Safe learning-based control via function-based uncertainty quantification
This work addresses safety in learning-based control for real-world systems like robotics, though it is incremental as it builds on existing scenario-based methods.
The paper tackled the problem of uncertainty quantification in learning-based control for safety-critical systems by constructing uncertainty tubes via the scenario approach, which relies solely on sampled realizations without restrictive assumptions, and demonstrated its application by safely tuning control parameters on a real Furuta pendulum.
Uncertainty quantification is essential when deploying learning-based control methods in safety-critical systems. This is commonly realized by constructing uncertainty tubes that enclose the unknown function of interest, e.g., the reward and constraint functions or the underlying dynamics model, with high probability. However, existing approaches for uncertainty quantification typically rely on restrictive assumptions on the unknown function, such as known bounds on functional norms or Lipschitz constants, and struggle with discontinuities. In this paper, we model the unknown function as a random function from which independent and identically distributed realizations can be generated, and construct uncertainty tubes via the scenario approach that hold with high probability and rely solely on the sampled realizations. We integrate these uncertainty tubes into a safe Bayesian optimization algorithm, which we then use to safely tune control parameters on a real Furuta pendulum.