What makes hard work feel meaningful, and does meaning emerge?
I want to live in a world in which robots help us live happier, healthier lives.
To get there, we need robot intelligence that we can understand, test and shape according to our needs.
- Building a research organisation for safe physical AI
- Cofounder, AICOR Solutions: a safe physical intelligence platform for industrial and lab automation
- Associate Member, AICOR Institute for Artificial Intelligence, University of Bremen
Writing
all posts →A summary of my invited talk at Safe AI Germany (SAIGE) on safety threats arising from physical AGI, and a tentative research agenda for grounding the discussion in empirical evaluations on real hardware.
A writeup of my one-week bikepacking trip through Northern California.
Introducing KRROOD, an open-source framework that brings native knowledge representation and reasoning capabilities to Python and bridges the gap between symbolic AI and modern software development.
At the 1st Workshop on Embodied AI and Robotics for Future Scientific Discovery (AIR4S) at IROS 2025, my colleagues and I are presenting a robot execution tracing system and virtual lab environment to facilitate reproducible research with robots.
Selected work
all 28 →Shadow Program Inversion with Differentiable Planning: A Framework for Unified Robot Program Parameter and Trajectory Optimization
In 2025 IEEE International Conference on Robotics and Automation (ICRA), May 2025
This paper presents SPI-DP, a novel first-order optimizer capable of optimizing robot programs with respect to both high-level task objectives and motion-level constraints. To that end, we introduce DGPMP2-ND, a differentiable collision-free motion planner for serial N-DoF kinematics, and integrate it into an iterative, gradient-based optimization approach for generic, parameterized robot program representations. SPI-DP allows first-order optimization of planned trajectories and program parameters with respect to objectives such as cycle time or smoothness subject to e.g. collision constraints, while enabling humans to understand, modify or even certify the optimized programs. We provide a comprehensive evaluation on two practical household and industrial applications.
RoboGrind: Intuitive and Interactive Surface Treatment with Industrial Robots
In 2024 IEEE International Conference on Robotics and Automation (ICRA), May 2024
Surface treatment tasks such as grinding, sanding or polishing are a vital step of the value chain in many industries, but are notoriously challenging to automate. We present RoboGrind, an integrated system for the intuitive, interactive automation of surface treatment tasks with industrial robots. It combines a sophisticated 3D perception pipeline for surface scanning and automatic defect identification, an interactive voice-controlled wizard system for the AI-assisted bootstrapping and parameterization of robot programs, and an automatic planning and execution pipeline for force-controlled robotic surface treatment. RoboGrind is evaluated both under laboratory and real-world conditions in the context of refabricating fiberglass wind turbine blades.
Robot Program Parameter Inference via Differentiable Shadow Program Inversion
In 2021 IEEE International Conference on Robotics and Automation (ICRA), May 2021
Challenging manipulation tasks can be solved effectively by combining individual robot skills, which must be parameterized for the concrete physical environment and task at hand. This is time-consuming and difficult for human programmers, particularly for force-controlled skills. To this end, we present Shadow Program Inversion (SPI), a novel approach to infer optimal skill parameters directly from data. SPI leverages unsupervised learning to train an auxiliary differentiable program representation ("shadow program") and realizes parameter inference via gradient-based model inversion. Our method enables the use of efficient first-order optimizers to infer optimal parameters for originally non-differentiable skills, including many skill variants currently used in production. SPI zero-shot generalizes across task objectives, meaning that shadow programs do not need to be retrained to infer parameters for different task variants. We evaluate our methods on three different robots and skill frameworks in industrial and household scenarios. Code and examples are available at https://innolab.artiminds.com/icra2021.