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

2024-06-12

arXiv.org

AI Summary

Real-world maze gaming platforms face significant challenges in trajectory planning and robust tracking due to non-convex obstacles, surface irregularities, and model mismatch. To address these issues, this paper proposes a two-layer adaptive nonlinear model predictive control (NMPC) framework. The upper layer performs global path optimization via online map learning, while the lower layer integrates obstacle-adaptive nonlinear constraints and real-time modeling of surface irregularities, enabling rapid receding-horizon optimization under non-convex constraints. The hierarchical architecture ensures both convergence and global optimality while meeting real-time computational requirements. Experimental results on a physical platform demonstrate that the proposed method substantially enhances disturbance rejection and robustness against model mismatch. Compared with baseline controllers—including PID and LQR—it achieves superior tracking accuracy and stability, validating its effectiveness for complex, unstructured environments.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Multiagent Systems: Multiagent Planning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

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.

Problem

• Nonlinear non-convex model predictive control
• Adaptive nonlinear constraints for obstacles
• Two-layer optimization for real-time control

Innovation

• Adaptive nonlinear model predictive control
• Two-layer optimization problem splitting
• Learned labyrinth surface irregularities map