Re4MPC: Reactive Nonlinear MPC for Multi-model Motion Planning via Deep Reinforcement Learning

2025/06/10 by Neşet Ünver Akmandor, Akmandor, Neşet Ünver, Sarvesh Prajapati +5
Engineering · #Advanced Control Systems Optimization #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Robotic Locomotion and Control #Robotic Mechanisms and Dynamics #Robotics (cs.RO) #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2506.08344

openalex publication_date 2025/06/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Traditional motion planning methods for robots with many degrees-of-freedom, such as mobile manipulators, are often computationally prohibitive for real-world settings. In this paper, we propose a novel multi-model motion planning pipeline, termed Re4MPC, which computes trajectories using Nonlinear Model Predictive Control (NMPC). Re4MPC generates trajectories in a computationally efficient manner by reactively selecting the model, cost, and constraints of the NMPC problem depending on the complexity of the task and robot state. The policy for this reactive decision-making is learned via a Deep Reinforcement Learning (DRL) framework. We introduce a mathematical formulation to integrate NMPC into this DRL framework. To validate our methodology and design choices, we evaluate DRL training and test outcomes in a physics-based simulation involving a mobile manipulator. Experimental results demonstrate that Re4MPC is more computationally efficient and achieves higher success rates in reaching end-effector goals than the NMPC baseline, which computes whole-body trajectories without our learning mechanism.

Citations

• Real-time Mixed-Integer Quadratic Programming for Vehicle Decision Making and Motion Planning
• An Architecture for Reactive Mobile Manipulation On-The-Move
• Deep Reinforcement Learning based Robot Navigation in Dynamic Environments using Occupancy Values of Motion Primitives
• Multi-Modal Model Predictive Control through Batch Non-Holonomic Trajectory Optimization: Application to Highway Driving
• A review of mobile robot motion planning methods: from classical motion planning workflows to reinforcement learning-based architectures
• iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks
• A Unified MPC Framework for Whole-Body Dynamic Locomotion and\n Manipulation
• Constraint Handling in Continuous-Time DDP-Based Model Predictive Control
• Motion Planner Augmented Reinforcement Learning for Robot Manipulation in Obstructed Environments
• HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile Manipulators
• Data Efficient Reinforcement Learning for Legged Robots
• A survey of robotic motion planning in dynamic environments
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Proximal Policy Optimization Algorithms
• Relaxed Logarithmic Barrier Function Based Model Predictive Control of\n Linear Systems
• Planning and acting in partially observable stochastic domains

Related

• A nonlinear real time capable motion cueing algorithm based on deep reinforcement learning
• Deep Reinforcement Learning-Based Motion Planning and PDE Control for Flexible Manipulators
• MPC-MPNet: Model-Predictive Motion Planning Networks for Fast, Near-Optimal Planning under Kinodynamic Constraints
• Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environments
• A review of mobile robot motion planning methods: from classical motion planning workflows to reinforcement learning-based architectures