Advancing connected vehicle through Automotive EDGE and LEAF on AWS

It’s no secret that most new cars are connected. But connected car capabilities have come a long way: from an OnStar button almost three decades ago, to in-vehicle internet connectivity, to the multitude of information and entertainment options that modern cars provide today. And yet, we are still at the beginning of this road, with a lot more to come as we enter the new automotive era.

In this two-part blog series, we first walk you through the challenges and opportunities of connected vehicles, providing a high-level overview of the Luxoft Edge Acceleration Framework (LEAF) solution, designed to manage edge workloads and address some of the common challenges associated with connected vehicles. In part 2, we delve into the detailed architecture, solution functionality, and benefits.

In this first post, we discuss the challenges and opportunities of connected vehicles and show a way to help accelerate the transition to “software-defined vehicles” (SDVs).­­­ We provide a high-level overview of the Luxoft Edge Acceleration Framework (LEAF) solution, designed to manage edge workloads.

Connected – Options: Cloud versus edge

The automotive industry is embracing the cloud because, among other reasons, the cloud helps facilitate many intelligent vehicle capabilities developed by automakers that users really want.

While advancements are being made, there appears to be an underlying differing view concerning connected vehicle systems. In some discussions, we notice two different perspectives being expressed: –

• Regarding connected vehicle systems, the cloud component plays an important role as it possesses extensive computing power, surpassing the computational abilities within the vehicle itself.
• However, the vehicle component (edge) is equally essential because it represents the direct interface where the actual implementation and functionality of the system take place, interacting with the physical environment.

Ultimately, both sides are true – the most important aspect in connected systems is the close interoperation between cloud and edge. The differing vantage points are not unique to the automotive industry; similar debates have unfolded in other industries that have implemented connected systems (otherwise known as Internet of Things (IoT) solutions.) In other industries such as manufacturing, healthcare and retail, debates around IoT have already settled down, but in the automotive industry, these topics are still fresh. On the bright side, this gives the benefit of hindsight so that the automotive industry can apply the IoT lessons learned from other industries.

What do we mean by “edge”?

Before exploring the relationship between cloud and edge in more detail, let’s clarify our definitions.
The word “edge” has different meanings depending on the context. In the connected vehicle context, edge means the ability to run high-level dynamic workloads in the vehicle’s centralized compute hardware that acts as the gateway to the cloud IoT system. This is in contrast to the vehicle’s numerous electronic control unit (ECU) modules that mostly have low-level fixed functions. The edge workloads consist of user-facing functionality, as well as internal functionality, such as collecting diagnostic information and performing updates.

This ability to act as an edge device within a larger cloud-based system is a defining characteristic of a connected vehicle and is also a deliberate decision by the automaker, who controls and designs the architecture in this way. In other words, to be a connected vehicle, it’s not enough for a vehicle to simply consume services (such as internet radio) from the web. Keeping this aspect in mind, connected vehicles perform intelligent functions under the supervision of a cloud-based connected system. In the rest of this article, we’ll use the terms “edge” and “connected vehicle” interchangeably.

Why vehicles and cloud complement each other?

Autonomous driving is a great example of intelligent vehicle capabilities based on artificial intelligence (AI)/ML technology that will help differentiate the vehicle experience and delight users. Let’s consider how close interoperation between cloud and edge will help deliver such intelligent capabilities.

Vehicle has local data

To make an intelligent feature highly relevant, its ML model should be trained on the data that is close to the user. “Close,” means that data is about this vehicle’s operation and occupants, rather than some other vehicle’s data. An ML model trained on such data will have the highest accuracy in anticipating the user’s needs and preferences. It will offer a personalized user experience that will increase customer satisfaction. In fact, the most advanced of modern vehicles already have sufficient compute resources to train such ML models inside the vehicle.

Cloud has variety

Now, imagine a car that has always operated in California or Texas and has trained its own vehicle models based on the hot temperatures that it has encountered. What will happen if the user takes a road trip to Canada? The models may experience difficulties or behave unexpectedly. To avoid this, the models need to be trained on data from diverse fleets of vehicles operating in different environments. This is where the cloud can help automakers by providing access to vast datasets from vehicles operating in a wide range of climates and conditions.

“Two heads are better than one”

Synergy benefits can be achieved by combining the two approaches mentioned above. For example, the federated learning technique can be used to train local models on individual vehicles and then the local models in the cloud to make the resulting intelligent feature more robust in varied conditions.

Using this approach, the OEM can train Local models on more detailed data that is available only inside vehicles, because the cost of transferring full-resolution data to the cloud would be prohibitive.

These are just a few examples of the benefits that can be achieved through close interoperation between cloud and edge. We discuss more examples in the next section.

How the “cloud + edge” formula helps meets the needs of the automotive industry

The automotive industry consists of many participants and components, and they all have different needs that can be met by bringing cloud and edge closer together. From the vehicles themselves to the manufacturers and end-users, each player in this industry stands to gain from the seamless integration of cloud and edge technologies. Let us consider some of them.

Connected vehicles

Connected vehicles require remote monitoring and management capabilities. This necessity becomes even more evident when vehicles achieve full autonomy, as there won’t be a human driver present to identify potential issues or malfunctions. However, even contemporary vehicles with human drivers can benefit from such remote monitoring systems, as not all drivers possess the expertise to promptly recognize every minor issue or problem with their vehicle.

Additionally, connected vehicles must have regular over-the-air (OTA) updates. Here are a few reasons:

• Just like with smartphones and computers, connected vehicles require regular updates to maintain continued protection against evolving cyberthreats.
• ML models need to be regularly updated due to “model drift”—when a model loses its predictive quality due to the gradual evolution of real-world phenomena that the model was trained on.
• Users expect modern vehicles to constantly improve with new features and capabilities.

Cloud

Even with its seemingly infinite resources and enables the OEM needs to manage its connected vehicles. The connected vehicle needs to perform an orchestration in which the cloud leads and the edge follows. This close coordination will benefit:

• Capacity. While the cloud is much more powerful than individual vehicles’ compute capabilities, it is still not unlimited. To avoid being the bottleneck when managing hundreds of millions of connected vehicles, the cloud needs to offload tasks that can be performed at the edge.
• Connectivity cost. Allowing the edge to be more self-sufficient will reduce communication frequency and help save on connectivity costs.
• Performance and latency. Some actions with tight latency requirements must be performed in the vehicle.
• Disconnected operations. Vehicles will continue operating even when disconnected from the cloud temporarily.
• Privacy. Certain data like camera feeds may contain sensitive personal information that users prefer not to transmit off the vehicle for privacy reasons. Local processing keeps this data contained.

Automakers

There are several areas where closer collaboration between vehicle and cloud sides will benefit automakers:

• Development: Adopting uniform toolsets and processes across vehicle and cloud sides would streamline the development process and facilitate collaboration between teams working on different components. This approach would enable seamless integration, efficient knowledge sharing, and consistent practices, ultimately accelerating the development of new vehicle features and enhancing agility in the automotive software-defined vehicle (SDV) domain.
• Testing: Testing vehicle functionality is complex, time consuming and needs powerful compute. By leveraging cloud computing resources, the OEM can run massive simulations and virtual testing environments in the cloud, scaling up computing power and storage as needed. This allows them to quickly test thousands of real-world scenarios and edge cases that would be impractical, expensive, or even dangerous to test physically. The elasticity and on-demand nature of cloud resources enables automotive companies to run complex testing workloads cost-effectively without having to build out expensive on-premises infrastructure.
• Deployment. Extending deployment toolsets from the cloud side to the vehicle would help streamline the product life cycle.

Vehicle users

Users expect intelligent vehicle capabilities that are possible only through unified interoperation between cloud and edge. This seamless integration can help ensures that vehicles can offer real-time updates, personalized experiences, and enhanced safety features, all while adapting to the evolving needs of the driver. Moreover, the ability to process data both in the cloud and at the edge allows vehicles to respond more quickly to changing conditions, providing a smoother and more reliable driving experience.

Automotive network

The automotive network needs a modern technological foundation, with cloud and edge working in unison, to meet the needs of the future. That’s because the vehicle of tomorrow will be much more than just a powerful motor and comfortable seats.

Connected vehicles are anticipated to engage in complex interactions with their surrounding environment, whether navigating the streets of a smart city or coordinating long-range tasks such as reserving a charging station miles away. While current vehicles are focused on advancing powertrain technologies, the next phase of technological evolution will shift towards artificial intelligence. The systems being developed must therefore be designed with the foresight to accommodate this shift, ensuring that they are fully equipped to support the sophisticated demands of future mobility.

LEAF: The Luxoft Edge Acceleration Framework

Luxoft has partnered with Amazon Web Services (AWS) to introduce the Luxoft Edge Acceleration Framework (LEAF), a solution designed to bridge the gap between cloud and edge computing, bringing significant benefits to the entire automotive network.

LEAF draws upon best practices from both cloud computing and vehicle systems to establish a flexible foundation for the long-term evolution of connected vehicles. It also incorporates key principles of Software Defined Vehicle (SDV).Ops—Luxoft’s methodology for the agile development of software-defined vehicles. The LEAF solution is designed to:

• Streamlines cloud-based development, testing, and deployment of OEM’s software to the edge, eliminating the complexities associated with varied hardware.
• Enhances and automates continuous integration/continuous deployment (CI/CD), accelerating the integration of software platforms capable of supporting diverse and innovative use cases, thus facilitating the advancement of SDVs.
• Provides feature to apply modern DevOps techniques, by using AWS services like AWS CodePipeline (which automates continuous delivery pipelines for rapid and reliable updates) and AWS CodeBuild (a fully managed continuous integration service).
• Provides a software-in-the-loop (SIL) testing approach that decouples the testing process from hardware, utilizing a virtual environment powered by Amazon EC2 instances. This approach offers secure, resizable compute capacity for virtually any workload, based on AWS Graviton processors, which deliver the best price performance for cloud workloads running on ARM-based Amazon EC2.

Figure 1: LEAF logical diagram

Conclusion

As a recognized innovator in the field of SDVs, Luxoft collaborates with its strategic partners like AWS to further the progress of connected vehicles. “Edge to cloud” is a key focus of this investment, and the future release of LEAF on AWS will help support automotive clients in the process of adopting innovative solutions in this area.

You can stay informed about our advancements in various SDV topics by visiting luxoft.com/industries/automotive or by following us on LinkedIn.