans to adopt MongoDB Atlas, the fully automated database as-a-service. The team believes that MongoDB will be a crucial component in helping them achieve Vision Zero and bring the new standards of safety across many cities and governments around the world./p