Adaptive Nonlinear Model Predictive Control for a Real-World Labyrinth Game

We present a nonlinear non-convex model predictive control approach to solving a real-world labyrinth game. We introduce adaptive nonlinear constraints, representing the non-convex obstacles within the labyrinth. Our method splits the computation-heavy optimization problem into two layers; first, a high-level model predictive controller which incorporates the full problem formulation and finds pseudo-global optimal trajectories at a low frequency. Secondly, a low-level model predictive controller that receives a reduced, computationally optimized version of the optimization problem to follow the given high-level path in real-time. Further, a map of the labyrinth surface irregularities is learned. Our controller is able to handle the major disturbances and model inaccuracies encountered on the labyrinth and outperforms other classical control methods.

@article{gaber2025_2406.08650,
  title={ Adaptive Nonlinear Model Predictive Control for a Real-World Labyrinth Game },
  author={ Johannes Gaber and Thomas Bi and Raffaello DÁndrea },
  journal={arXiv preprint arXiv:2406.08650},
  year={ 2025 }
}