Deep Learning has increased interest in using artificial intelligence in more and more systems. Reinforcement Learning in Machine Learning has also experienced an upswing. However, despite these impressive recent successes, it still faces the challenge of being accepted and successfully deployed. This is especially true for safety-critical tasks such as robotics, autonomous driving, and industrial control. One approach that can help address this problem is Hierarchical Reinforcement Learning.

Reinforcement learning (RL) is one of three main machine learning (ML) paradigms. Unlike the other two, supervised learning and unsupervised learning, in reinforcement learning the learning takes place in direct interaction with the surroundings. A brief introduction follows.

Leaving cooperative, heterogeneous robots alone in unstructured environments isn’t such a good idea. After all, only with an AI-powered management solution will they be able to solve complex tasks without causing any damage. The Fraunhofer IKS is working on developing such a system.

From medical diagnosis to quality control, visual information is often used to make important decisions. Automating these decisions can relieve the burden on experts and avoid errors. This requires complex AI systems whose development involves large amounts of data, and which are generally unable to make reliable predictions. FAST attempts to provide an answer to these problems: a framework for developing reliable AI systems with little data.

In our previous article, we introduced some standardized terminology related to Autonomous Driving and Operational Design Domain (ODD). In this article, we look at the safety implications of transitioning through multiple ODDs while executing the Dynamic Driving Task (DDT).

How can intelligent systems learn to perform tasks – and do so simply by interacting with their environment? This is the subject of reinforcement learning, a subfield of machine learning. Problems occur primarily when situations arise that the system is not yet familiar with.

Can deep neural networks in image processing reliably recognize new, unknown test patterns? First considerations for different methods — especially for safety-critical applications.

The system in autonomous vehicles must be able to reliably detect pedestrians. Deep learning approaches are the main method used for this task. However, in comparison with classic software, the results of these approaches must also be checked and verified, which requires various complicated technical measures. This article provides an overview of these measures.

In the field of modern warehouse logistics, speed is crucial to success. This is where autonomous mobile robots (AMR) come in. In order to perform their tasks, they must respond as flexibly as possible to new environmental conditions and warehouse goods. ResilientSOA, the framework developed by Fraunhofer IKS, provides the necessary prerequisites. In this interview, project manager Florian Wörter explains exactly how it works.

In modern perception applications, such as in medical engineering, models based on artificial intelligence (AI) are increasingly being used due to their strong performance. However, this increasing performance often comes at the cost of the transparency of results. An online tool developed by the Fraunhofer Institute for Cognitive Systems IKS can help here.