Generalized Benders Decomposition with Continual Learning for Hybrid Model Predictive Control in Dynamic Environment

TL;DR

This paper introduces a hybrid MPC solver that combines Generalized Benders Decomposition with continual learning, significantly speeding up solutions in dynamic environments for robotic control tasks.

Contribution

The novel integration of continual learning with GBD enhances hybrid MPC solving speed in changing environments, enabling real-time robotic control.

Findings

Solver is 2-3 times faster than Gurobi.

Maintains solving speed despite environmental changes.

Effective in controlling a cart-pole with moving contact walls.

Abstract

Hybrid model predictive control (MPC) with both continuous and discrete variables is widely applicable to robotic control tasks, especially those involving contact with the environment. Due to the combinatorial complexity, the solving speed of hybrid MPC can be insufficient for real-time applications. In this paper, we proposed a hybrid MPC solver based on Generalized Benders Decomposition (GBD) with continual learning. The algorithm accumulates cutting planes from the invariant dual space of the subproblems. After a short cold-start phase, the accumulated cuts provide warm-starts for the new problem instances to increase the solving speed. Despite the randomly changing environment that the control is unprepared for, the solving speed maintains. We verified our solver on controlling a cart-pole system with randomly moving soft contact walls and show that the solving speed is 2-3 times faster than the off-the-shelf solver Gurobi.