Abstract We propose Kernel Predictive Control (KPC), a learning-based predictive control
strategy that enjoys deterministic guarantees of safety. Noise-corrupted samples of the …

The accuracy of real-time hybrid simulation (RTHS) is greatly influenced by the inevitable
time delay and amplitude error due to the control plant dynamics. Several tracking …

Data play an essential role in the optimal control of smart buildings' operation, especially in
building energy-management for the target of nearly zero buildings. The building monitoring …

Physically inspired models of the stochastic nature of the human-robot-environment
interaction are generally difficult to derive from first principles, thus alternative data-driven …

Autonomous dynamical systems enter our daily lives and homes. They appear in the form of
self-driving cars, vacuum cleaning robots, and smart manufacturing cobots. Hence, these …

Often, systems need to adapt their behavior to other systems in their surroundings while
obeying constraints to achieve good performance or due to safety reasons. We consider …

There is a steadily increasing demand for full and partial autonomous operation of systems.
One way to achieve autonomy for systems is the fusion of classical control approaches with …

Physically inspired models of the stochastic nature of the human–robot environment
interaction are generally difficult to derive from first principles, thus alternative data-driven …

Data play an essential role in the optimal control of smart buildings' operation, especially in
building energy-management for the target of nearly zero buildings. The building monitoring …

Figure 1. Machine learning can support model predictive control by providing information
about disturbances and references (left), by identifying the system model (middle) or can …