More than just self-driving technology: the future of the automotive industry
More recently, innovations in the automotive industry have focused on increasing engine power and then increasing efficiency by improving aerodynamics, comfort and redesigning the appearance of vehicles. Today, hyper-connectivity and automation are driving the automotive industry into the future. Driverless cars are the first thing that comes to mind when thinking about the car of the future, but tomorrow’s automotive industry will offer much more than self-driving technologies.
One of the key factors driving the transformation of cars is their connectivity — connectivity that paves the way for remote updates, predictive maintenance, improved driving safety, and protection against cyber threats. The cornerstone of connectivity, in turn, is data collection and storage.
Of course, the expansion of the car’s connectivity capability has increased driving pleasure, but the focus is on the collection, processing and generation of large amounts of data by the connected car. According to last year’s projections, over the next decade, self-driving cars will learn to generate so much information that they will need more than 2 TB to store it, much more space than today. . And that’s not the limit: as technology advances, the number will only increase. Against this background, device manufacturers must ask themselves how they can effectively meet the demands of massive data growth in such an environment.
How will the architecture of unmanned vehicles evolve?
Continuous improvement of functions such as managing data generated by unmanned vehicles, object recognition, map navigation, and decision-making largely depends on the success of machine learning and artificial intelligence models. The challenge for automakers is clear: the more advanced the machine learning models, the better the driving experience for users.
At the same time, the architecture of unmanned vehicles is evolving in the name of optimization. Manufacturers are increasingly opting for a large network of microcontrollers installed for the needs of each specific application, preferring instead to install a large processor with plenty of processing power. It is this transition from multiple automotive microcontrollers (MCUs) to a single central MCU that will likely be the most significant architectural change in cars of the future.
Transfer data storage function from car to cloud
Unmanned vehicle data can be stored both directly onboard, when fast processing is required, or in the cloud, which is better suited for in-depth analysis. The data routing depends on its function: there is data that the driver needs immediately, for example information from motion sensors or location data from a GPS system, and based on this the car manufacturer can draw important conclusions and work further on improving the ADAS driver assistance system.
In a Wi-Fi coverage area, sending data to the cloud is economically feasible and technically simple, but when the car is in motion a 4G (and possibly 5G) connection may be the only option available. And if the technical aspect of data transmission over a cellular network does not cause serious doubts, then their cost can be incredibly high. Because of this, many self-driving cars need to stay close to home or some other place where they can connect to WiFi for a while. This is a much cheaper option to upload data to the cloud for further analysis and archiving.
The role of 5G in the fate of connected cars
Existing 4G networks will continue to be the primary communication channel for most applications; However, 5G technology may become an important catalyst for the development of connected and autonomous cars, as they enable them to communicate with each other, buildings and infrastructure (V2V) almost instantaneously. , V2I, V2X).
Self-driving cars cannot function without a network connection, and 5G holds the key to faster connectivity and lower latency that future drivers will benefit from. Faster connection speeds reduce the time it takes to receive collected data from the vehicle, allowing the vehicle to respond to sudden changes in traffic or weather conditions almost immediately. The advent of 5G will also mark a turning point in the development of digital services for drivers and passengers to enjoy their journey even more, thereby increasing potential profits for these service providers.
Data security: who has the keys?
It goes without saying that autonomous vehicles must be protected by state-of-the-art cybersecurity. According to a recent study, 84% of respondents in the IT and automotive industries expressed concern that automakers are not keeping up with the increase in cyber threats.
Here are some of the measures that will help automakers ensure the security and integrity of data used by self-driving vehicles.
1. Cryptographic protection restricts access to encrypted data to a specific group of people who know the current “key”.
2. End-to-end security involves the implementation of a variety of measures to detect a hacking attempt at every entry point of the data transmission line, from microsensors to 5G communication towers.
3. The integrity of the data collected is an important factor and implies that the information received from the vehicles remains intact until it is processed and converted into a meaningful result. If the converted data is corrupted, the “raw” data can be viewed and processed again.
The Importance of Plan B
In order to be able to fulfill all critical tasks, the vehicle’s central storage system must function reliably. But how can automakers ensure these goals are met when the system fails? One way of avoiding accidents when the main system fails would be to store the data on a redundant computer system; However, this option is incredibly expensive to implement.
So some engineers have gone the other way: They’re working to create backup systems for individual car components involved in unmanned driving, specifically brakes, steering, sensors, and computer chips. Which means a reduction in costs and on the other hand still ensures everything to ensure protection in the event of a system failure.
As autonomous vehicle design evolves, the entire evolution of transportation will be driven by data. By adapting machine learning algorithms to process the massive amounts of data autonomous vehicles rely on and implementing robust and actionable strategies to protect them from external threats, manufacturers can finally design a car that is safe enough , deal with it. Guide. The digital roads of the future.