Unlocking New Potentials: How FogHorn and Porsche Leverage Edge Computing for Vehicles
Moore’s Law, you probably all know it. The phenomenon named after Gordon Moore, co-founder of Intel, who predicted that the number of transistors that can be placed on an integrated circuit — in short: computing power — will double roughly every two years, back in 1965. His prediction became a self-fulfilling prophecy for the computer industry, leading to exponential growth in computing power and increasingly powerful microprocessors over the last five decades. Just so you can imagine the dimension: if the top speed of cars had followed the same trend since 1965, we would be watching Lewis Hamilton fly around Silverstone at more than 11,000,000,000 mph.
Computing Power at the Edge
As computing power is now coming closer to the „edge“, meaning that computing is done at or near the source of the data instead of relying on the cloud in a data center somewhere, vehicles are increasingly able to handle data and compute themselves. This opens up completely new possibilities and applications for edge computing in vehicles. As part of the Stuttgart-based innovation platform Startup Autobahn, Porsche and US-based edge computing startup FogHorn joined forces to develop a prototypical edge solution that enables the keyless and easy unlocking of a Porsche vehicle.
Multi-factor Authentication for Keyless Entry
One case for edge computing in the automotive industry is to provide a frictionless entry to the car based on multiple security factors — a great chance to enhance the driver experience. This is why the ideation and innovation team at Porsche wanted to build a prototype and experience how this use case can actually work when the vehicle is offline and thus not able to access any resources from the internet. And this is where FogHorn comes in, a US-based company that claimed to have an edge intelligence solution for this.
FogHorn is a leading developer of “edge intelligence” software for industrial and commercial IoT application solutions. Their Lighting™ Edge AI software platform brings the power of advanced analytics and machine learning to in-vehicle and the on-premises edge environment enabling a new class of applications for advanced monitoring and diagnostics, machine performance optimization, proactive maintenance, and operational intelligence use cases.
Joining Forces at Startup Autobahn: 100 days of Edge Computing in a Porsche
During the Startup Autobahn program, which provides an excellent framework for startup and corporate cooperation, Porsche wanted to implement the joint project with FogHorn to validate their claims and see how they work with edge computing. It was all about allowing customers to open the drivers’ door of their car without any friction — but how? We wanted to achieve this by using a camera for face recognition, an infrared camera for spoofing detection and a Bluetooth sensor to detect the proximity of the driver’s mobile phone — three examples of multifactor driver authentication. The goal: unlock a real Porsche vehicle.
Within the 100 day program, we worked in weekly sprints. During the first weeks, FogHorn evaluated different machine learning algorithms and cameras. Later, real camera images were used to train the algorithms and prepare the demonstration at the Expo Day — where the prototype was supposed to actually work in real life.
FogHorn provided the edge intelligence solution for face recognition, training in the cloud, pushing down the trained model to the edge and the evaluation of the camera images while being offline. Meanwhile, Porsche provided the integration to unlock the car as well as mobile phone detection via Bluetooth.
Unlocking a Porsche and New Potentials
After the intense work period, we were able to present a functioning, highly-developed solution at the Startup Autobahn Expo Day #6. There was no need for any workarounds: the pre-trained model of a few people was available on the edge within the vehicle and thus the system could perform the recognition standalone in offline mode — live. We presented a superb user experience and were able to showcase the edge computing capabilities in a vehicle to all visitors.
To us, the Startup Autobahn project was a full success. FogHorn fulfilled their promises — and together, we were able to implement it into a Porsche car within 100 days. Once again, the innovation platform proved to not only provide the opportunity to collaborate with industry-leading companies but also accelerate deployment with real projects.
But this was only the beginning. There are many more use cases of edge computing in the automotive industry and we’re now looking further into the possibilities of the technology to enhance the driving experience — let’s push it to the edge together!
Chad Boulanger is Managing Director and VP for AI EMEA at FogHorn Systems, Inc. Matthias Hub is IT Project Manager and Prototyper at Porsche AG. Follow us on Twitter (Porsche Digital, Next Visions), Instagram (Porsche Digital Lab Berlin, Porsche Digital, Next Visions) and LinkedIn (Porsche Digital Lab Berlin, Porsche Digital) for more.