Computational efficiency and robustness are essential in process modeling, optimization, and control for real-world engineering applications. While neural network-based approaches have gained significant attention in recent years, conventional neural networks often fail to address these two critical aspects simultaneously or even independently. Inspired by natural physical systems and established literature, input convex architectures are known to enhance computational efficiency in optimization tasks, whereas Lipschitz-constrained architectures improve robustness. However, combining these properties within a single model requires careful review, as inappropriate methods for enforcing one property can undermine the other. To overcome this, we introduce a novel network architecture, termed Input Convex Lipschitz Recurrent Neural Networks (ICLRNNs). This architecture seamlessly integrates the benefits of convexity and Lipschitz continuity, enabling fast and robust neural network-based modeling and optimization. The ICLRNN outperforms existing recurrent units in both computational efficiency and robustness. Additionally, it has been successfully applied to practical engineering scenarios, such as modeling and control of chemical process and the modeling and real-world solar irradiance prediction for solar PV system planning at LHT Holdings in Singapore. Source code is available at https://github.com/killingbear999/ICLRNN.
This paper presents a new approach to predict the occupancy for building energy systems (BES). A Gaussian Process (GP) is used to model the occupancy and is represented as a state space model that is equivalent to the full GP if Kalman filtering and smoothing is used. The combination of GPs and mechanistic models is called Latent Force Model (LFM). An LFM-based model predictive control (MPC) concept for BES is presented that benefits from the extrapolation capability of mechanistic models and the learning ability of GPs to predict the occupancy within the building. Simulations with EnergyPlus and a comparison with real-world data from the Bosch Research Campus in Renningen show that a reduced energy demand and thermal discomfort can be obtained with the LFM-based MPC scheme by accounting for the predicted stochastic occupancy.
Model Predictive Control (MPC) is a powerful method for complex system regulation, but its reliance on an accurate model poses many limitations in real-world applications. Data-driven predictive control (DDPC) aims at overcoming this limitation, by relying on historical data to provide information on the plant to be controlled. In this work, we present a unified stochastic framework for direct DDPC, where control actions are obtained by optimizing the Final Control Error (FCE), which is directly computed from available data only and automatically weighs the impact of uncertainty on the control objective. Our framework allows us to establish a separation principle for Predictive Control, elucidating the role that predictive models and their uncertainty play in DDPC. Moreover, it generalizes existing DDPC methods, like regularized Data-enabled Predictive Control (DeePC) and $\gamma$-DDPC, providing a path toward noise-tolerant data-based control with rigorous optimality guarantees. The theoretical investigation is complemented by a series of experiments (code available on GitHub: https://github.com/marcofabris92/a-separation-principle-in-d3pc), revealing that the proposed method consistently outperforms or, at worst, matches existing techniques without requiring tuning regularization parameters as other methods do.
We propose an adaptive model-predictive controller that balances driving the system to a goal state and seeking system observations that are informative with respect to the parameters of a nonlinear autoregressive exogenous model. The controller's objective function is derived from an expected free energy functional and contains information-theoretic terms expressing uncertainty over model parameters and output predictions. Experiments illustrate how parameter uncertainty affects the control objective and evaluate the proposed controller for a pendulum swing-up task.
Safety guarantees are vital in many control applications, such as robotics. Model predictive control (MPC) provides a constructive framework for controlling safety-critical systems, but is limited by its computational complexity. We address this problem by presenting a novel algorithm that automatically computes an explicit approximation to nonlinear MPC schemes while retaining closed-loop guarantees. Specifically, the problem can be reduced to a function approximation problem, which we then tackle by proposing ALKIA-X, the Adaptive and Localized Kernel Interpolation Algorithm with eXtrapolated reproducing kernel Hilbert space norm. ALKIA-X is a non-iterative algorithm that ensures numerically well-conditioned computations, a fast-to-evaluate approximating function, and the guaranteed satisfaction of any desired bound on the approximation error. Hence, ALKIA-X automatically computes an explicit function that approximates the MPC, yielding a controller suitable for safety-critical systems and high sampling rates. We apply ALKIA-X to approximate two nonlinear MPC schemes, demonstrating reduced computational demand and applicability to realistic problems.
In this paper, we introduce a new class of parameterized controllers, drawing inspiration from Model Predictive Control (MPC). The controller resembles a Quadratic Programming (QP) solver of a linear MPC problem, with the parameters of the controller being trained via Deep Reinforcement Learning (DRL) rather than derived from system models. This approach addresses the limitations of common controllers with Multi-Layer Perceptron (MLP) or other general neural network architecture used in DRL, in terms of verifiability and performance guarantees, and the learned controllers possess verifiable properties like persistent feasibility and asymptotic stability akin to MPC. On the other hand, numerical examples illustrate that the proposed controller empirically matches MPC and MLP controllers in terms of control performance and has superior robustness against modeling uncertainty and noises. Furthermore, the proposed controller is significantly more computationally efficient compared to MPC and requires fewer parameters to learn than MLP controllers. Real-world experiments on vehicle drift maneuvering task demonstrate the potential of these controllers for robotics and other demanding control tasks.
This paper presents a novel approach to multi-agent reinforcement learning (RL) for linear systems with convex polytopic constraints. Existing work on RL has demonstrated the use of model predictive control (MPC) as a function approximator for the policy and value functions. The current paper is the first work to extend this idea to the multi-agent setting. We propose the use of a distributed MPC scheme as a function approximator, with a structure allowing for distributed learning and deployment. We then show that Q-learning updates can be performed distributively without introducing nonstationarity, by reconstructing a centralized learning update. The effectiveness of the approach is demonstrated on two numerical examples.
We propose an integrated behavior and motion planning framework for the lane-merging problem. The behavior planner combines search-based planning with game theory to model vehicle interactions and plan multi-vehicle trajectories. Inspired by human drivers, we model the lane-merging problem as a gap selection process and determine the appropriate gap by solving a matrix game. Moreover, we introduce a branch model predictive control (BMPC) framework to account for the uncertain equilibrium strategies adopted by the surrounding vehicles, including Nash and Stackelberg strategies. A tailored numerical solver is developed to enhance computational efficiency by exploiting the tree structure inherent in BMPC. Finally, we validate our proposed integrated planner using real traffic data and demonstrate its effectiveness in handling interactions in dense traffic scenarios. The code is publicly available at: https://github.com/SailorBrandon/GT-BMPC.
In the backdrop of an increasingly pressing need for effective urban and highway transportation systems, this work explores the synergy between model-based and learning-based strategies to enhance traffic flow management by use of an innovative approach to the problem of ramp metering control that embeds Reinforcement Learning (RL) techniques within the Model Predictive Control (MPC) framework. The control problem is formulated as an RL task by crafting a suitable stage cost function that is representative of the traffic conditions, variability in the control action, and violations of the constraint on the maximum number of vehicles in queue. An MPC-based RL approach, which leverages the MPC optimal problem as a function approximation for the RL algorithm, is proposed to learn to efficiently control an on-ramp and satisfy its constraints despite uncertainties in the system model and variable demands. Simulations are performed on a benchmark small-scale highway network to compare the proposed methodology against other state-of-the-art control approaches. Results show that, starting from an MPC controller that has an imprecise model and is poorly tuned, the proposed methodology is able to effectively learn to improve the control policy such that congestion in the network is reduced and constraints are satisfied, yielding an improved performance that is superior to the other controllers.
Neural network-based optimization and control methods, often referred to as black-box approaches, are increasingly gaining attention in energy and manufacturing systems, particularly in situations where first-principles models are either unavailable or inaccurate. However, their non-convex nature significantly slows down the optimization and control processes, limiting their application in real-time decision-making processes. To address this challenge, we propose a novel Input Convex Long Short-Term Memory (IC-LSTM) network to enhance the computational efficiency of neural network-based optimization. Through two case studies employing real-time neural network-based optimization for optimizing energy and chemical systems, we demonstrate the superior performance of IC-LSTM-based optimization in terms of runtime. Specifically, in a real-time optimization problem of a real-world solar photovoltaic energy system at LHT Holdings in Singapore, IC-LSTM-based optimization achieved at least 4-fold speedup compared to conventional LSTM-based optimization. These results highlight the potential of IC-LSTM networks to significantly enhance the efficiency of neural network-based optimization and control in practical applications. Source code is available at https://github.com/killingbear999/ICLSTM.
This article presents a new optimal control-based interactive motion planning algorithm for an autonomous vehicle interacting with a human-driven vehicle. The ego vehicle solves a joint optimization problem for its motion planning involving costs and coupled constraints of both vehicles and applies its own actions. The non-convex feasible region and lane discipline are handled by introducing integer decision variables and the resulting optimization problem is a mixed-integer quadratic program (MIQP) which is implemented via model predictive control (MPC). Furthermore, the ego vehicle imputes the cost of human-driven neighboring vehicle (NV) using an inverse optimal control method based on Karush-Kuhn-Tucker (KKT) conditions and adapts the joint optimization cost accordingly. We call the algorithm adaptive interactive mixed-integer MPC (aiMPC). Its interaction with human subjects driving the NV in a mandatory lane change scenario is tested in a developed software-and-human-in-the-loop simulator. Results show the effectiveness of the presented algorithm in terms of enhanced mobility of both the vehicles compared to baseline methods.
Model predictive control (MPC) may provide local motion planning for mobile robotic platforms. The challenging aspect is the analytic representation of collision cost for the case when both the obstacle map and robot footprint are arbitrary. We propose a Neural Potential Field: a neural network model that returns a differentiable collision cost based on robot pose, obstacle map, and robot footprint. The differentiability of our model allows its usage within the MPC solver. It is computationally hard to solve problems with a very high number of parameters. Therefore, our architecture includes neural image encoders, which transform obstacle maps and robot footprints into embeddings, which reduce problem dimensionality by two orders of magnitude. The reference data for network training are generated based on algorithmic calculation of a signed distance function. Comparative experiments showed that the proposed approach is comparable with existing local planners: it provides trajectories with outperforming smoothness, comparable path length, and safe distance from obstacles. Experiment on Husky UGV mobile robot showed that our approach allows real-time and safe local planning. The code for our approach is presented at https://github.com/cog-isa/NPField together with demo video.
Traditional methods plan feasible paths for multiple agents in the stochastic environment. However, the methods' iterations with the changes in the environment result in computation complexities, especially for the decentralized agents without a centralized planner. Although reinforcement learning provides a plausible solution because of the generalization for different environments, it struggles with enormous agent-environment interactions in training. Here, we propose a novel centralized training with decentralized execution method based on multi-agent reinforcement learning, which is improved based on the idea of model predictive control. In our approach, agents communicate only with the centralized planner to make decentralized decisions online in the stochastic environment. Furthermore, considering the communication constraint with the centralized planner, each agent plans feasible paths through the extended observation, which combines information on neighboring agents based on the distance-weighted mean field approach. Inspired by the rolling optimization approach of model predictive control, we conduct multi-step value convergence in multi-agent reinforcement learning to enhance the training efficiency, which reduces the expensive interactions in convergence. Experiment results in both comparison, ablation, and real-robot studies validate the effectiveness and generalization performance of our method.
Reinforcement learning suffers from limitations in real practices primarily due to the number of required interactions with virtual environments. It results in a challenging problem because we are implausible to obtain a local optimal strategy with only a few attempts for many learning methods. Hereby, we design an improved reinforcement learning method based on model predictive control that models the environment through a data-driven approach. Based on the learned environment model, it performs multi-step prediction to estimate the value function and optimize the policy. The method demonstrates higher learning efficiency, faster convergent speed of strategies tending to the local optimal value, and less sample capacity space required by experience replay buffers. Experimental results, both in classic databases and in a dynamic obstacle avoidance scenario for an unmanned aerial vehicle, validate the proposed approaches.
This paper introduces zonoLAB, a MATLAB-based toolbox for set-based control system analysis using the hybrid zonotope set representation. Hybrid zonotopes have proven to be an expressive set representation that can exactly represent the reachable sets of mixed-logical dynamical systems and tightly approximate the reachable sets of nonlinear dynamic systems. Moreover, hybrid zonotopes can exactly represent the continuous piecewise linear control laws associated with model predictive control and the input-output mappings of neural networks with piecewise linear activation functions. The hybrid zonotope set representation is also highly exploitable, where efficient methods developed for mixed-integer linear programming can be directly used for set operation and analysis. The zonoLAB toolbox is designed to make these capabilities accessible to the dynamic systems and controls community, with functionality spanning fundamental operations with hybrid zonotope, constrained zonotope, and zonotope set representations, powerful set analysis tools, and general-purpose algorithms for reachability analysis of open- and closed-loop systems.
Active components, such as actuators, constitute a fundamental aspect of engineering systems, affording the freedom to shape system behavior as desired. However, this capability necessitates energy consumption, primarily in the form of electricity. Thus, a trade-off emerges between energy usage and desired outcomes. While open-loop optimal control methods strive for efficiency, practical implementation is hampered by disturbances and model discrepancies, underscoring the need for closed-loop controllers. The Proportional- Integral-Derivative (PID) controller is widely favored in industry due to its simplicity, despite sub-optimal responses in many cases. To bridge this gap, Model Predictive Control (MPC) offers a solution, yet its complexity limits its broad applicability. This paper introduces user-friendly Python-based MPC software, enabling easy access to MPC. The effectiveness of this software is demonstrated through multiple examples, including those with a known analytical solution.
Precise arbitrary trajectory tracking for quadrotors is challenging due to unknown nonlinear dynamics, trajectory infeasibility, and actuation limits. To tackle these challenges, we present Deep Adaptive Trajectory Tracking (DATT), a learning-based approach that can precisely track arbitrary, potentially infeasible trajectories in the presence of large disturbances in the real world. DATT builds on a novel feedforward-feedback-adaptive control structure trained in simulation using reinforcement learning. When deployed on real hardware, DATT is augmented with a disturbance estimator using L1 adaptive control in closed-loop, without any fine-tuning. DATT significantly outperforms competitive adaptive nonlinear and model predictive controllers for both feasible smooth and infeasible trajectories in unsteady wind fields, including challenging scenarios where baselines completely fail. Moreover, DATT can efficiently run online with an inference time less than 3.2 ms, less than 1/4 of the adaptive nonlinear model predictive control baseline
Model Predictive Control (MPC) provides an optimal control solution based on a cost function while allowing for the implementation of process constraints. As a model-based optimal control technique, the performance of MPC strongly depends on the model used where a trade-off between model computation time and prediction performance exists. One solution is the integration of MPC with a machine learning (ML) based process model which are quick to evaluate online. This work presents the experimental implementation of a deep neural network (DNN) based nonlinear MPC for Homogeneous Charge Compression Ignition (HCCI) combustion control. The DNN model consists of a Long Short-Term Memory (LSTM) network surrounded by fully connected layers which was trained using experimental engine data and showed acceptable prediction performance with under 5% error for all outputs. Using this model, the MPC is designed to track the Indicated Mean Effective Pressure (IMEP) and combustion phasing trajectories, while minimizing several parameters. Using the acados software package to enable the real-time implementation of the MPC on an ARM Cortex A72, the optimization calculations are completed within 1.4 ms. The external A72 processor is integrated with the prototyping engine controller using a UDP connection allowing for rapid experimental deployment of the NMPC. The IMEP trajectory following of the developed controller was excellent, with a root-mean-square error of 0.133 bar, in addition to observing process constraints.
A major challenge in robotics is to design robust policies which enable complex and agile behaviors in the real world. On one end of the spectrum, we have model-free reinforcement learning (MFRL), which is incredibly flexible and general but often results in brittle policies. In contrast, model predictive control (MPC) continually re-plans at each time step to remain robust to perturbations and model inaccuracies. However, despite its real-world successes, MPC often under-performs the optimal strategy. This is due to model quality, myopic behavior from short planning horizons, and approximations due to computational constraints. And even with a perfect model and enough compute, MPC can get stuck in bad local optima, depending heavily on the quality of the optimization algorithm. To this end, we propose Deep Model Predictive Optimization (DMPO), which learns the inner-loop of an MPC optimization algorithm directly via experience, specifically tailored to the needs of the control problem. We evaluate DMPO on a real quadrotor agile trajectory tracking task, on which it improves performance over a baseline MPC algorithm for a given computational budget. It can outperform the best MPC algorithm by up to 27% with fewer samples and an end-to-end policy trained with MFRL by 19%. Moreover, because DMPO requires fewer samples, it can also achieve these benefits with 4.3X less memory. When we subject the quadrotor to turbulent wind fields with an attached drag plate, DMPO can adapt zero-shot while still outperforming all baselines. Additional results can be found at https://tinyurl.com/mr2ywmnw.
Grid-interfacing inverters act as the interface between renewable resources and the electric grid, and have the potential to offer fast and programmable controls compared to synchronous generators. With this flexibility there has been significant research efforts into determining the best way to control these inverters. Inverters are limited in their maximum current output in order to protect semiconductor devices, presenting a nonlinear constraint that needs to be accounted for in their control algorithms. Existing approaches either simply saturate a controller that is designed for unconstrained systems, or assume small perturbations and linearize a saturated system. These approaches can lead to stability issues or limiting the control actions to be too conservative. In this paper, we directly focus on a nonlinear system that explicitly accounts for the saturation of the current magnitude. We use a Lyapunov stability approach to determine a stability condition for the system, guaranteeing that a class of controllers would be stabilizing if they satisfy a simple SDP condition. With this condition we fit a linear-feedback controller by sampling the output (offline) model predictive control problems. This learned controller has improved performances with existing designs.