Search

The choice of objective is critical for the performance of an optimal controller. When control requirements vary during operation, e.g. due to changes in the environment with which the system is interacting, these variations should be reflected in the cost function. In this paper we consider the problem of identifying a time dependent cost function from given trajectories. We propose a strategy for explicitly representing time dependency in the cost function, i.e. decomposing it into the product of an unknown time dependent parameter vector and a known state and input dependent vector, modelling the former via a linear combination of trigonometric basis functions. These are incorporated within an inverse optimal control framework that uses the Karush-Kuhn-Tucker (KKT) conditions for ensuring optimality, and allows for formulating an optimization problem with respect to a finite set of basis function hyperparameters. Results are shown for two systems in simulation and evaluated against state-of-the-art approaches.

The effectiveness of non-parametric, kernel-based methods for function estimation comes at the price of high computational complexity, which hinders their applicability in adaptive, model-based control. Motivated by approximation techniques based on sparse spectrum Gaussian processes, we focus on models given by regularized trigonometric linear regression. This paper provides an analysis of the performance of such an estimation set-up within the statistical learning framework. In particular, we derive a novel bound for the sample error in finite-dimensional spaces, accounting for noise with potentially unbounded support. Next, we study the approximation error and discuss the bias-variance trade-off as a function of the regularization parameter by combining the two bounds.

Mobile manipulation in robotics is challenging due to the need of solving many diverse tasks, such as opening a door or picking-and-placing an object. Typically, a basic first-principles system description of the robot is available, thus motivating the use of model-based controllers. However, the robot dynamics and its interaction with an object are affected by uncertainty, limiting the controller's performance. To tackle this problem, we propose a Bayesian multi-task learning model that uses trigonometric basis functions to identify the error in the dynamics. In this way, data from different but related tasks can be leveraged to provide a descriptive error model that can be efficiently updated online for new, unseen tasks. We combine this learning scheme with a model predictive controller, and extensively test the effectiveness of the proposed approach, including comparisons with available baseline controllers. We present simulation tests with a ball-balancing robot, and door-opening hardware experiments with a quadrupedal manipulator., Comment: Accepted for publication in the IEEE Robotics and Automation Letters (RA-L)

The performance of model-based control techniques strongly depends on the quality of the employed dynamics model. If strong guarantees are desired, it is therefore common to robustly treat all possible sources of uncertainty, such as model inaccuracies or external disturbances. This, however, can result in overly conservative control strategies. In this paper, we present a stochastic model predictive control approach for discrete-time LTI systems subject to bounded parametric uncertainty and potentially unbounded stochastic additive noise. The proposed scheme makes use of homothetic tubes along the prediction horizon for a robust treatment of parametric uncertainty. Stochastic noise is handled by non-conservatively tightening constraints using the concept of probabilistic reachable sets (PRS). In order to accommodate all possible parametric uncertainties, we provide a strategy for generating "robustified" PRS based only on first and second moments of the noise sequence. In the case of quadratic cost functions, and under a further i.i.d. assumption on the noise distribution, we also provide an average asymptotic performance bound for the l2-norm of the closed-loop state. Finally, we demonstrate our scheme on both an illustrative example, and in a building temperature control problem.

Learning-based model predictive control has been widely applied in autonomous racing to improve the closed-loop behaviour of vehicles in a data-driven manner. When environmental conditions change, e.g., due to rain, often only the predictive model is adapted, but the controller parameters are kept constant. However, this can lead to suboptimal behaviour. In this paper, we address the problem of data-efficient controller tuning, adapting both the model and objective simultaneously. The key novelty of the proposed approach is that we leverage a learned dynamics model to encode the environmental condition as a so-called context. This insight allows us to employ contextual Bayesian optimization to efficiently transfer knowledge across different environmental conditions. Consequently, we require fewer data to find the optimal controller configuration for each context. The proposed framework is extensively evaluated with more than 3'000 laps driven on an experimental platform with 1:28 scale RC race cars. The results show that our approach successfully optimizes the lap time across different contexts requiring fewer data compared to other approaches based on standard Bayesian optimization.

Data availability has dramatically increased in recent years, driving model-based control methods to exploit learning techniques for improving the system description, and thus control performance. Two key factors that hinder the practical applicability of learning methods in control are their high computational complexity and limited generalization capabilities to unseen conditions. Meta-learning is a powerful tool that enables efficient learning across a finite set of related tasks, easing adaptation to new unseen tasks. This paper makes use of a meta-learning approach for adaptive model predictive control, by learning a system model that leverages data from previous related tasks, while enabling fast fine-tuning to the current task during closed-loop operation. The dynamics is modeled via Gaussian process regression and, building on the Karhunen-Lo{\`e}ve expansion, can be approximately reformulated as a finite linear combination of kernel eigenfunctions. Using data collected over a set of tasks, the eigenfunction hyperparameters are optimized in a meta-training phase by maximizing a variational bound for the log-marginal likelihood. During meta-testing, the eigenfunctions are fixed, so that only the linear parameters are adapted to the new unseen task in an online adaptive fashion via Bayesian linear regression, providing a simple and efficient inference scheme. Simulation results are provided for autonomous racing with miniature race cars adapting to unseen road conditions.

Established techniques for simulation and prediction with Gaussian process (GP) dynamics often implicitly make use of an independence assumption on successive function evaluations of the dynamics model. This can result in significant error and underestimation of the prediction uncertainty, potentially leading to failures in safety-critical applications. This paper discusses methods that explicitly take the correlation of successive function evaluations into account. We first describe two sampling-based techniques; one approach provides samples of the true trajectory distribution, suitable for `ground truth' simulations, while the other draws function samples from basis function approximations of the GP. Second, we propose a linearization-based technique that directly provides approximations of the trajectory distribution, taking correlations explicitly into account. We demonstrate the procedures in simple numerical examples, contrasting the results with established methods.

Designing controllers for systems affected by model uncertainty can prove to be a challenge, especially when seeking the optimal compromise between the conflicting goals of identification and control. This trade-off is explicitly taken into account in the dual control problem, for which the exact solution is provided by stochastic dynamic programming. Due to its computational intractability, we propose a sampling-based approximation for systems affected by both parametric and structural model uncertainty. The approach proposed in this paper separates the prediction horizon in a dual and an exploitation part. The dual part is formulated as a scenario tree that actively discriminates among a set of potential models while learning unknown parameters. In the exploitation part, achieved information is fixed for each scenario, and open-loop control sequences are computed for the remainder of the horizon. As a result, we solve one optimization problem over a collection of control sequences for the entire horizon, explicitly considering the knowledge gained in each scenario, leading to a dual model predictive control formulation.

Dual control explicitly addresses the problem of trading off active exploration and exploitation in the optimal control of partially unknown systems. While the problem can be cast in the framework of stochastic dynamic programming, exact solutions are only tractable for discrete state and action spaces of very small dimension due to a series of nested minimization and expectation operations. We propose an approximate dual control method for systems with continuous state and input domain based on a rollout dynamic programming approach, splitting the control horizon into a dual and an exploitation part. The dual part is approximated using a scenario tree generated by sampling the process noise and the unknown system parameters, for which the underlying distribution is updated via Bayesian estimation along the horizon. In the exploitation part, we fix the resulting parameter estimate of each scenario branch and compute an open-loop control sequence for the remainder of the horizon. The key benefit of the proposed sampling-based approximation is that it enables the formulation as one optimization problem that computes a collection of control sequences over the scenario tree, leading to a dual model predictive control formulation.