In this paper, we introduce a new conservation-based approach to model traffic dynamics, and apply the model predictive control (MPC) approach to control the boundary traffic inflow and outflow, so that the traffic congestion is reduced. We establish an interface between the Simulation of Urban Mobility (SUMO) software and MATLAB to define a network of interconnected roads (NOIR) as a directed graph, and present traffic congestion management as a network control problem. By formally specifying the traffic feasibility conditions, and using the linear temporal logic, we present the proposed MPC-based boundary control problem as a quadratic programming with linear equality and inequality constraints. The success of the proposed traffic boundary control is demonstrated by simulation of traffic congestion control in Center City Philadelphia.
This paper focuses on distributed learning-based control of decentralized multi-agent systems where the agents' dynamics are modeled by Gaussian Processes (GPs). Two fundamental problems are considered: the optimal design of experiment for concurrent learning of the agents' GP models, and the distributed coordination given the learned models. Using a Distributed Model Predictive Control (DMPC) approach, the two problems are formulated as distributed optimization problems, where each agent's sub-problem includes both local and shared objectives and constraints. To solve the resulting complex and non-convex DMPC problems efficiently, we develop an algorithm called Alternating Direction Method of Multipliers with Convexification (ADMM-C) that combines a distributed ADMM algorithm and a Sequential Convexification method. The computational efficiency of our proposed method comes from the facts that the computation for solving the DMPC problem is distributed to all agents and that efficient convex optimization solvers are used at the agents for solving the convexified sub-problems. We also prove that, under some technical assumptions, the ADMM-C algorithm converges to a stationary point of the penalized optimization problem. The effectiveness of our approach is demonstrated in numerical simulations of a multi-vehicle formation control example.
Decentralized conflict resolution for autonomous vehicles is needed in many places where a centralized method is not feasible, e.g., parking lots, rural roads, merge lanes, etc. However, existing methods generally do not fully utilize optimization in decentralized conflict resolution. We propose a decentralized conflict resolution method for autonomous vehicles based on a novel extension to the Alternating Directions Method of Multipliers (ADMM), called Online Adaptive ADMM (OA-ADMM), and on Model Predictive Control (MPC). OA-ADMM is tailored to online systems, where fast and adaptive real-time optimization is crucial, and allows the use of safety information about the physical system to improve safety in real-time control. We prove convergence in the static case and give requirements for online convergence. Combining OA-ADMM and MPC allows for robust decentralized motion planning and control that seamlessly integrates decentralized conflict resolution. The effectiveness of our proposed method is shown through simulations in CARLA, an open-source vehicle simulator, resulting in a reduction of 47.93% in mean added delay compared with the next best method.
This article presents the real-time implementation of the model predictive control for tracking formulation to control a two-wheeled inverted pendulum robot. This formulation offers several advantages over standard MPC formulations at the expense of the addition of a small number of decision variables, which complicates the inner structure of the matrices of the optimization problem. We implement a sparse solver, based on an extension of the alternating direction method of multipliers, in the system's embedded hardware. The results indicate that the solver is suitable for controlling a real system with sample times in the range of milliseconds using current, readily-available hardware.
We present a learning algorithm for training a single policy that imitates multiple gaits of a walking robot. To achieve this, we use and extend MPC-Net, which is an Imitation Learning approach guided by Model Predictive Control (MPC). The strategy of MPC-Net differs from many other approaches since its objective is to minimize the control Hamiltonian, which derives from the principle of optimality. To represent the policies, we employ a mixture-of-experts network (MEN) and observe that the performance of a policy improves if each expert of a MEN specializes in controlling exactly one mode of a hybrid system, such as a walking robot. We introduce new loss functions for single- and multi-gait policies to achieve this kind of expert selection behavior. Moreover, we benchmark our algorithm against Behavioral Cloning and the original MPC implementation on various rough terrain scenarios. We validate our approach on hardware and show that a single learned policy can replace its teacher to control multiple gaits.
We present a robust data-driven control scheme for an unknown linear system model with bounded process and measurement noise. Instead of depending on a system model in traditional predictive control, a controller utilizing data-driven reachable regions is proposed. The data-driven reachable regions are based on a matrix zonotope recursion and are computed based on only noisy input-output data of a trajectory of the system. We assume that measurement and process noise are contained in bounded sets. While we assume knowledge of these bounds, no knowledge about the statistical properties of the noise is assumed. In the noise-free case, we prove that the presented purely data-driven control scheme results in an equivalent closed-loop behavior to a nominal model predictive control scheme. In the case of measurement and process noise, our proposed scheme guarantees robust constraint satisfaction, which is essential in safety-critical applications. Numerical experiments show the effectiveness of the proposed data-driven controller in comparison to model-based control schemes.
This paper focuses on the trajectory tracking control problem for an articulated unmanned ground vehicle. We propose and compare two approaches in terms of performance and computational complexity. The first uses a nonlinear mathematical model derived from first principles and combines a nonlinear model predictive controller (NMPC) with a nonlinear moving horizon estimator (NMHE) to produce a control strategy. The second is based on an input-state linearization (ISL) of the original model followed by linear model predictive control (LMPC). A fast real-time iteration scheme is proposed, implemented for the NMHE-NMPC framework and benchmarked against the ISL-LMPC framework, which is a traditional and cheap method. The experimental results for a time-based trajectory show that the NMHE-NMPC framework with the proposed real-time iteration scheme gives better trajectory tracking performance than the ISL-LMPC framework and the required computation time is feasible for real-time applications. Moreover, the ISL-LMPC produces results of a quality comparable to the NMHE-NMPC framework at a significantly reduced computational cost.
Substantial advancements to model-based reinforcement learning algorithms have been impeded by the model-bias induced by the collected data, which generally hurts performance. Meanwhile, their inherent sample efficiency warrants utility for most robot applications, limiting potential damage to the robot and its environment during training. Inspired by information theoretic model predictive control and advances in deep reinforcement learning, we introduce Model Predictive Actor-Critic (MoPAC), a hybrid model-based/model-free method that combines model predictive rollouts with policy optimization as to mitigate model bias. MoPAC leverages optimal trajectories to guide policy learning, but explores via its model-free method, allowing the algorithm to learn more expressive dynamics models. This combination guarantees optimal skill learning up to an approximation error and reduces necessary physical interaction with the environment, making it suitable for real-robot training. We provide extensive results showcasing how our proposed method generally outperforms current state-of-the-art and conclude by evaluating MoPAC for learning on a physical robotic hand performing valve rotation and finger gaiting--a task that requires grasping, manipulation, and then regrasping of an object.
In this paper, we present the use of Reinforcement Learning (RL) based on Robust Model Predictive Control (RMPC) for the control of an Autonomous Surface Vehicle (ASV). The RL-MPC strategy is utilized for obstacle avoidance and target (set-point) tracking. A scenario-tree robust MPC is used to handle potential failures of the ship thrusters. Besides, the wind and ocean current are considered as unknown stochastic disturbances in the real system, which are handled via constraints tightening. The tightening and other cost parameters are adjusted by RL, using a Q-learning technique. An economic cost is considered, minimizing the time and energy required to achieve the ship missions. The method is illustrated in simulation on a nonlinear 3-DOF model of a scaled version of the Cybership 2.
This paper proposes an observer-based framework for solving Partially Observable Markov Decision Processes (POMDPs) when an accurate model is not available. We first propose to use a Moving Horizon Estimation-Model Predictive Control (MHE-MPC) scheme in order to provide a policy for the POMDP problem, where the full state of the real process is not measured and necessarily known. We propose to parameterize both MPC and MHE formulations, where certain adjustable parameters are regarded for tuning the policy. In this paper, for the sake of tackling the unmodeled and partially observable dynamics, we leverage the Reinforcement Learning (RL) to tune the parameters of MPC and MHE schemes jointly, with the closed-loop performance of the policy as a goal rather than model fitting or the MHE performance. Illustrations show that the proposed approach can effectively increase the performance of close-loop control of systems formulated as POMDPs.
This paper presents high precision control and deep learning-based corn stand counting algorithms for a low-cost, ultra-compact 3D printed and autonomous field robot for agricultural operations. Currently, plant traits, such as emergence rate, biomass, vigor, and stand counting, are measured manually. This is highly labor-intensive and prone to errors. The robot, termed TerraSentia, is designed to automate the measurement of plant traits for efficient phenotyping as an alternative to manual measurements. In this paper, we formulate a Nonlinear Moving Horizon Estimator (NMHE) that identifies key terrain parameters using onboard robot sensors and a learning-based Nonlinear Model Predictive Control (NMPC) that ensures high precision path tracking in the presence of unknown wheel-terrain interaction. Moreover, we develop a machine vision algorithm designed to enable an ultra-compact ground robot to count corn stands by driving through the fields autonomously. The algorithm leverages a deep network to detect corn plants in images, and a visual tracking model to re-identify detected objects at different time steps. We collected data from 53 corn plots in various fields for corn plants around 14 days after emergence (stage V3 - V4). The robot predictions have agreed well with the ground truth with $C_{robot}=1.02 \times C_{human}-0.86$ and a correlation coefficient $R=0.96$. The mean relative error given by the algorithm is $-3.78\%$, and the standard deviation is $6.76\%$. These results indicate a first and significant step towards autonomous robot-based real-time phenotyping using low-cost, ultra-compact ground robots for corn and potentially other crops.
In advanced tokamak scenarios, active feedback control of unstable resistive wall modes (RWM) may be required. A RWM is an instability due to plasma kink at higher plasma pressure, moderated by the presence of a resistive wall surrounding the plasma. We address the dominant kink instability associated with the main nonaxisymmetric (n = 1) RWM, described by the CarMa model. Model predictive control (MPC) is used, with the aim of enlarging the domain of attraction of the unstable RWM modes subject to power-supply voltage constraints. The implementation of MPC is challenging, because the related quadratic programming (QP) on-line optimization problems must be solved at a sub-ms sampling rate. Using complexity-reduction pre-processing techniques and a primal fast gradient method (FGM) QP solver, sufficiently short computation times for ITER are reachable using a standard personal computer (PC). In this work we explore even faster finite-word-length (FWL) implementation using field-programmable gate arrays (FPGA), which would facilitate experimental testing of such control algorithms on dynamically faster medium-sized tokamaks, and compare the computational accuracy and time with the PC implementation.
So far, many control algorithms have been developed for singularly perturbed systems. However, in many industrial processes, enforcing closed-loop fast-slow dynamics for peculiarly non-separable ones is a prior request and a crucial issue to be resolved. Aiming at the above problem, this paper presents two dual-level model predictive control (MPC) algorithms for two-timescale dynamical systems with unknown bounded disturbance and input constraint. The proposed algorithms, each one composed of two regulators working in slow and fast time scales, are designed to generate closed-loop separable dynamics at the high and low levels. As a key feature, the proposed algorithms are not only suitable for singularly perturbed systems, but also capable of imposing separable closed-loop performance for dynamics that are non-separable and strongly coupled. The recursive feasibility and convergence properties are proven under suitable assumptions. The simulation results on controlling a Boiler Turbine (BT) system, including the comparisons with other classic controllers are reported, which show the effectiveness of the proposed algorithms.
Active network management (ANM) of electricity distribution networks include many complex stochastic sequential optimization problems. These problems need to be solved for integrating renewable energies and distributed storage into future electrical grids. In this work, we introduce Gym-ANM, a framework for designing reinforcement learning (RL) environments that model ANM tasks in electricity distribution networks. These environments provide new playgrounds for RL research in the management of electricity networks that do not require an extensive knowledge of the underlying dynamics of such systems. Along with this work, we are releasing an implementation of an introductory toy-environment, ANM6-Easy, designed to emphasize common challenges in ANM. We also show that state-of-the-art RL algorithms can already achieve good performance on ANM6-Easy when compared against a model predictive control (MPC) approach. Finally, we provide guidelines to create new Gym-ANM environments differing in terms of (a) the distribution network topology and parameters, (b) the observation space, (c) the modelling of the stochastic processes present in the system, and (d) a set of hyperparameters influencing the reward signal. Gym-ANM can be downloaded at https://github.com/robinhenry/gym-anm.
A path-following collision-avoidance model predictive control (MPC) method is proposed which approximates obstacle shapes as convex polygons. Collision-avoidance is ensured by means of the signed distance function which is calculated efficiently as part of the MPC problem by making use of a dual formulation. The overall MPC problem can be solved by standard nonlinear programming (NLP) solvers. The dual signed distance formulation yields, besides the (dual) collision-avoidance constraints, norm, and consistency constraints. A novel approach is presented that combines the arising norm equality with the dual collision-avoidance inequality constraints to yield an alternative formulation reduced in complexity. Moving obstacles are considered using separate convex sets of linearly predicted obstacle positions in the dual problem. The theoretical findings and simplifications are compared with the often-used ellipsoidal obstacle formulation and are analyzed with regard to efficiency by the example of a simulated path-following autonomous surface vessel during a realistic maneuver and AIS obstacle data from the Kiel bay area.
Model predictive control is an advanced control approach for multivariable systems with constraints, which is reliant on an accurate dynamic model. Most real dynamic models are however affected by uncertainties, which can lead to closed-loop performance deterioration and constraint violations. In this paper we introduce a new algorithm to explicitly consider time-invariant stochastic uncertainties in optimal control problems. The difficulty of propagating stochastic variables through nonlinear functions is dealt with by combining Gaussian processes with polynomial chaos expansions. The main novelty in this paper is to use this combination in an efficient fashion to obtain mean and variance estimates of nonlinear transformations. Using this algorithm, it is shown how to formulate both chance-constraints and a probabilistic objective for the optimal control problem. On a batch reactor case study we firstly verify the ability of the new approach to accurately approximate the probability distributions required. Secondly, a tractable stochastic nonlinear model predictive control approach is formulated with an economic objective to demonstrate the closed-loop performance of the method via Monte Carlo simulations.
We present a straightforward and efficient way to control unstable robotic systems using an estimated dynamics model. Specifically, we show how to exploit the differentiability of Gaussian Processes to create a state-dependent linearized approximation of the true continuous dynamics that can be integrated with model predictive control. Our approach is compatible with most Gaussian process approaches for system identification, and can learn an accurate model using modest amounts of training data. We validate our approach by learning the dynamics of an unstable system such as a segway with a 7-D state space and 2-D input space (using only one minute of data), and we show that the resulting controller is robust to unmodelled dynamics and disturbances, while state-of-the-art control methods based on nominal models can fail under small perturbations. Code is open sourced at https://github.com/learning-and-control/core .
Vehicle trajectory prediction tasks have been commonly tackled from two distinct perspectives: either with knowledge-driven methods or more recently with data-driven ones. On the one hand, we can explicitly implement domain-knowledge or physical priors such as anticipating that vehicles will follow the middle of the roads. While this perspective leads to feasible outputs, it has limited performance due to the difficulty to hand-craft complex interactions in urban environments. On the other hand, recent works use data-driven approaches which can learn complex interactions from the data leading to superior performance. However, generalization, \textit{i.e.}, having accurate predictions on unseen data, is an issue leading to unrealistic outputs. In this paper, we propose to learn a "Realistic Residual Block" (RRB), which effectively connects these two perspectives. Our RRB takes any off-the-shelf knowledge-driven model and finds the required residuals to add to the knowledge-aware trajectory. Our proposed method outputs realistic predictions by confining the residual range and taking into account its uncertainty. We also constrain our output with Model Predictive Control (MPC) to satisfy kinematic constraints. Using a publicly available dataset, we show that our method outperforms previous works in terms of accuracy and generalization to new scenes. We will release our code and data split here: https://github.com/vita-epfl/RRB.
The System Level Synthesis (SLS) approach facilitates distributed control of large cyberphysical networks in an easy-to-understand, computationally scalable way. We present an overview of the SLS approach and its associated extensions in nonlinear control, MPC, adaptive control, and learning for control. To illustrate the effectiveness of SLS-based methods, we present a case study motivated by the power grid, with communication constraints, actuator saturation, disturbances, and changing setpoints. This simple but challenging case study necessitates the use of model predictive control (MPC); however, standard MPC techniques often scales poorly to large systems and incurs heavy computational burden. To address this challenge, we combine two SLS-based controllers to form a layered MPC-like controller. Our controller has constant computational complexity with respect to the system size, gives a 20-fold reduction in online computation requirements, and still achieves performance that is within 3% of the centralized MPC controller.
Although ground robotic autonomy has gained widespread usage in structured and controlled environments, autonomy in unknown and off-road terrain remains a difficult problem. Extreme, off-road, and unstructured environments such as undeveloped wilderness, caves, and rubble pose unique and challenging problems for autonomous navigation. To tackle these problems we propose an approach for assessing traversability and planning a safe, feasible, and fast trajectory in real-time. Our approach, which we name STEP (Stochastic Traversability Evaluation and Planning), relies on: 1) rapid uncertainty-aware mapping and traversability evaluation, 2) tail risk assessment using the Conditional Value-at-Risk (CVaR), and 3) efficient risk and constraint-aware kinodynamic motion planning using sequential quadratic programming-based (SQP) model predictive control (MPC). We analyze our method in simulation and validate its efficacy on wheeled and legged robotic platforms exploring extreme terrains including an abandoned subway and an underground lava tube.