ZipMPC: Compressed Context-Dependent MPC Cost via Imitation LearningShow others and affiliations
2025 (English)Conference paper, Published paper (Refereed)
Abstract [en]
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.
Place, publisher, year, edition, pages
JMIR Publications , 2025. Vol. 305, p. 3115-3136
Series
Proceedings of Machine Learning Research (PMLR), E-ISSN 2640-3498 ; 305
Keywords [en]
Imitation Learning, Model Predictive Control, Context-Dependent Control
National Category
Control Engineering
Identifiers
URN: urn:nbn:se:oru:diva-125501ISI: 001676333500148OAI: oai:DiVA.org:oru-125501DiVA, id: diva2:2019664
Conference
9th Conference on Robot Learning (CoRL 2025), Seoul, Korea, September 27-30, 2025
Funder
Knowledge Foundation, 20190128Wallenberg AI, Autonomous Systems and Software Program (WASP)
Note
This work has been partially supported by the Industrial Graduate School Collaborative AI & Robotics funded by the Swedish Knowledge Foundation Dnr:20190128, and the Knut and Alice Wallenberg Foundation through Wallenberg AI, Autonomous Systems and Software Program (WASP).
2025-12-082025-12-082026-03-10Bibliographically approved