Real-Time Nonlinear MPC via Sequential Quadratic Programming with Structure-Exploiting ADMM and Interior-Point Methods for Underactuated Double-Pendulum Swing-Up
2026-08-10 • Robotics
Robotics
AI summaryⓘ
The authors describe a competition where participants must create a control strategy to make a two-part pendulum swing up and stay balanced. Unlike before, the control is tested directly on real hardware accessed online, without knowing the pendulum's exact details ahead of time. The authors present a method using a smart, step-by-step prediction technique called sequential quadratic programming to control the pendulum in real time. Their approach reliably swings up and stabilizes the pendulum, even when there are disturbances. This shows their method can handle unexpected changes while keeping the system balanced.
underactuated systemtwo-link pendulummodel predictive controlnonlinear controlsequential quadratic programmingswing-up controlreal-time controlrobustnessoptimal controldisturbance rejection
Authors
Nick Karydakis, Konstantinos Chatzilygeroudis
Abstract
The 4th "AI Olympics with RealAIGym" competition, to be held at IJCAI-ECAI 2026 in Bremen, challenges participants to develop a global control policy for swinging up and stabilizing an underactuated two-link system in its upright position. In contrast to previous editions, participants develop and evaluate their control strategies directly on remotely accessible CloudPendulum hardware, with limited interaction time and without prior knowledge of the system's model parameters. This paper presents an optimal-control-based approach employing real-time nonlinear model predictive control implemented using sequential quadratic programming. The results demonstrate that the proposed SQP-based MPC controller achieves reliable swing-up and stabilization performance, while maintaining robustness against disturbances.