Projects

CONVINCE – Context Aware Verifiable Dynamic Deliberation

CONVINCE is a project funded by the European Union Horizon Europe Program (Grant Agreement N. 101070227) of which I was the PI from Bosch Research side. The main contribution of the project is to develop and verify cognitive deliberation capabilities that ensure robust robot operation over extended periods of time without human intervention and integrate these capabilities into a model-driven software toolbox for robot developers. The goal is to advance the state of the art in situation understanding and scene perception, task and motion planning in dynamic environments, design-time and runtime verification, and integrate all these capabilities in an open source software toolbox.

I was mostly involved in bridging the gap between model checking and robotics tooling to achieve our goals regarding design-time verification. I was supervising a PhD and several Master’s thesis students within the project. In addition, I was leading Work Package 5 on the toolbox integration trying to connect the methods and tools developed in the different topic groups of the project. Apart from that, I was very active in the project management and dissemination activities.

Related to the EU-funded project, I was leading a Bosch Research internal project on similar topics for Bosch use cases.

In addition, I am a member of the External Advisory Board of the CoreSense EU Horizon project, the sister project of CONVINCE in the EU Horizon initiative. Read more about it here.

Center for Perspicuous Systems (CPEC)

I was part of the team working in the Center for Perspicuous Systems (CPEC), the collaborative research center 248 Foundations of Perspicuous Software Systems, funded by the DFG during my full PhD studies. In this project researchers from TU Dresden, TU Tübingen, and Saarland Informatics Campus in Saarbrücken collaborate. More precisely, I was involved in the projects C2, C3 and C6.

C2 deals with composition and abstraction with explications, harvesting quantitative behavioral properties related to component suitability, putting in focus how formal and empirical approaches can be integrated towards a comprehensive and reliable understanding of quantitative system properties. We focused on providing explications to identify limitations and to come to new conclusions regarding the influence of uncertainty, configurability, and nondeterminism, addressing interactions in formal and empirical models.

C3 deals with the supervision of dynamic dependable systems, which is relevant because cyber-physical systems are expected to be adaptable in the field without sacrificing dependable operation. This project looks into ways to enable the rapid deployment of new software variants without inducing safety risks. In this context, we addressed challenges related to interactions with the technical environment the system is placed in.

In C6 we tried to achieve advancements in fast, safe, and perspicuous runtime-planning. AI systems choosing actions in dynamic environments need to react to environment behavior in real-time. Neural networks are rapidly gaining traction in tackling this, by learning a policy at design-time, so that at run-time, it suffices to call the policy to obtain the next action to execute. This form of run-time planning is fast, but it comes with severe safety and perspicuity issues. The vision of Project C6 is to address these problems through a range of methods relying on declarative models, or simulators, of the environment. This encompasses policy safeguarding – trying to avoid unsafe situations at runtime, verification and testing of policy behavior, explication of policy decisions, policy-behavior visualization, and policy retraining leveraging information which is provided by all these techniques.

From May 2020 to December 2022 I was the PhD representative on the CPEC Board, where my main task was the conception and organization of measures for the promotion of young scientists. This included mentoring of other PhD students, being a contact person for their needs in the research center, organizing workshops, coachings and social events for PhD students, and more. In addition, I represented the group of PhD students working in CPEC. Board tasks are:

• Staff matters (recruitment etc.)
• Proposals for the election of CPEC committee members
• Proposals for the admission and exclusion of CPEC members
• Decisions on major reallocation requests
• Consultations with the university management / management of the departments or faculties on questions of basic equipment and appointment issues
• Conception and organization of measures for the promotion of young scientists
• All matters that do not fall within the competence of another body or the spokesperson under the Rules of Procedure.

Furthermore, I was involved in the organization of the first DFG review of the project proposal before the research center was granted. I was also heavily involved in the preparations, especially the writing process, for the proposal for the second phase of CPEC as well as in the implementation of the review.