ZipMPC: Compressed Context-Dependent MPC Cost via Imitation Learning

TL;DR

ZipMPC learns a compressed, context-dependent cost function to enable short-horizon MPC to imitate long-horizon control, improving performance and generalization in real-time systems like autonomous racing.

Contribution

It introduces ZipMPC, a novel imitation learning approach that compresses long-horizon MPC behavior into a short-horizon, context-dependent cost function using differentiable MPC and neural networks.

Findings

ZipMPC outperforms alternative methods in optimizing long-term objectives.

It maintains computational costs comparable to short-horizon MPC.

It generalizes control behavior to unseen environments.

Abstract

The computational burden of model predictive control (MPC) limits its application on real-time systems, such as robots, and often requires the use of short prediction horizons. This not only affects the control performance, but also increases the difficulty of designing MPC cost functions that reflect the desired long-term objective. This paper proposes ZipMPC, a method that imitates a long-horizon MPC behaviour by learning a compressed and context-dependent cost function for a short-horizon MPC. It improves performance over alternative methods, such as approximate explicit MPC and automatic cost parameter tuning, in particular in terms of i) optimizing the long term objective; ii) maintaining computational costs comparable to a short-horizon MPC; iii) ensuring constraint satisfaction; and iv) generalizing control behaviour to environments not observed during training. For this purpose, ZipMPC leverages the concept of differentiable MPC with neural networks to propagate gradients of the imitation loss through the MPC optimization. We validate our proposed method in simulation and real-world experiments on autonomous racing. ZipMPC consistently completes laps faster than selected baselines, achieving lap times close to the long-horizon MPC baseline. In challenging scenarios where the short-horizon MPC baseline fails to complete a lap, ZipMPC is able to do so. In particular, these performance gains are also observed on tracks unseen during training.