A Spotlight On Porsche’s AI Collaboration Projects
Since 2017, Porsche is a partner of the innovation platform Startup Autobahn. There, young start-ups and industry-leading companies join forces to drive innovative technologies forward towards the future of mobility. Here’s a look at four of our most exciting AI collaboration projects.
Artificial Intelligence (AI) is omnipresent — and yet sometimes difficult for the general public to grasp. The term AI alone is used so liberally that probably hardly anybody knows what exactly is being referred to. To give you a better sense of what is possible with the technology in regards to mobility, we have collected some of our most exciting AI-driven projects to share. These are collaborations with start-ups that may one day hit the road — and define the Porsche experience of the future.
The collaborations ignited at the innovation platform Startup Autobahn. For more than four years, we have been partnering with Startup Autobahn, developing and realizing more than 70 innovative solutions and pilot projects together with many startups. The solutions range from moving sensor technology, VR entertainment for passengers or autonomous driving in the workshop, and far beyond. Take a look!
HiAuto — Next Level Voice Control
Many speech recognition platforms today suffer from poor recognition rates in a noisy environment. Kids on the backseat of your car, a chatty passenger, music, or driving around in your convertible can make it hard to control your car via voice. HiAuto is here to change that. The Tel-Aviv-based start-up and Porsche worked together on speech recognition technology that can block out all disturbing noises, so the in-car voice assistant is able to understand the commands made by the driver properly.
Porsche and HiAuto used deep learning software to recognize who exactly is talking via a microphone and a camera and to separate background noise from voice commands. You can blast your sound system while going fast in your convertible on the autobahn and still give a voice command. “We wanted to validate if a system that uses video and audio can be better than the current industry standard,” as project lead and electric engineer, Marius Schach explains.
Monk AI — Automated and Smart Damage Detection
Many people fulfil their dream of driving the legendary Porsche 911 with the help of Porsche’s innovative leasing and rental offers. However, every year companies spend vast amounts of time and money assessing the condition of vehicles. 99 percent of these inspections are still done manually, despite the costs associated with it. Damages are often not discovered or assessed incorrectly. This can lead to negative user experiences.
“We want to make sure that the customer can walk away with a good feeling — knowing that there is no more cost,” says Antoon Versteeg, innovation manager and project lead.
In times where each of us carries around a device with a high-resolution camera and constant internet connectivity, MonkAI worked to find an adequate solution to this. The French software start-up develops computer vision algorithms to analyze any item’s condition based on visual aspects. You only need a smartphone camera.
Foghorn — Edge Technology to Unlock your Porsche
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.
“We wanted to evaluate how FogHorn’s technology can be applied to a car manufacturer like us,” says Matthias Hub, who was managing the project from Porsche’s side. Eventually, Porsche joined forces with the US-based start-up to develop a prototypical edge solution that enables the keyless and easy unlocking of a Porsche vehicle. FogHorn evaluated different machine learning algorithms and trained them with real camera images, Porsche provided the integration to unlock the car as well as mobile phone detection via Bluetooth. At 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.
MX Automotive — Managing the Data Stream
The more data is generated, the more demanding it becomes to interpret it correctly. This also applies to cars. Sensors constantly supply data points, but how do you find exciting correlations in a mountain of information?
MX Automotive offers a solution called SiaSearch for classifying the contents of measurement reports. In the project with Porsche (led by Dr.-Ing. Johannes Bach), the start-up company worked on a solution that identifies different manoeuvres within the data, such as a lane change or an overtaking manoeuvre. This allows the R&D department to use a tool to search for these manoeuvres, read out the measured values in a targeted pattern — and analyze the effect on different vehicle parts in order to optimally adjust and improve vehicles.
One thing is for sure: AI technology offers enormous innovation potential for the future of mobility. These projects are only a small glimpse into what Porsche is researching and working on to get the future on the road. A process that is far from complete: We extended our cooperation with the innovation platform Startup Autobahn for another three years and are looking forward to building more solutions that combine the classic Porsche-feeling with smart and innovative technologies.
Andy Grau is an Innovation Manager at Porsche AG.
About this publication: Where innovation meets tradition. There’s more to Porsche than sports cars — we’re tackling new challenges, develop digital products and think digital with a focus on the customer. On our Medium blog, we tell these stories. It’s about our #nextvisions, smart technologies and the people that drive our digital journey. Please follow us on Twitter and LinkedIn.
