Hi, my name is Bernhard. I am heading the robot systems research group at ROBOTICS - the institute for robotics and mechatronics in Klagenfurt, Austria.
In addition, I am an advisor to ALIAS Robotics S.L. (https://aliasrobotics.com). Together, we are pushing to make future robots secure.
My current research interests include robotics and especially software and security for modern robots. During my PhD I have engaged myself in resource-awareness for visual sensor networks, smart cameras and computer vision.
My overall vision is to enable future robots to be a trustworthy part of our everyday life. To achieve this, I am working on making robots secure on the one hand and on the other hand, I am engaging in ethical issues revolving around robots and future technologies. Further, we are working on the quality (especially testing) of robot sofware.
PhD in Information Technology, 2013
Alpen-Adria Universität Klagenfurt, Austria
DI in Applied Informatics, 2008
Alpen-Adria Universität Klagenfurt, Austria
ROS is the most popular framework in robotics research and it also grows in terms of industrial use. This makes ROS a worthwhile target for attackers especially since security is not addressed by the core framework itself. Its open architecture and flexibility are also the reasons why ROS suffers from security issues. For example, in ROS it is possible to isolate single nodes from the rest of the application without the ROS master, the other nodes or even the node itself (i.e., its business code) noticing it. This is true for publishers, subscribers and services alike. This makes attacks very difficult to spot at runtime. Penetration testing is the most common security testing practice. The goal is to test an application for possible security flaws. To better facilitate penetration testing for ROS, we introduce ROSPenTo and Roschaos, tools that make use of the vulnerabilities of ROS and demonstrate how ROS applications can be sabotaged by an attacker. In this tutorial you will learn about the ROS XML-RPC API, which is our main attack point. You will see, how API attacks on ROS work in depth. You will get to know Roschaos and ROSPentTo, two tools, which can be used to manipulate running ROS applications.
Today, camera networks are pervasively used in smart environments such as intelligent homes, industrial automa tion or surveillance. These applications often require cameras to be aware of their spatial neighbors or even to operate on a common ground plane. A major concern in the use of sensor networks in general is their robustness and reliability even in the presence of attackers. This paper addresses the challenge of detecting malicious nodes during the calibration phase of camera networks. Such a resilient calibration enables robust and reliable localization results and the elimination of attackers right after the network deployment. Specifically, we consider the problem of identifying subverted nodes which manipulate calibration data and can not be detected through standard cryptographic methods. The experiments in our network show that our self-calibration algorithm enables location-unknown cameras to successfully detect malicious nodes while autonomously calibrating the network.
With ongoing research in robotics, some specific architectural approaches of robotic systems earn more and more interest by all kinds of industries. Mobile manipulators–robots consisting of a mobile base and a serial manipulator–provide the ability to make robotic manipulation location-independent, which will be an essential feature in future production. Such robot platforms offer a high level of flexibility and efficiency of robot applications. Especially under the aspect of modularity, mobile manipulators would provide even more flexibility by offering the possibility to exchange or extend the robot hardware for specific applications. To achieve this, modularity also has to be considered in software. In this paper, we present a software architecture for modular mobile manipulation applications. It provides mechanism for reconfigurability, easy programming, and an easy approach for adding external hardware components. Being targeted at industrial use, the architecture also considers security and software deployment aspects. These considerations will, in combination with all the other aspects, be presented by means of two modular mobile manipulation platforms and a set of representative scenarios.
Using the effects of quantum mechanics for computing challenges has been an often discussed topic for decades. The frequent successes and early products in this area, which we have seen in recent years, indicate that we are currently entering a new era of computing. This paradigm shift will also impact the work of robotic scientists and the applications of robotics. New possibilities as well as new approaches to known problems will enable the creation of even more powerful and intelligent robots that make use of quantum computing cloud services or co-processors. In this position paper, we discuss potential application areas and also point out open research topics in quantum computing for robotics. We go into detail on the impact of quantum computing in artiﬁcial intelligence and machine learning, sensing and perception, kinematics as well as system diagnosis. For each topic we point out where quantum computing could be applied based on results from current research.
Mobile manipulation will play an essential role in future production’s intralogistics. In addition, it can be assumed that location-independence of manipulation will greatly contribute to flexible production and higher efficiency in robot use. Modular mobile manipulators can be combined from standalone robotic components like mobile platforms and serial arms. This combination enables more flexibility since the robot can be adapted to specific use-cases by exchanging hardware. However, since those robots tend to be very complex systems, their integration into networked Industry 4.0 environments will also cause security risks. In this paper, we present a security architecture and secure interaction workflows for modular mobile manipulators that on the one hand secure the system against unauthorized manipulation and on the other hand enable the integration of mobile manipulators into larger IT infrastructures. Using the example of our inhouse-developed CHIMERA mobile manipulator, we show which architectural means can be considered in order to make a modular mobile manipulator secure. We analyze the expected attack vectors on mobile manipulators and describe their mitigation within our architecture.
Research project “Engineering proprioception in Computing Systems (EPICS)”
We are regularily providing software to the community as part of our work.
You can find an overview of our public projects at Github
The ROS Penetration Testing Tool can be used to explore the insecurity of the robot operating system (ROS).
Rosmap is a tool to scan dependencies and extract metrics from ROS repositories at large scale. This tool is described in our paper Can I depend on you? Mapping the dependency and quality landscape of ROS packages.
The ROS message parser is more of an internal project (however, read below). It is used to generate parsers for ROS message files and ROS message definitions from the wire protocol in .net core. The however: it contains a antlr grammar file that can be used to create corresponding parser in many other programm languages. This might be useful for some.
The Ella middleware was part of my work at the Alpen-Adria Universität. It is a publish-subscribe middleware written in native C#.
This is a software framework for evolutionary multi-objective optimization.
The goal of this project is to work on the technical fundamentals to make future robots credible (that is, perceivable trustworthy). We …
This project aims to increase the public awareness and discussion on robotics. We host different events to get in touch with the public …
In CollRob (Collaborative Robotics), we are working on new methods for human-robot collaboration.