Autonomous vehicles are complex systems that operate in dynamic environments, where automated driving seeks to control the coupled longitudinal and lateral vehicle dynamics to follow a certain behavior. Model predictive control is one of the most promising tools for this type of application due to its optimal performance and ability to handle input and output constraints. This paper addresses autonomous driving by introducing an adaptive linear parameter varying model predictive controller (LPV-MPC), whose prediction model is adapted online by a neural network. Moreover, the controller’s cost function is optimized by an improved Genetic Algorithm. The proposed controller is evaluated on a challenging track subject to variable wind disturbances.
To reduce the typical time-consuming routines of plant modeling for model-based controller designs, the fictitious reference iterative tuning (FRIT) has been proposed and has proven to be effective in many applications. However, it is generally difficult to select a reference model properly without information on the plant, which significantly affects the control performance and sometimes leads to considerable performance degradation. To address this problem, we propose a pseudo-linearization (PL) method using FRIT and design a new controller for nonlinear systems that combines data-driven and model-based control. This design considers the input constraints using model predictive control. The effectiveness of the proposed method was evaluated according to several practical references using numerical simulations for nonlinear classes and experiments involving artificial muscles with hysteresis characteristics.
Employing Stochastic Nonlinear Model Predictive Control (SNMPC) for real-time applications is challenging due to the complex task of propagating uncertainties through nonlinear systems. This difficulty becomes more pronounced in high-dimensional systems with extended prediction horizons, such as autonomous vehicles. To enhance closed-loop performance in and feasibility in SNMPCs, we introduce the concept of the Uncertainty Propagation Horizon (UPH). The UPH limits the time for uncertainty propagation through system dynamics, preventing trajectory divergence, optimizing feedback loop advantages, and reducing computational overhead. Our SNMPC approach utilizes Polynomial Chaos Expansion (PCE) to propagate uncertainties and incorporates nonlinear hard constraints on state expectations and nonlinear probabilistic constraints. We transform the probabilistic constraints into deterministic constraints by estimating the nonlinear constraints' expectation and variance. We then showcase our algorithm's effectiveness in real-time control of a high-dimensional, highly nonlinear system-the trajectory following of an autonomous passenger vehicle, modeled with a dynamic nonlinear single-track model. Experimental results demonstrate our approach's robust capability to follow an optimal racetrack trajectory at speeds of up to 37.5m/s while dealing with state estimation disturbances, achieving a minimum solving frequency of 97Hz. Additionally, our experiments illustrate that limiting the UPH renders previously infeasible SNMPC problems feasible, even when incorrect uncertainty assumptions or strong disturbances are present.
Increasingly, homeowners opt for photovoltaic (PV) systems and/or battery storage to minimize their energy bills and maximize renewable energy usage. This has spurred the development of advanced control algorithms that maximally achieve those goals. However, a common challenge faced while developing such controllers is the unavailability of accurate forecasts of household power consumption, especially for shorter time resolutions (15 minutes) and in a data-efficient manner. In this paper, we analyze how transfer learning can help by exploiting data from multiple households to improve a single house's load forecasting. Specifically, we train an advanced forecasting model (a temporal fusion transformer) using data from multiple different households, and then finetune this global model on a new household with limited data (i.e. only a few days). The obtained models are used for forecasting power consumption of the household for the next 24 hours~(day-ahead) at a time resolution of 15 minutes, with the intention of using these forecasts in advanced controllers such as Model Predictive Control. We show the benefit of this transfer learning setup versus solely using the individual new household's data, both in terms of (i) forecasting accuracy ($\sim$15\% MAE reduction) and (ii) control performance ($\sim$2\% energy cost reduction), using real-world household data.
In highly interactive driving scenarios, the actions of one agent greatly influences those of its neighbors. Planning safe motions for autonomous vehicles in such interactive environments, therefore, requires reasoning about the impact of the ego's intended motion plan on nearby agents' behavior. Deep-learning-based models have recently achieved great success in trajectory prediction and many models in the literature allow for ego-conditioned prediction. However, leveraging ego-conditioned prediction remains challenging in downstream planning due to the complex nature of neural networks, limiting the planner structure to simple ones, e.g., sampling-based planner. Despite their ability to generate fine-grained high-quality motion plans, it is difficult for gradient-based planning algorithms, such as model predictive control (MPC), to leverage ego-conditioned prediction due to their iterative nature and need for gradient. We present Interactive Joint Planning (IJP) that bridges MPC with learned prediction models in a computationally scalable manner to provide us the best of both the worlds. In particular, IJP jointly optimizes over the behavior of the ego and the surrounding agents and leverages deep-learned prediction models as prediction priors that the join trajectory optimization tries to stay close to. Furthermore, by leveraging homotopy classes, our joint optimizer searches over diverse motion plans to avoid getting stuck at local minima. Closed-loop simulation result shows that IJP significantly outperforms the baselines that are either without joint optimization or running sampling-based planning.
Uncertainty in the behavior of other traffic participants is a crucial factor in collision avoidance for automated driving; here, stochastic metrics could avoid overly conservative decisions. This paper introduces a Stochastic Model Predictive Control (SMPC) planner for emergency collision avoidance in highway scenarios to proactively minimize collision risk while ensuring safety through chance constraints. To guarantee that the emergency trajectory can be attained, we incorporate nonlinear tire dynamics in the prediction model of the ego vehicle. Further, we exploit Max-Min-Plus-Scaling (MMPS) approximations of the nonlinearities to avoid conservatism, enforce proactive collision avoidance, and improve computational efficiency in terms of performance and speed. Consequently, our contributions include integrating a dynamic ego vehicle model into the SMPC planner, introducing the MMPS approximation for real-time implementation in emergency scenarios, and integrating SMPC with hybridized chance constraints and risk minimization. We evaluate our SMPC formulation in terms of proactivity and efficiency in various hazardous scenarios. Moreover, we demonstrate the effectiveness of our proposed approach by comparing it with a state-of-the-art SMPC planner and we validate that the generated trajectories can be attained using a high-fidelity vehicle model in IPG CarMaker.
Harmonic model predictive control (HMPC) is a recent model predictive control (MPC) formulation for tracking piece-wise constant references that includes a parameterized artificial harmonic reference as a decision variable, resulting in an increased performance and domain of attraction with respect to other MPC formulations. This article presents an extension of the HMPC formulation to track periodic harmonic/sinusoidal references and discusses its use for tracking arbitrary trajectories. The proposed formulation inherits the benefits of its predecessor, namely its good performance and large domain of attraction when using small prediction horizons, and that the complexity of its optimization problem does not depend on the period of the reference. We show closed-loop results discussing its performance and comparing it to other MPC formulations.
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.
The power flexibility from smart buildings makes them suitable candidates for providing grid services. The building automation system (BAS) that employs model predictive control (MPC) for grid services relies heavily on sensor data gathered from IoT-based HVAC systems through communication networks. However, cyber-attacks that tamper sensor values can compromise the accuracy and flexibility of HVAC system power adjustment. Existing studies on grid-interactive buildings mainly focus on the efficiency and flexibility of buildings' participation in grid operations, while the security aspect is lacking. In this paper, we investigate the effects of cyber-attacks on HVAC systems in grid-interactive buildings, specifically their power-tracking performance. We design a stochastic optimization-based stealthy sensor attack and a corresponding defense strategy using a resilient control framework. The attack and its defense are tested in a physical model of a test building with a single-chiller HVAC system. Simulation results demonstrate that minor falsifications caused by a stealthy sensor attack can significantly alter the power profile, leading to large power tracking errors. However, the resilient control framework can reduce the power tracking error by over 70% under such attacks without filtering out compromised data.
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.
In this paper, we present a controller framework that synthesizes control policies for Jump Markov Linear Systems subject to stochastic mode switches and imperfect mode estimation. Our approach builds on safe and robust methods for Model Predictive Control (MPC), but in contrast to existing approaches that either optimize without regard to feasibility or utilize soft constraints that increase computational requirements, we employ a safe and robust control approach informed by the feasibility of the optimization problem. We formulate and encode finite horizon safety for multiple model systems in our MPC design using Control Barrier Functions (CBFs). When subject to inaccurate hybrid state estimation, our feasibility-guided MPC generates a control policy that is maximally robust to uncertainty in the system's modes. We evaluate our approach on an orbital rendezvous problem and a six degree-of-freedom hexacopter under several scenarios and benchmarks to demonstrate the utility of the framework. Results indicate that the proposed technique of maximizing the robustness horizon, and the use of CBFs for safety awareness, improve the overall safety and performance of MPC for Jump Markov Linear Systems.
This paper addresses the data-based modelling and optimal control of District Heating Systems (DHSs). Physical models of such large-scale networked systems are governed by complex nonlinear equations that require a large amount of parameters, leading to potential computational issues in optimizing their operation. A novel methodology is hence proposed, exploiting operational data and available physical knowledge to attain accurate and computationally efficient DHSs dynamic models. The proposed idea consists in leveraging multiple Recurrent Neural Networks (RNNs) and in embedding the physical topology of the DHS network in their interconnections. With respect to standard RNN approaches, the resulting modelling methodology, denoted as Physics-Informed RNN (PI-RNN), enables to achieve faster training procedures and higher modelling accuracy, even when reduced-dimension models are exploited. The developed PI-RNN modelling technique paves the way for the design of a Nonlinear Model Predictive Control (NMPC) regulation strategy, enabling, with limited computational time, to minimize production costs, to increase system efficiency and to respect operative constraints over the whole DHS network. The proposed methods are tested in simulation on a DHS benchmark referenced in the literature, showing promising results from the modelling and control perspective.
This paper explores the synergies between integrated power and thermal management (iPTM) and battery charging in an electric vehicle (EV). A multi-objective model predictive control (MPC) framework is developed to optimize the fast charging performance while enforcing the constraints in the power and thermal loops. The approach takes into account the coupling of the battery and cabin thermal management. The case study of a commercial EV demonstrates that the proposed method can effectively meet the requirements of fast charging and thermal management when accurate preview information is available. However, failure to predict the charging event can result in performance degradation with longer charging time. A time-varying weighting strategy is proposed to enhance charging performance in the presence of uncertainty. This strategy leverages the battery state-of-charge (SOC) and adjusts the priority of the multi-objective MPC at different phases during charging. Simulated results using a commercial EV use case show improved robustness in charging time using the proposed strategy.
This work presents a new sufficient condition for synthesizing nonlinear controllers that yield bounded closed-loop tracking error transients despite the presence of unmatched uncertainties that are concurrently being learned online. The approach utilizes contraction theory and addresses fundamental limitations of existing approaches by allowing the contraction metric to depend on the unknown model parameters. This allows the controller to incorporate new model estimates generated online without sacrificing its strong convergence and bounded transients guarantees. The approach is specifically designed for trajectory tracking so the approach is more broadly applicable to adaptive model predictive control as well. Simulation results on a nonlinear system with unmatched uncertainties demonstrates the approach.
Autonomous vehicles are the upcoming solution to most transportation problems such as safety, comfort, and efficiency. The steering control is one of the main important tasks in achieving autonomous driving. Model predictive control (MPC) is among the fittest controllers for this task due to its optimal performance and ability to handle constraints. This paper proposes an adaptive MPC controller (AMPC) for the path-tracking task and an improved PSO algorithm for optimizing the AMPC parameters. Parameter adaption is realized online using a lookup table approach. The proposed AMPC performance is assessed and compared with the classic MPC and the Pure Pursuit controller through simulations.
Seamless human-robot manipulation in close proximity relies on accurate forecasts of human motion. While there has been significant progress in learning forecast models at scale, when applied to manipulation tasks, these models accrue high errors at critical transition points leading to degradation in downstream planning performance. Our key insight is that instead of predicting the most likely human motion, it is sufficient to produce forecasts that capture how future human motion would affect the cost of a robot's plan. We present ManiCast, a novel framework that learns cost-aware human forecasts and feeds them to a model predictive control planner to execute collaborative manipulation tasks. Our framework enables fluid, real-time interactions between a human and a 7-DoF robot arm across a number of real-world tasks such as reactive stirring, object handovers, and collaborative table setting. We evaluate both the motion forecasts and the end-to-end forecaster-planner system against a range of learned and heuristic baselines while additionally contributing new datasets. We release our code and datasets at https://portal-cornell.github.io/manicast/.
Automated Vehicle Path Following Control (PFC) is an advanced control system that can regulate the vehicle into a collision-free region in the presence of other objects on the road. Common collision avoidance functions, such as forward collision warning and automatic emergency braking, have recently been developed and equipped on production vehicles. However, it is impossible to develop a perfectly precise vehicle model when the vehicle is driving. Most PFCs did not consider uncertainties in the vehicle model, external disturbances, and parameter variations at the same time. To address the issues associated with this important feature and function in autonomous driving, a new vehicle PFC is proposed using a robust model predictive control (MPC) design technique based on matrix inequality and the theoretical approach of the hybrid $\&$ switched system. The proposed methodology requires a combination of continuous and discrete states, e.g. regulating the continuous states of the AV (e.g., velocity and yaw angle) and discrete switching of the control strategy that affects the dynamic behaviors of the AV under different driving speeds. Firstly, considering bounded model uncertainties, and norm-bounded external disturbances, the system states and control matrices are modified.