Autonomous robots deployed in unknown search-and-rescue (SaR) environments can significantly improve the efficiency of the mission by assisting in fast localisation and rescue of the trapped victims. We propose a novel integrated hierarchical control architecture, called model predictive fuzzy control (MPFC), for autonomous mission planning of multi-robot SaR systems that should efficiently map an unknown environment: We combine model predictive control (MPC) and fuzzy logic control (FLC), where the robots are locally controlled by computationally efficient FLC controllers, and the parameters of these local controllers are tuned via a centralised MPC controller, in a regular or event-triggered manner. The proposed architecture provides three main advantages: (1) The control decisions are made by the FLC controllers, thus the real-time computation time is affordable. (2) The centralised MPC controller optimises the performance criteria with a global and predictive vision of the system dynamics, and updates the parameters of the FLC controllers accordingly. (3) FLC controllers are heuristic by nature and thus do not take into account optimality in their decisions, while the tuned parameters via the MPC controller can indirectly incorporate some level of optimality in local decisions of the robots. A simulation environment for victim detection in a disaster environment was designed in MATLAB using discrete, 2-D grid-based models. While being comparable from the point of computational efficiency, the integrated MPFC architecture improves the performance of the multi-robot SaR system compared to decentralised FLC controllers. Moreover, the performance of MPFC is comparable to the performance of centralised MPC for path planning of SaR robots, whereas MPFC requires significantly less computational resources, since the number of the optimisation variables in the control problem are reduced.
Quadrupedal robots are increasingly deployed for load-carrying tasks across diverse terrains. While Model Predictive Control (MPC)-based methods can account for payload variations, they often depend on predefined gait schedules or trajectory generators, limiting their adaptability in unstructured environments. To address these limitations, we propose an Adaptive Reinforcement Learning (RL) framework that enables quadrupedal robots to dynamically adapt to both varying payloads and diverse terrains. The framework consists of a nominal policy responsible for baseline locomotion and an adaptive policy that learns corrective actions to preserve stability and improve command tracking under payload variations. We validate the proposed approach through large-scale simulation experiments in Isaac Gym and real-world hardware deployment on a Unitree Go1 quadruped. The controller was tested on flat ground, slopes, and stairs under both static and dynamic payload changes. Across all settings, our adaptive controller consistently outperformed the controller in tracking body height and velocity commands, demonstrating enhanced robustness and adaptability without requiring explicit gait design or manual tuning.
This paper proposes an integrated approach for the safe and efficient control of mobile robots in dynamic and uncertain environments. The approach consists of two key steps: one-shot multimodal motion prediction to anticipate motions of dynamic obstacles and model predictive control to incorporate these predictions into the motion planning process. Motion prediction is driven by an energy-based neural network that generates high-resolution, multi-step predictions in a single operation. The prediction outcomes are further utilized to create geometric shapes formulated as mathematical constraints. Instead of treating each dynamic obstacle individually, predicted obstacles are grouped by proximity in an unsupervised way to improve performance and efficiency. The overall collision-free navigation is handled by model predictive control with a specific design for proactive dynamic obstacle avoidance. The proposed approach allows mobile robots to navigate effectively in dynamic environments. Its performance is accessed across various scenarios that represent typical warehouse settings. The results demonstrate that the proposed approach outperforms other existing dynamic obstacle avoidance methods.
This paper tackles the challenge of learning multi-goal dexterous hand manipulation tasks using model-based Reinforcement Learning. We propose Goal-Conditioned Probabilistic Model Predictive Control (GC-PMPC) by designing probabilistic neural network ensembles to describe the high-dimensional dexterous hand dynamics and introducing an asynchronous MPC policy to meet the control frequency requirements in real-world dexterous hand systems. Extensive evaluations on four simulated Shadow Hand manipulation scenarios with randomly generated goals demonstrate GC-PMPC's superior performance over state-of-the-art baselines. It successfully drives a cable-driven Dexterous hand, DexHand 021 with 12 Active DOFs and 5 tactile sensors, to learn manipulating a cubic die to three goal poses within approximately 80 minutes of interactions, demonstrating exceptional learning efficiency and control performance on a cost-effective dexterous hand platform.
Reinforcement Learning (RL) and Machine Learning Integrated Model Predictive Control (ML-MPC) are promising approaches for optimizing hydrogen-diesel dual-fuel engine control, as they can effectively control multiple-input multiple-output systems and nonlinear processes. ML-MPC is advantageous for providing safe and optimal controls, ensuring the engine operates within predefined safety limits. In contrast, RL is distinguished by its adaptability to changing conditions through its learning-based approach. However, the practical implementation of either method alone poses challenges. RL requires high variance in control inputs during early learning phases, which can pose risks to the system by potentially executing unsafe actions, leading to mechanical damage. Conversely, ML-MPC relies on an accurate system model to generate optimal control inputs and has limited adaptability to system drifts, such as injector aging, which naturally occur in engine applications. To address these limitations, this study proposes a hybrid RL and ML-MPC approach that uses an ML-MPC framework while incorporating an RL agent to dynamically adjust the ML-MPC load tracking reference in response to changes in the environment. At the same time, the ML-MPC ensures that actions stay safe throughout the RL agent's exploration. To evaluate the effectiveness of this approach, fuel pressure is deliberately varied to introduce a model-plant mismatch between the ML-MPC and the engine test bench. The result of this mismatch is a root mean square error (RMSE) in indicated mean effective pressure of 0.57 bar when running the ML-MPC. The experimental results demonstrate that RL successfully adapts to changing boundary conditions by altering the tracking reference while ML-MPC ensures safe control inputs. The quantitative improvement in load tracking by implementing RL is an RSME of 0.44 bar.
Sampling-based model predictive control (MPC) offers strong performance in nonlinear and contact-rich robotic tasks, yet often suffers from poor exploration due to locally greedy sampling schemes. We propose \emph{Model Tensor Planning} (MTP), a novel sampling-based MPC framework that introduces high-entropy control trajectory generation through structured tensor sampling. By sampling over randomized multipartite graphs and interpolating control trajectories with B-splines and Akima splines, MTP ensures smooth and globally diverse control candidates. We further propose a simple $\beta$-mixing strategy that blends local exploitative and global exploratory samples within the modified Cross-Entropy Method (CEM) update, balancing control refinement and exploration. Theoretically, we show that MTP achieves asymptotic path coverage and maximum entropy in the control trajectory space in the limit of infinite tensor depth and width. Our implementation is fully vectorized using JAX and compatible with MuJoCo XLA, supporting \emph{Just-in-time} (JIT) compilation and batched rollouts for real-time control with online domain randomization. Through experiments on various challenging robotic tasks, ranging from dexterous in-hand manipulation to humanoid locomotion, we demonstrate that MTP outperforms standard MPC and evolutionary strategy baselines in task success and control robustness. Design and sensitivity ablations confirm the effectiveness of MTP tensor sampling structure, spline interpolation choices, and mixing strategy. Altogether, MTP offers a scalable framework for robust exploration in model-based planning and control.
In this paper, we propose a data-driven Evolutionary Game-Based Model Predictive Control (EG-MPC) framework for the energy dispatch of a hybrid renewable energy system powering an autonomous ship. The system integrates solar photovoltaic and wind turbine generation with battery energy storage and diesel backup power to ensure reliable operation. Given the uncertainties in renewable generation and dynamic energy demands, an optimal dispatch strategy is crucial to minimize operational costs while maintaining system reliability. To address these challenges, we formulate a cost minimization problem that considers both battery degradation costs and diesel fuel expenses, leveraging real-world data to enhance modeling accuracy. The EG-MPC approach integrates evolutionary game dynamics within a receding-horizon optimization framework, enabling adaptive and near-optimal control solutions in real time. Simulation results based on site-specific data demonstrate that the proposed method achieves cost-effective, reliable, and adaptive energy dispatch, outperforming conventional rule-based and standard MPC approaches, particularly under uncertainty.
Imitation learning is a widely used approach for training agents to replicate expert behavior in complex decision-making tasks. However, existing methods often struggle with compounding errors and limited generalization, due to the inherent challenge of error correction and the distribution shift between training and deployment. In this paper, we present a novel model-based imitation learning framework inspired by model predictive control, which addresses these limitations by integrating predictive modeling through multi-step state predictions. Our method outperforms traditional behavior cloning numerical benchmarks, demonstrating superior robustness to distribution shift and measurement noise both in available data and during execution. Furthermore, we provide theoretical guarantees on the sample complexity and error bounds of our method, offering insights into its convergence properties.
The ability to update a path plan is a required capability for autonomous mobile robots navigating through uncertain environments. This paper proposes a re-planning strategy using a multilayer planning and control framework for cases where the robot's environment is partially known. A medial axis graph-based planner defines a global path plan based on known obstacles where each edge in the graph corresponds to a unique corridor. A mixed-integer model predictive control (MPC) method detects if a terminal constraint derived from the global plan is infeasible, subject to a non-convex description of the local environment. Infeasibility detection is used to trigger efficient global re-planning via medial axis graph edge deletion. The proposed re-planning strategy is demonstrated experimentally.
This paper investigates the application of a Model Predictive Controller (MPC) for the cruise control system of a quadrotor, focusing on hovering point stabilization and reference tracking. Initially, a full-state-feedback MPC is designed for the ideal scenario. To account for real-world conditions, a constant disturbance is introduced to the quadrotor, simulating a gust of wind in a specific direction. In response, an output-feedback offset-free MPC is developed to stabilize the quadrotor while rejecting the disturbance. We validate the design of the controller by conducting stability analysis, as well as numerical simulations under different circumstances. It is shown that the designed controller can achieve all the expected goals for the cruise control, including reference tracking and disturbance rejection. This project was implemented using Python and the CVXPY library for convex optimization.
Today's control systems are often characterized by modularity and safety requirements to handle complexity, resulting in hierarchical control structures. Although hierarchical model predictive control offers favorable properties, achieving a provably safe, yet modular design remains a challenge. This paper introduces a contract-based hierarchical control strategy to improve the performance of control systems facing challenges related to model inconsistency and independent controller design across hierarchies. We consider a setup where a higher-level controller generates references that affect the constraints of a lower-level controller, which is based on a soft-constrained MPC formulation. The optimal slack variables serve as the basis for a contract that allows the higher-level controller to assess the feasibility of the reference trajectory without exact knowledge of the model, constraints, and cost of the lower-level controller. To ensure computational efficiency while maintaining model confidentiality, we propose using an explicit function approximation, such as a neural network, to represent the cost of optimal slack values. The approach is tested for a hierarchical control setup consisting of a planner and a motion controller as commonly found in autonomous driving.
Training Neural Networks (NNs) to behave as Model Predictive Control (MPC) algorithms is an effective way to implement them in constrained embedded devices. By collecting large amounts of input-output data, where inputs represent system states and outputs are MPC-generated control actions, NNs can be trained to replicate MPC behavior at a fraction of the computational cost. However, although the composition of the training data critically influences the final NN accuracy, methods for systematically optimizing it remain underexplored. In this paper, we introduce the concept of Optimally-Sampled Datasets (OSDs) as ideal training sets and present an efficient algorithm for generating them. An OSD is a parametrized subset of all the available data that (i) preserves existing MPC information up to a certain numerical resolution, (ii) avoids duplicate or near-duplicate states, and (iii) becomes saturated or complete. We demonstrate the effectiveness of OSDs by training NNs to replicate the University of Virginia's MPC algorithm for automated insulin delivery in Type-1 Diabetes, achieving a four-fold improvement in final accuracy. Notably, two OSD-trained NNs received regulatory clearance for clinical testing as the first NN-based control algorithm for direct human insulin dosing. This methodology opens new pathways for implementing advanced optimizations on resource-constrained embedded platforms, potentially revolutionizing how complex algorithms are deployed.
This paper presents a robust adaptive learning Model Predictive Control (MPC) framework for linear systems with parametric uncertainties and additive disturbances performing iterative tasks. The approach iteratively refines the parameter estimates using set membership estimation. Performance enhancement over iterations is achieved by learning the terminal cost from data. Safety is enforced using a terminal set, which is also learned iteratively. The proposed method guarantees recursive feasibility, constraint satisfaction, and a robust bound on the closed-loop cost. Numerical simulations on a mass-spring-damper system demonstrate improved computational efficiency and control performance compared to an existing robust adaptive MPC approach.
In this paper, we design offset-free nonlinear Model Predictive Control (MPC) for surrogate models based on Extended Dynamic Mode Decomposition (EDMD). The model used for prediction in MPC is augmented with a disturbance term, that is estimated by an observer. If the full information about the equilibrium of the real system is not available, a reference calculator is introduced in the algorithm to compute the MPC state and input references. The control algorithm guarantees offset-free tracking of the controlled output under the assumption that the modeling errors are asymptotically constant. The effectiveness of the proposed approach is showcased with numerical simulations for two popular benchmark systems: the van-der-Pol oscillator and the four-tanks process.
Aquifer thermal energy storages (ATES) represent groundwater saturated aquifers that store thermal energy in the form of heated or cooled groundwater. Combining two ATES, one can harness excess thermal energy from summer (heat) and winter (cold) to support the building's heating, ventilation, and air conditioning (HVAC) technology. In general, a dynamic operation of ATES throughout the year is beneficial to avoid using fossil fuel-based HVAC technology and maximize the ``green use'' of ATES. Model predictive control (MPC) with an appropriate system model may become a crucial control approach for ATES systems. Consequently, the MPC model should reflect spatial temperature profiles around ATES' boreholes to predict extracted groundwater temperatures accurately. However, meaningful predictions require the estimation of the current state of the system, as measurements are usually only at the borehole of the ATES. In control, this is often realized by model-based observers. Still, observing the state of an ATES system is non-trivial, since the model is typically hybrid. We show how to exploit the specific structure of the hybrid ATES model and design an easy-to-solve moving horizon estimator based on a quadratic program.
This paper introduces a novel method for robust output-feedback model predictive control (MPC) for a class of nonlinear discrete-time systems. We propose a novel interval-valued predictor which, given an initial estimate of the state, produces intervals which are guaranteed to contain the future trajectory of the system. By parameterizing the control input with an initial stabilizing feedback term, we are able to reduce the width of the predicted state intervals compared to existing methods. We demonstrate this through a numerical comparison where we show that our controller performs better in the presence of large amounts of noise. Finally, we present a simulation study of a robot navigation scenario, where we incorporate a time-varying entropy term into the cost function in order to autonomously explore an uncertain area.
Aerial transportation using quadrotors with cable-suspended payloads holds great potential for applications in disaster response, logistics, and infrastructure maintenance. However, their hybrid and underactuated dynamics pose significant control and perception challenges. Traditional approaches often assume a taut cable condition, limiting their effectiveness in real-world applications where slack-to-taut transitions occur due to disturbances. We introduce ES-HPC-MPC, a model predictive control framework that enforces exponential stability and perception-constrained control under hybrid dynamics. Our method leverages Exponentially Stabilizing Control Lyapunov Functions (ES-CLFs) to enforce stability during the tasks and Control Barrier Functions (CBFs) to maintain the payload within the onboard camera's field of view (FoV). We validate our method through both simulation and real-world experiments, demonstrating stable trajectory tracking and reliable payload perception. We validate that our method maintains stability and satisfies perception constraints while tracking dynamically infeasible trajectories and when the system is subjected to hybrid mode transitions caused by unexpected disturbances.
In the realm of control systems, model predictive control (MPC) has exhibited remarkable potential; however, its reliance on accurate models and substantial computational resources has hindered its broader application, especially within real-time nonlinear systems. This study presents an innovative control framework to enhance the practical viability of the MPC. The developed safe data-driven predictive control aims to eliminate the requirement for precise models and alleviate computational burdens in the nonlinear MPC (NMPC). This is achieved by learning both the system dynamics and the control policy, enabling efficient data-driven predictive control while ensuring system safety. The methodology involves a spatial temporal filter (STF)-based concurrent learning for system identification, a robust control barrier function (RCBF) to ensure the system safety amid model uncertainties, and a RCBF-based NMPC policy approximation. An online policy correction mechanism is also introduced to counteract performance degradation caused by the existing model uncertainties. Demonstrated through simulations on two applications, the proposed approach offers comparable performance to existing benchmarks with significantly reduced computational costs.
Shipboard carbon capture is a promising solution to help reduce carbon emissions in international shipping. In this work, we propose a data-driven dynamic modeling and economic predictive control approach within the Koopman framework. This integrated modeling and control approach is used to achieve safe and energy-efficient process operation of shipboard post-combustion carbon capture plants. Specifically, we propose a deep neural Koopman operator modeling approach, based on which a Koopman model with time-varying model parameters is established. This Koopman model predicts the overall economic operational cost and key system outputs, based on accessible partial state measurements. By leveraging this learned model, a constrained economic predictive control scheme is developed. Despite time-varying parameters involved in the formulated model, the formulated optimization problem associated with the economic predictive control design is convex, and it can be solved efficiently during online control implementations. Extensive tests are conducted on a high-fidelity simulation environment for shipboard post-combustion carbon capture processes. Four ship operational conditions are taken into account. The results show that the proposed method significantly improves the overall economic operational performance and carbon capture rate. Additionally, the proposed method guarantees safe operation by ensuring that hard constraints on the system outputs are satisfied.
The transition to renewable energy is driving the rise of distributed multi-energy systems, in which individual energy hubs and prosumers (e.g., homes, industrial campuses) generate, store, and trade energy. Economic Model Predictive Control (MPC) schemes are widely used to optimize operation of energy hubs by efficiently dispatching resources and minimizing costs while ensuring operational constraints are met. Peer-to-peer (P2P) energy trading among hubs enhances network efficiency and reduces costs but also increases computational and privacy challenges, especially as the network scales. Additionally, current distributed control techniques require global recomputation whenever the network topology changes, limiting scalability. To address these challenges, we propose a clustering-based P2P trading framework that enables plug-and-play operation, allowing energy hubs to seamlessly join or leave without requiring network-wide controller updates. The impact is restricted to the hubs within the affected cluster. The energy trading problem is formulated as a bi-level bargaining game, where inter-cluster trading commitments are determined at the cluster level, while energy dispatch and cost-sharing among hubs within a cluster are refined at the hub level. Both levels are solved in a distributed manner using ADMM, ensuring computational feasibility and privacy preservation. Moreover, we develop plug-and-play procedures to handle dynamic topology changes at both the hub and cluster levels, minimizing disruptions across the network. Simulation results demonstrate that the proposed bi-level framework reduces operational costs, and enables scalable energy management under plug-and-play operation.