In this paper, we develop an optimal weight adaptation strategy of model predictive control (MPC) for connected and automated vehicles (CAVs) in mixed traffic. We model the interaction between a CAV and a human-driven vehicle (HDV) as a simultaneous game and formulate a game-theoretic MPC problem to find a Nash equilibrium of the game. In the MPC problem, the weights in the HDV's objective function can be learned online using moving horizon inverse reinforcement learning. Using Bayesian optimization, we propose a strategy to optimally adapt the weights in the CAV's objective function so that the expected true cost when using MPC in simulations can be minimized. We validate the effectiveness of the optimal strategy by numerical simulations of a vehicle crossing example at an unsignalized intersection.
We present Self-Tuning Tube-based Model Predictive Control (STT-MPC), an adaptive robust control algorithm for uncertain linear systems with additive disturbances based on the least-squares estimator and polytopic tubes. Our algorithm leverages concentration results to bound the system uncertainty set with prescribed confidence, and guarantees robust constraint satisfaction for this set, along with recursive feasibility and input-to-state stability. Persistence of excitation is ensured without compromising the algorithm's asymptotic performance or increasing its computational complexity. We demonstrate the performance of our algorithm using numerical experiments.
The current trend in the evolution of wind turbines is to increase their rotor size in order to capture more power. This leads to taller, slender and more flexible towers, which thus experience higher dynamical loads due to the turbine rotation and environmental factors. It is hence compelling to deploy advanced control methods that can dynamically counteract such loads, especially at tower positions that are more prone to develop cracks or corrosion damages. Still, to the best of the authors' knowledge, little to no attention has been paid in the literature to load mitigation at multiple tower locations. Furthermore, there is a need for control schemes that can balance load reduction with optimization of power production. In this paper, we develop an Economic Model Predictive Control (eMPC) framework to address such needs. First, we develop a linear modal model to account for the tower flexural dynamics. Then we incorporate it into an eMPC framework, where the dynamics of the turbine rotation are expressed in energy terms. This allows us to obtain a convex formulation, that is computationally attractive. Our control law is designed to avoid the 'turn-pike' behavior and guarantee recursive feasibility. We demonstrate the performance of the proposed controller on a 5MW reference WT model: the results illustrate that the proposed controller is able to reduce the tower loads at multiple locations, without significant effects to the generated power.
Switched-actuator systems with setup times (SAcSSs) are systems in which the actuator configuration has to be switched during operation, and where the switching induces non-negligible actuator downtime. Optimally controlling SAcSSs requires the online solving of both a discrete actuator allocation problem, in which the switch-induced actuator downtime is taken into account, as well as an optimization problem for the (typically continuous) control inputs. Mixed-integer model predictive control (MI-MPC) offers a powerful framework for tackling such problems. However, the efficient modeling of SAcSSs for MI-MPC is not straightforward, and real-time feasibility is often a major hurdle in practice. It is the objective of this paper to provide an intuitive and systematic modeling procedure tailored to SAcSSs, which is specifically designed to allow for user-friendly controller synthesis, and to yield efficient MI-MPCs. We apply these new results in a case study of large-volume magnetic-resonance-guided high-intensity focused ultrasound hyperthermia, which involves the heating of tumors (using real-valued local heating controls, as well as discrete range-extending actuator relocation during which no heating is allowed) to enhance the efficacy of radio- and chemotherapy.
Control design for robotic systems is complex and often requires solving an optimization to follow a trajectory accurately. Online optimization approaches like Model Predictive Control (MPC) have been shown to achieve great tracking performance, but require high computing power. Conversely, learning-based offline optimization approaches, such as Reinforcement Learning (RL), allow fast and efficient execution on the robot but hardly match the accuracy of MPC in trajectory tracking tasks. In systems with limited compute, such as aerial vehicles, an accurate controller that is efficient at execution time is imperative. We propose an Analytic Policy Gradient (APG) method to tackle this problem. APG exploits the availability of differentiable simulators by training a controller offline with gradient descent on the tracking error. We address training instabilities that frequently occur with APG through curriculum learning and experiment on a widely used controls benchmark, the CartPole, and two common aerial robots, a quadrotor and a fixed-wing drone. Our proposed method outperforms both model-based and model-free RL methods in terms of tracking error. Concurrently, it achieves similar performance to MPC while requiring more than an order of magnitude less computation time. Our work provides insights into the potential of APG as a promising control method for robotics. To facilitate the exploration of APG, we open-source our code and make it available at https://github.com/lis-epfl/apg_trajectory_tracking.
We present a robust model predictive control method (MPC) for discrete-time linear time-delayed systems with state and control input constraints. The system is subject to both polytopic model uncertainty and additive disturbances. In the proposed method, a time-varying feedback control policy is optimized such that the robust satisfaction of all constraints for the closed-loop system is guaranteed. By encoding the effects of the delayed states and inputs into the feedback policy, we solve the robust optimal control problem in MPC using System Level Synthesis which results in a convex quadratic program that jointly conducts uncertainty over-approximation and robust controller synthesis. Notably, the number of variables in the quadratic program is independent of the delay horizon. The effectiveness and scalability of our proposed method are demonstrated numerically.
We present a robust adaptive model predictive control (MPC) framework for nonlinear continuous-time systems with bounded parametric uncertainty and additive disturbance. We utilize general control contraction metrics (CCMs) to parameterize a homothetic tube around a nominal prediction that contains all uncertain trajectories. Furthermore, we incorporate model adaptation using set-membership estimation. As a result, the proposed MPC formulation is applicable to a large class of nonlinear systems, reduces conservatism during online operation, and guarantees robust constraint satisfaction and convergence to a neighborhood of the desired setpoint. One of the main technical contributions is the derivation of corresponding tube dynamics based on CCMs that account for the state and input dependent nature of the model mismatch. Furthermore, we online optimize over the nominal parameter, which enables general set-membership updates for the parametric uncertainty in the MPC. Benefits of the proposed homothetic tube MPC and online adaptation are demonstrated using a numerical example involving a planar quadrotor.
Wind turbine (WT) controllers are often geared towards maximum power extraction, while suitable operating constraints should be guaranteed such that WT components are protected from failures. Control strategies can be also devised to reduce the generated power, for instance to track a power reference provided by the grid operator. They are called down-regulation strategies and allow to balance power generation and grid loads, as well as to provide ancillary grid services, such as frequency regulation. Although this balance is limited by the wind availability and grid demand, the quality of wind energy can be improved by introducing down-regulation strategies that make use of the kinetic energy of the turbine dynamics. This paper shows how the kinetic energy in the rotating components of turbines can be used as an additional degree-of-freedom by different down-regulation strategies. In particular we explore the power tracking problem based on convex model predictive control (MPC) at a single wind turbine. The use of MPC allows us to introduce a further constraint that guarantees flow stability and avoids stall conditions. Simulation results are used to illustrate the performance of the developed down-regulation strategies. Notably, by maximizing rotor speeds, and thus kinetic energy, the turbine can still temporarily guarantee tracking of a given power reference even when occasional saturation of the available wind power occurs. In the study case we proved that our approach can guarantee power tracking in saturated conditions for 10 times longer than with traditional down-regulation strategies.
Despite decades of research, existing navigation systems still face real-world challenges when deployed in the wild, e.g., in cluttered home environments or in human-occupied public spaces. To address this, we present a new class of implicit control policies combining the benefits of imitation learning with the robust handling of system constraints from Model Predictive Control (MPC). Our approach, called Performer-MPC, uses a learned cost function parameterized by vision context embeddings provided by Performers -- a low-rank implicit-attention Transformer. We jointly train the cost function and construct the controller relying on it, effectively solving end-to-end the corresponding bi-level optimization problem. We show that the resulting policy improves standard MPC performance by leveraging a few expert demonstrations of the desired navigation behavior in different challenging real-world scenarios. Compared with a standard MPC policy, Performer-MPC achieves >40% better goal reached in cluttered environments and >65% better on social metrics when navigating around humans.
This paper investigates the combination of model predictive control (MPC) concepts and posterior sampling techniques and proposes a simple constraint tightening technique to introduce cautiousness during explorative learning episodes. The provided theoretical analysis in terms of cumulative regret focuses on previously stated sufficient conditions of the resulting `Cautious Bayesian MPC' algorithm and shows Lipschitz continuity of the future reward function in the case of linear MPC problems. In the case of nonlinear MPC problems, it is shown that commonly required assumptions for nonlinear MPC optimization techniques provide sufficient criteria for model-based RL using posterior sampling. Furthermore, it is shown that the proposed constraint tightening implies a bound on the expected number of unsafe learning episodes in the linear and nonlinear case using a soft-constrained MPC formulation. The efficiency of the method is illustrated using numerical examples.
Data-driven models for nonlinear dynamical systems based on approximating the underlying Koopman operator or generator have proven to be successful tools for forecasting, feature learning, state estimation, and control. It has become well known that the Koopman generators for control-affine systems also have affine dependence on the input, leading to convenient finite-dimensional bilinear approximations of the dynamics. Yet there are still two main obstacles that limit the scope of current approaches for approximating the Koopman generators of systems with actuation. First, the performance of existing methods depends heavily on the choice of basis functions over which the Koopman generator is to be approximated; and there is currently no universal way to choose them for systems that are not measure preserving. Secondly, if we do not observe the full state, then it becomes necessary to account for the dependence of the output time series on the sequence of supplied inputs when constructing observables to approximate Koopman operators. To address these issues, we write the dynamics of observables governed by the Koopman generator as a bilinear hidden Markov model, and determine the model parameters using the expectation-maximization (EM) algorithm. The E-step involves a standard Kalman filter and smoother, while the M-step resembles control-affine dynamic mode decomposition for the generator. We demonstrate the performance of this method on three examples, including recovery of a finite-dimensional Koopman-invariant subspace for an actuated system with a slow manifold; estimation of Koopman eigenfunctions for the unforced Duffing equation; and model-predictive control of a fluidic pinball system based only on noisy observations of lift and drag.
As robots increasingly enter human-centered environments, they must not only be able to navigate safely around humans, but also adhere to complex social norms. Humans often rely on non-verbal communication through gestures and facial expressions when navigating around other people, especially in densely occupied spaces. Consequently, robots also need to be able to interpret gestures as part of solving social navigation tasks. To this end, we present Gesture2Path, a novel social navigation approach that combines image-based imitation learning with model-predictive control. Gestures are interpreted based on a neural network that operates on streams of images, while we use a state-of-the-art model predictive control algorithm to solve point-to-point navigation tasks. We deploy our method on real robots and showcase the effectiveness of our approach for the four gestures-navigation scenarios: left/right, follow me, and make a circle. Our experiments indicate that our method is able to successfully interpret complex human gestures and to use them as a signal to generate socially compliant trajectories for navigation tasks. We validated our method based on in-situ ratings of participants interacting with the robots.
Model predictive control (MPC) for uncertain systems in the presence of hard constraints on state and input is a non-trivial problem, and the challenge is increased manyfold in the absence of state measurements. In this paper, we propose an adaptive output feedback MPC technique, based on a novel combination of an adaptive observer and robust MPC, for single-input single-output discrete-time linear time-invariant systems. At each time instant, the adaptive observer provides estimates of the states and the system parameters that are then leveraged in the MPC optimization routine while robustly accounting for the estimation errors. The solution to the optimization problem results in a homothetic tube where the state estimate trajectory lies. The true state evolves inside a larger outer tube obtained by augmenting a set, invariant to the state estimation error, around the homothetic tube sections. The proof for recursive feasibility for the proposed `homothetic and invariant' two-tube approach is provided, along with simulation results on an academic system.
This paper studies the consensus problem of general linear discrete-time multi-agent systems (MAS) with input constraints and bounded time-varying communication delays. We propose a robust distributed model predictive control (DMPC) consensus protocol that integrates the offline consensus design with online DMPC optimization to exploit their respective advantages. More precisely, each agent is equipped with an offline consensus protocol, which is a priori designed, depending on its immediate neighbors' estimated states. Further, the estimation errors propagated over time due to inexact neighboring information are proved bounded under mild technical assumptions, based on which a robust DMPC strategy is deliberately designed to achieve robust consensus while satisfying input constraints. Moreover, it is shown that, with the suitably designed cost function and constraints, the feasibility of the associated optimization problem can be recursively ensured. We further provide the consensus convergence result of the constrained MAS in the presence of bounded varying delays. Finally, two numerical examples are given to verify the effectiveness of the proposed distributed consensus algorithm.
In this article the implementation of a controller and specifically of a Model Predictive Controller (MPC) on an Edge Computing device, for controlling the trajectory of an Unmanned Aerial Vehicle (UAV) model, is examined. MPC requires more computation power in comparison to other controllers, such as PID or LQR, since it use cost functions, optimization methods and iteratively predicts the output of the system and the control commands for some determined steps in the future (prediction horizon). Thus, the computation power required depends on the prediction horizon, the complexity of the cost functions and the optimization. The more steps determined for the horizon the more efficient the controller can be, but also more computation power is required. Since sometimes robots are not capable of managing all the computing process locally, it is important to offload some of the computing process from the robot to the cloud. But then some disadvantages may occur, such as latency and safety issues. Cloud computing may offer "infinity" computation power but the whole system suffers in latency. A solution to this is the use of Edge Computing, which will reduce time delays since the Edge device is much closer to the source of data. Moreover, by using the Edge we can offload the demanding controller from the UAV and set a longer prediction horizon and try to get a more efficient controller.
Model Predictive Control (MPC) is a state-of-the-art (SOTA) control technique which requires solving hard constrained optimization problems iteratively. For uncertain dynamics, analytical model based robust MPC imposes additional constraints, increasing the hardness of the problem. The problem exacerbates in performance-critical applications, when more compute is required in lesser time. Data-driven regression methods such as Neural Networks have been proposed in the past to approximate system dynamics. However, such models rely on high volumes of labeled data, in the absence of symbolic analytical priors. This incurs non-trivial training overheads. Physics-informed Neural Networks (PINNs) have gained traction for approximating non-linear system of ordinary differential equations (ODEs), with reasonable accuracy. In this work, we propose a Robust Adaptive MPC framework via PINNs (RAMP-Net), which uses a neural network trained partly from simple ODEs and partly from data. A physics loss is used to learn simple ODEs representing ideal dynamics. Having access to analytical functions inside the loss function acts as a regularizer, enforcing robust behavior for parametric uncertainties. On the other hand, a regular data loss is used for adapting to residual disturbances (non-parametric uncertainties), unaccounted during mathematical modelling. Experiments are performed in a simulated environment for trajectory tracking of a quadrotor. We report 7.8% to 43.2% and 8.04% to 61.5% reduction in tracking errors for speeds ranging from 0.5 to 1.75 m/s compared to two SOTA regression based MPC methods.
In this paper, the model predictive control is designed for an interval type-2 Takagi-Sugeno (T-S) system with unknown time-varying delay in state and input vectors. The time-varying delay is a weird phenomenon that is appeared in almost all systems. It can make many problems and instability while the system is working. In this paper, the time-varying delay is considered in both states and input vectors and is the sensible difference between the proposed method here and previous algorithms, besides, it is unknown but bounded. To solve the problem, the Razumikhin approach is applied to the proposed method since it includes a Lyapunov function with the original nonaugmented state space of system models compared to Krasovskii formula. On the other hand, the Razumikhin method act better and avoids the inherent complexity of the Krasovskii specifically when large delays and disturbances are appeared. To stabilize output results, the model predictive control (MPC) is designed for the system and the considered system in this paper is interval type-2 (IT2) fuzzy T-S that has better estimation of the dynamic model of the system. Here, online optimization problems are solved by the linear matrix inequalities (LMIs) which reduce the burdens of the computation and online computational costs compared to the offline and non-LMI approach. At the end, an example is illustrated for the proposed approach.
Density of the reachable states can help understand the risk of safety-critical systems, especially in situations when worst-case reachability is too conservative. Recent work provides a data-driven approach to compute the density distribution of autonomous systems' forward reachable states online. In this paper, we study the use of such approach in combination with model predictive control for verifiable safe path planning under uncertainties. We first use the learned density distribution to compute the risk of collision online. If such risk exceeds the acceptable threshold, our method will plan for a new path around the previous trajectory, with the risk of collision below the threshold. Our method is well-suited to handle systems with uncertainties and complicated dynamics as our data-driven approach does not need an analytical form of the systems' dynamics and can estimate forward state density with an arbitrary initial distribution of uncertainties. We design two challenging scenarios (autonomous driving and hovercraft control) for safe motion planning in environments with obstacles under system uncertainties. We first show that our density estimation approach can reach a similar accuracy as the Monte-Carlo-based method while using only 0.01X training samples. By leveraging the estimated risk, our algorithm achieves the highest success rate in goal reaching when enforcing the safety rate above 0.99.
The optimal operation of regulated lakes is a challenging task involving conflicting objectives, ranging from controlling lake levels to avoid floods and low levels to water supply downstream. The traditional approach to operation policy design is based on an offline optimization, where a feedback control rule mapping lake storage into daily release decisions is identified over a set of observational data. In this paper, we propose a receding-horizon policy for a more frequent, online regulation of the lake level, and we discuss its tuning as compared to benchmark approaches. As side contributions, we provide a daily alternative based on the same rationale, and we show that this is still valid under some assumptions on the water inflow. Numerical simulations are used to show the effectiveness of the proposed approach. We demonstrate the approach on the regulated lake Como, Italy.
Control barrier functions (CBFs) recently introduced a systematic way to guarantee the system's safety through set invariance. Together with a nominal control method, it establishes a safety-critical control mechanism. The resulting safety constraints can be enforced as hard constraints in quadratic programming (QP) optimization, which rectifies the nominal control law based on the set of safe inputs. In this work, we introduce a multiple CBFs scheme which enforces several safety constraints with high relative degrees. This control structure is essential in many challenging robotic applications that need to meet several safety criteria simultaneously. In order to illustrate the capabilities of the proposed method, we have addressed the problem of reactive obstacle avoidance for a class of tractor-trailer systems. Safety is one of the fundamental issues in autonomous tractor-trailer systems design. The lack of fast response due to poor maneuverability makes reactive obstacle avoidance difficult for these systems. We develop a control structure based on a multiple CBFs scheme for a multi-steering tractor-trailer system to ensure a collision-free maneuver for both the tractor and trailer in the presence of several obstacles. Model predictive control is selected as the nominal tracking controller, and the proposed control strategy is tested in several challenging scenarios.