Skip to main content

Institute for Cyber Security and Privacy (ICSP)

20190814_fbinf_hochgeschwender_nico_portrait.jpg (DE)

Prof. Dr Nico Hochgeschwender

Professor

Unit

Department of Computer Science, Institute for Cyber Security and Privacy (ICSP), Institute for Artificial Intelligence and Autonomous Systems (A2S)

Research fields

  • Software Engineering for Autonomous Systems
  • Safety and Security of Autonomous Systems
  • Domain-specific Modeling and Languages for Robotic and Autonomous Systems
  • Explainabe AI

Location

Sankt Augustin

Room

C 206

Address

Grantham-Allee 20

53757, Sankt Augustin

Telephone

+ 49 2241 865 9634

Research Projects

SESAME (Safe and Secure Multi-Robot-Systems)

The overarching goal of SESAME is to develop an open, modular, configurable, model-based approach for systematic engineering of dependable MRS. The approach is supported by a set of public meta-models, components and configuration tools produced by the project. Target MRS may employ AI, and will be capable of operating dependably in open configurations, and in conditions of uncertainty that include the acknowledged possibility of cyber-attacks. Five novel applications that add value to the European science and economy will be developed and verified for dependability using the SESAME approach.

Project management at the H-BRS

Prof. Dr Nico Hochgeschwender
Teaser Placeholder
Safe Airframe Inspection using Multiple UAVs (SAFEMUV)

Assuring the safety of teams of autonomous unmanned aerial vehicles (UAVs) that carry out a safety-critical inspection task collaboratively is very challenging due to uncertainties and risks associated with the operating environment, individual UAV failures, inconsistent global perspective between team, interference and/or contention because of limited physical space, and unreliable communication. In SAFEMUV, we will extend, adapt, and integrate our recent research and the latest advances from operational risk assessment for UAVs, managing variability in robotic systems through feature modelling, and automated synthesis of models and testing campaigns for assessing system robustness. In a nutshell, SAFEMUV will deliver a process for systematic robustness assessment of UAV teams underpinned by methods for the specification, generation and testing of collaborative inspection scenarios, enabling the progressive transition from simulation to lab-based operations and to real-world operations; and a demonstrator that realises this process using an a simulated environment, an indoor flight arena and an outdoor space at Luxembourg Airport.

Project management at the H-BRS

Prof. Dr Nico Hochgeschwender
Teaser Placeholder
Metrological Evaluation and Testing of Robots in International Competitions (METRICS)

The main objective of METRICS is to organise challenge-led robotics competitions as clear, rigorous and effective evaluation campaigns for the four priority areas, namely healthcare, agile production, inspection and maintenance and agri-food. These competitions are a cornerstone for the effective design, manufacture, deployment and modification of robotic systems. To this end, METRICS will design metrology-grade methods for robotics evaluation, maximise the take-up of the evaluation and benchmarking tools, ensure the industrial relevance of challenge-led competitions, attract industrial stakeholders, academics and the general public to competitions, maximise the compliance of robots with ethical, legal, social, economic requirements, help to fill the normative gap for intelligent robotic systems by designing evaluation plans as representative standards, and structure the European robotics community around competitions in the four PAs and ensure its sustainability.

Project management at the H-BRS

Prof. Dr Nico Hochgeschwender
Teaser Placeholder
Verifiable Composition of Dynamics and Control Algorithms for Robot Motion (VeriComp)

Generating robot motion is mandatory to accomplish a plenitude of real-world tasks which usually require feedback control schemes and the application of advanced force/motion control concepts. However, realizing this requires composing the concepts from domains such as geometry, mechanics or control in non-trivial ways which makes predictability of system-level properties related to performance, safety and other important categories difficult to achieve. VeriComp aims at addressing this challenges by augmenting functional composition inside components with verifiable properties and domain-specific extension. Thereby VeriComp shall enable important robot stakeholders such as function developers and component supplierto create verifiable compositions of functions, package those into components while propagating verifiable properties and analyze system-level composition of components with respect to ultimately emerging performance and safety properties.

Project management at the H-BRS

Prof. Dr Nico Hochgeschwender
Teaser Placeholder