Model Predictive Control
Model Predictive Control (MPC) is an advanced control technique that optimizes control actions over a predicted future time horizon, subject to constraints. Current research emphasizes improving MPC's computational efficiency for real-time applications, particularly in robotics, through parallel computing, accelerated gradient descent, and neural network approximations (e.g., differentiable predictive control, TransformerMPC). This focus stems from MPC's importance in diverse fields, including robotics, battery management, and autonomous driving, where its ability to handle complex systems and safety constraints is crucial.
Papers
Diffusion Model Predictive Control
Guangyao Zhou, Sivaramakrishnan Swaminathan, Rajkumar Vasudeva Raju, J. Swaroop Guntupalli, Wolfgang Lehrach, Joseph Ortiz, Antoine Dedieu, Miguel Lázaro-Gredilla, Kevin Murphy
Safe Learning-Based Optimization of Model Predictive Control: Application to Battery Fast-Charging
Sebastian Hirt, Andreas Höhl, Johannes Pohlodek, Joachim Schaeffer, Maik Pfefferkorn, Richard D. Braatz, Rolf Findeisen
Terrain-Aware Model Predictive Control of Heterogeneous Bipedal and Aerial Robot Coordination for Search and Rescue Tasks
Abdulaziz Shamsah, Jesse Jiang, Ziwon Yoon, Samuel Coogan, Ye Zhao
Learning Koopman Dynamics for Safe Legged Locomotion with Reinforcement Learning-based Controller
Jeonghwan Kim, Yunhai Han, Harish Ravichandar, Sehoon Ha
Differentiable Predictive Control for Robotics: A Data-Driven Predictive Safety Filter Approach
John Viljoen, Wenceslao Shaw Cortez, Jan Drgona, Sebastian East, Masayoshi Tomizuka, Draguna Vrabie
Incremental Few-Shot Adaptation for Non-Prehensile Object Manipulation using Parallelizable Physics Simulators
Fabian Baumeister, Lukas Mack, Joerg Stueckler