Bridging the Sim-to-real Gap: A Control Framework for Imitation Learning of Model Predictive Control
On the map: Offline RL and imitation learning from data → Imitation learning methods
Abstract (arXiv)
To address the computational challenges of Model Predictive Control (MPC), recent research has studied using imitation learning to approximate MPC with a computationally efficient Deep Neural Network (DNN). However, this introduces a common issue in learning-based control, the simulation-to-reality (sim-to-real) gap. Inspired by Robust Tube MPC, this study proposes a new control framework that addresses this issue from a control perspective. The framework ensures the DNN operates in the same environment as the source domain, addressing the sim-to-real gap with great data collection efficiency. Moreover, an input refinement governor is introduced to address the DNN's inability to adapt to variations in model parameters, enabling the system to satisfy MPC constraints more robustly under parameter-changing conditions. The proposed framework was validated through two case studies: cart-pole control and vehicle collision avoidance control, which analyzed the principles of the proposed framework in detail and demonstrated its application to a vehicle control case.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 18 of its 51 references that are in the map. First posted on arXiv 25 Mar 2025.
Builds on
18 of 51 references.
Closest ancestors · 4
Same direction, newest first
- 2025Imitation Learning of MPC with Neural Networks: Error Guarantees and Sparsification7 Jan
- 2023Efficient Deep Learning of Robust Policies from MPC using Imitation and Tube-Guided Data Augmentation1 Jun
- 2021Demonstration-Efficient Guided Policy Search via Imitation of Robust Tube MPC21 Sep
- 2021Imitation Learning from MPC for Quadrupedal Multi-Gait Control26 Mar
Other references · 14
- 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
- 2018Learning Dexterous In-Hand Manipulationcited by 687
- 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 413
- 2018Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomizationcited by 294
- 2020A Brief Review of Domain Adaptationcited by 288
- 2018Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experiencecited by 217
- 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 176
- 2018Model-Based Reinforcement Learning via Meta-Policy Optimizationcited by 101
- 2018Reinforcement Learning with Perturbed Rewardscited by 79
- 2018Efficient representation and approximation of model predictive control laws via deep learningcited by 58
- 2015Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Searchcited by 42
- 2019TuneNet: One-Shot Residual Tuning for System Identification and Sim-to-Real Robot Task Transfercited by 22
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2022MPC-based Imitation Learning for Safe and Human-like Autonomous Driving
- 2026Stability-Aware Imitation Learning from Model Predictive Control for Autonomous Vehicle Lateral Control: Exact Q-Loss and a Novel Training Procedure
- 2025ZipMPC: Compressed Context-Dependent MPC Cost via Imitation Learning
- 2023Efficient Deep Learning of Robust, Adaptive Policies using Tube MPC-Guided Data Augmentation
- 2023GAN-MPC: Training Model Predictive Controllers with Parameterized Cost Functions using Demonstrations from Non-identical Experts
- 2022Model Predictive Control via On-Policy Imitation Learning
- 2018Safe end-to-end imitation learning for model predictive control
- 2024PlanNetX: Learning an Efficient Neural Network Planner from MPC for Longitudinal Control