We are searching data for your request:
Upon completion, a link will appear to access the found materials.
The automotive industry can benefit from innovative and cost-effective ways of using the vast amount of data generated by in-vehicle sensors and control units. When value is extracted from the data, it can help improving vehicle safety and autonomy at lower operational costs.
"Data driven insights will be key to innovation in the automotive and automotive insurance sectors, as a result, capturing highly accurate information from cars is the basis needed to drive to these insights." --Katelyn Johnson, Principal at American Family Ventures
Teraki's new cloud-based Development Center for Artificial Intelligent (AI) applications now enables automotive electronics developers to test-drive using their own data.
Automotive electronics applications developers such as automotive Original Equipment Manufacturers (OEMs) and Tier 1 electronic suppliers can now use a cloud-based data training and prototyping environment that allows them to train Teraki's algorithms on their own data.
Berlin-based, privately held and funded, Teraki is an automotive AI startup that provides breakthrough edge data processing software to meet the expanding data demands of the automotive electronics industry.
The company's AI-based Intelligent Signal Processing software delivers over 10 times increase in automotive chip, communications, and learning performance. According to the company, this results in highly accurate AI applications possible at scale in embedded environments.
Edge computing: A fundamental pillar for the automotive industry
The exponential growth of data that comes from connected and autonomous vehicles requires the use of Edge computing. Edge computing refers to computing located close to the data source.
In connected vehicles, this means close to sensors. Data generated by vehicles is quickly increasing and becoming a challenge. The data collected by the sensors is in part transferred to the cloud.
Edge computing is also required for safety-related functions. These functions have to be available at all times without interruptions. For now, these functions cannot rely on wireless connectivity since 5G is not going to be available everywhere, at least for the first years.
According to Teraki, many applications in the car are safety-related or real-time and can't fully rely on a network. Therefore, these applications will need to operate autonomously inside the vehicle.
For example, if an autonomous vehicle is on a highway and needs to break due to an emergency, the emergency braking can't afford any delays of computational and transmission latencies. If it does, the passengers in the car could be at risk.
For Teraki, the data that comes from safety critical applications running in cars has to be processed near the sensors to be accurate and reliable. That is why Edge computing plays an important role when accurate and fast decisions can make a difference, especially in an emergency.
There are still challenges to do this quickly and accurately due to constrained computing capacities. There is room for improvement. The main challenge in Edge computing is to bring Machine Learning and Artificial Intelligence from the cloud to the devices at the Edge.
Or to bring Machine Learning and Artificial Intelligence to the actual sensors at the very Edge. Teraki says that the specific challenge is how to process data accurately and efficiently in environments with far less computing power and storage capacity.
Teaching AI models or machine learning algorithms
Data training is a very essential step used to teach Artificial Intelligence models or Machine Learning algorithms on how to make data-driven predictions or make decisions by building a mathematical model from input data.
According to Teraki, their Development Center is unique to the industry. It automates the complex process providing development teams with the opportunity to quickly train Teraki's machine learning algorithms based on their own data.
It also lets developers evaluate exactly what performance advantages Teraki's technology can provide.
"With the DevCenter we have automated data training tasks, allowing development teams to test our solution with their own data more quickly," says Markus Kopf, Teraki's co-founder, and CTO. "Automating this entire process is complex and difficult."
According to Kopf, their current customers find it "much easier to experience by themselves what Teraki's technology can do in terms of edge processing and performance improvement that can lower their hardware and data communication costs, improve their applications and algorithms, and create new possibilities in the automotive systems of tomorrow."
The company has completed several pre-production validations by premium automotive manufacturers, as well as successful integrations on a variety of microcontrollers. All in all, exciting times ahead for the automotive industry.