Autonomous Systems

At a glance

© Fotolia

Autonomous systems are essentially concerned with determining how a given system should behave according to a great many observed environmental parameters. This means that, unlike for traditional remote systems, the goal is to avoid operational control via another system (e.g. a person). In complex situations, relying on remote systems can be problematic since a complete survey of the necessary events by a person can often lead to long response times. In the era of automation, the solution is to have independent systems.

The technology

Process steps towards automated action

The key point is that technical “assistants” are playing an increasingly important role in everyday life and their functions and responsibilities are becoming more and more complex. As a general rule, environmental data collected by sensors must be processed and evaluated. Take the flood of data provided by smartphones; in the near future, this is to be individually filtered instead of having references and notifications add to it. But user experience is improved only when this selection is automated. The next step will be when this kind of machine learning becomes established in everyday life, which means we will all encounter it in a variety of ways. However, the basic principle is the same: systems learn to provide tailored information and supply only the data necessary. Fraunhofer IIS puts its main focus on local, real-time systems without access to vast amounts of data or computing capacity.

The institute has the requisite expertise in sensor fusion, machine learning, positioning and SLAM. What data gets collected and evaluated is part of the automated action that depends on the individual requirements placed on the system. So the “assistant” evaluates a situation and generates options for action; the actions themselves are divided into long-term/high-level and short-term/low-level.

 

Reinforcement learning

In the past few years, one thing that has become particularly important is reinforcement learning, whereby an agent interacts with its environment to independently draft a strategy for solving a given problem. To do so, the agent independently “explores” the requisite data set in order to derive rules for how actions or decisions are carried out. This eliminates the need for supervised learning from gathered data.

Applications for reinforcement learning include the control of machines or vehicles, since these are areas in which data is not available in advance. In traditional control engineering, (physical) models are used to design certain rules. But here too, each model represents a mere approximation of reality. The goal of reinforcement learning is then either to approximate the model and integrate it into a set of traditional rules or to directly replace the rules as end-to-end learning.

© Fotolia

We offer

Vernetzung der Welt
© Fotolia

Expertise

Fraunhofer IIS pools expertise that is essential for automated systems: from sensor fusion and machine learning to positioning. Automated systems are however still in their infancy and offer vast potential for research and development – which we are happy to undertake in collaboration with you, tailored to your requirements.

Research collaboration

Together with the Friedrich-Alexander-Universität Erlangen-Nürnberg, Fraunhofer IIS is also expanding its range of teaching events, for instance for deep and reinforcement learning or machine learning. From the end of 2018, there will be a new exchange platform – the Machine Learning Forum – through which students, industry and educational institutions can exchange information. This will advance the field of automated systems, supported by the German Federal Ministry of Education and Research, which put this project out to tender.

 

ESI-Automotive

Developing reliable detection of passers-by using a combination of camera, LIDAR and RADAR sensors.