collaborators

5 papers

eess.SY2025

Inverse Optimal Control with Constraint Relaxation

Rahel Rickenbach, Amon Lahr, Melanie N. Zeilinger

Inverse optimal control (IOC) is a promising paradigm for learning and mimicking optimal control strategies from capable demonstrators, or gaining a deeper understanding of their i…

eess.SY2025

Finite-Sample-Based Reachability for Safe Control with Gaussian Process Dynamics

Manish Prajapat, Johannes Köhler, Amon Lahr +2

Gaussian Process (GP) regression is shown to be effective for learning unknown dynamics, enabling efficient and safety-aware control strategies across diverse applications. However…

cs.LG2025

Optimal kernel regression bounds under energy-bounded noise

Amon Lahr, Johannes Köhler, Anna Scampicchio +1

Non-conservative uncertainty bounds are key for both assessing an estimation algorithm's accuracy and in view of downstream tasks, such as its deployment in safety-critical context…

eess.SY2025

Gaussian processes for dynamics learning in model predictive control

Anna Scampicchio, Elena Arcari, Amon Lahr +1

Due to its state-of-the-art estimation performance complemented by rigorous and non-conservative uncertainty bounds, Gaussian process regression is a popular tool for enhancing dyn…

math.OC2024

Towards safe and tractable Gaussian process-based MPC: Efficient sampling within a sequential quadratic programming framework

Manish Prajapat, Amon Lahr, Johannes Köhler +2

Learning uncertain dynamics models using Gaussian process~(GP) regression has been demonstrated to enable high-performance and safety-aware control strategies for challenging real-…