arXiv subjects

Guillaume Crevecoeur

Publications and source records attributed to Guillaume Crevecoeur.

At least 19 recordsLinked to original sources

arXiv2026

Learning On The Job: Zero-Shot Task Execution under Parametric Uncertainty via Trajectory-Parametrized Dual Control

Model-based control can achieve reliable task performance, but its effectiveness depends on the accuracy of the underlying model. Robots operating under model uncertainty must often adapt to previously unseen payloads, objects, and interaction dynamics to complete a task successfully. Conventional approaches typically rely on a dedicated task- and control-agnostic excitation phase for estimating physics parameters, delaying task execution and collecting potentially irrelevant data. In this paper, we instead consider zero-shot task execution under parametric uncertainty, where online model learning and control proceed concurrently during task execution. Our approach formulates reference generation within a dual control framework to produce task-relevant, informative trajectories that reduce parameter uncertainty in directions critical to task success. We predefine a feedback policy with an explicit parameter adaptation law and optimize the reference through the resulting adaptive closed-loop dynamics. We propose two formulations: 1) minimizing expected task cost under parameter uncertainty, and 2) minimizing optimality loss, which quantifies the degradation in task performance caused by planning with an incorrect parameter estimate. By actively optimizing for informative trajectories via a natural Fisher information measure, we tightly approach a lower bound on task-relevant parameter uncertainty while simultaneously achieving reliable task execution. Across diverse tasks, controllers, and adaptation laws, targeted exploration enables the identification required for successful task execution, allowing robots to learn relevant physical parameters while completing the task in a single attempt.

cs.RO↗

arXiv2026

Optimal Path Planning of Airborne Wind Energy Systems with a Flexible Tether

In this work, we establish an optimal control framework for airborne wind energy systems (AWESs) with flexible tethers. The AWES configuration, consisting of a six-degree-of-freedom aircraft, a flexible tether, and a winch, is formulated as an index-1 differential-algebraic system of equations (DAE). We achieve this by adopting a minimal coordinate representation that uses Euler angles to characterize the aircraft's attitude and employing a quasi-static approach for the tether. The presented method contrasts with other recent optimization studies that use an index-3 DAE approach. By doing so, our approach avoids related inconsistency condition problems. We use a homotopy strategy to solve the optimal control problem that ultimately generates optimal trajectories of the AWES with a flexible tether. We furthermore compare with a rigid tether model by investigating the resulting mechanical powers and tether forces. Simulation results demonstrate the efficacy of the presented methodology and the necessity to incorporate the flexibility of the tether when solving the optimal control problem.

math.OC↗

arXiv2026

Unifying Entropy Regularization in Optimal Control: From and Back to Classical Objectives via Iterated Soft Policies and Path Integral Solutions

This paper develops a unified perspective on several optimal control formulations through the lens of Kullback-Leibler (KL) regularization. We propose a central problem that separates the KL penalties on policies and transitions with independent weights, thus generalizing the standard trajectory-level KL-regularization used in probabilistic optimal control. This umbrella formulation recovers various control problems: the classical Stochastic Optimal Control (SOC), Risk-Sensitive Stochastic Optimal Control (RSOC), and their policy-based KL-regularized counterparts, termed soft-policy SOC and RSOC, which yield tractable surrogates. Beyond being regularized variants, these soft-policy formulations majorize the original SOC and RSOC, thus, iterating their solutions recovers the original objectives. We further identify a synchronized case of soft-policy RSOC where the policy and transition KL weights coincide, yielding a linear Bellman operator, path-integral solution, and compositionality -- extending these computationally favourable properties to a broad class of control problems.

math.OC↗

arXiv2025

Gaussian Process Dual MPC using Active Inference: An Autonomous Vehicle Usecase

Designing controllers under uncertainty requires balancing the need to explore system dynamics with the requirement to maintain reliable control performance. Dual control addresses this challenge by selecting actions that both regulate the system and actively gather informative data. This paper investigates the use of the Active Inference framework, grounded in the Free Energy Principle, for developing a dual model-predictive controller (MPC). To identify and quantify uncertainty, we introduce an online sparse semi-parametric Gaussian Process model that combines the flexibility of nonparametric with the efficiency of parametric learning for real-time updates. By applying the expected free energy functional to this adaptive probabilistic model, we derive an MPC objective that incorporates an information-theoretic term, which captures uncertainty arising from both the learned model and measurement noise. This formulation leads to a stochastic optimal control problem for dual controller design, which is solved using a novel dynamic-programming-based method. Simulation results on a vehicle use case demonstrate that the proposed algorithm enhances autonomous driving control performance across different settings and scenarios.

math.OC↗

arXiv2025

How to Capture Human Preference: Commissioning of a Robotic Use-Case via Preferential Bayesian Optimisation

The popularity of Bayesian Optimization (BO) to automate or support the commissioning of engineering systems is rising. Conventional BO, however, relies on the availability of a scalar objective function. The latter is often difficult to define and rarely captures the nuanced judgement of expert operators in industrial settings. Preferential Bayesian Optimization (PBO) addresses this limitation by relying solely on pairwise preference feedback of a human expert, so-called duels. In this paper, we study PBO's capacity to commission a particular setup where a manipulator needs to push a block towards a target position. We benchmark state-of-the-art algorithms in both simulations and in the real world. Our results confirm that PBO can commission the set-up to the satisfaction of an expert operator whilst relying solely on binary preference feedback. To evaluate to what extend the same result can be achieved using conventional BO we investigate the experts decision consistency against an expert-designed cost function. Our study reveals that the experts fail to define a cost function that is in full agreement with their own decision process as witnessed in the PBO experiments. We then show that the auxiliary cost function that is constructed as a by-product of the PBO algorithms outperforms the expert-designed cost function in terms of decision consistency. Furthermore we demonstrate that this cost function can be used with conventional BO algorithms in an effort to reproduce the optimal design. This proofs the preference based cost function captures the experts' preferences perhaps more effectively than the experts could articulate preference themselves. In conclusion, we discuss downsides and propose directions for future research.

eess.SY↗

arXiv2025

Differential Flatness of Quasi-Static Slider-Pusher Models with Applications in Control

This paper investigates the dynamic properties of planar slider-pusher systems as a motion primitive in manipulation tasks. To that end, we construct a differential kinematic model deriving from the limit surface approach under the quasi-static assumption and with negligible contact friction. The quasi-static model applies to generic slider shapes and circular pusher geometries, enabling a differential kinematic representation of the system. From this model, we analyze differential flatness - a property advantageous for control synthesis and planning - and find that slider-pusher systems with polygon sliders and circular pushers exhibit flatness with the centre of mass as a flat output. Leveraging this property, we propose two control strategies for trajectory tracking: a cascaded quasi-static feedback strategy and a dynamic feedback linearization approach. We validate these strategies through closed-loop simulations incorporating perturbed models and input noise, as well as experimental results using a physical setup with a finger-like pusher and vision-based state detection. The real-world experiments confirm the applicability of the simulation gains, highlighting the potential of the proposed methods for

eess.SY↗

arXiv2025

Efficient Training of Neural SDEs Using Stochastic Optimal Control

We present a hierarchical, control theory inspired method for variational inference (VI) for neural stochastic differential equations (SDEs). While VI for neural SDEs is a promising avenue for uncertainty-aware reasoning in time-series, it is computationally challenging due to the iterative nature of maximizing the ELBO. In this work, we propose to decompose the control term into linear and residual non-linear components and derive an optimal control term for linear SDEs, using stochastic optimal control. Modeling the non-linear component by a neural network, we show how to efficiently train neural SDEs without sacrificing their expressive power. Since the linear part of the control term is optimal and does not need to be learned, the training is initialized at a lower cost and we observe faster convergence.

cs.LG↗

arXiv2024

Probabilistic Latent Variable Modeling for Dynamic Friction Identification and Estimation

Precise identification of dynamic models in robotics is essential to support control design, friction compensation, output torque estimation, etc. A longstanding challenge remains in the identification of friction models for robotic joints, given the numerous physical phenomena affecting the underlying friction dynamics which result into nonlinear characteristics and hysteresis behaviour in particular. These phenomena proof difficult to be modelled and captured accurately using physical analogies alone. This has motivated researchers to shift from physics-based to data-driven models. Currently, these methods are still limited in their ability to generalize effectively to typical industrial robot deployement, characterized by high- and low-velocity operations and frequent direction reversals. Empirical observations motivate the use of dynamic friction models but these remain particulary challenging to establish. To address the current limitations, we propose to account for unidentified dynamics in the robot joints using latent dynamic states. The friction model may then utilize both the dynamic robot state and additional information encoded in the latent state to evaluate the friction torque. We cast this stochastic and partially unsupervised identification problem as a standard probabilistic representation learning problem. In this work both the friction model and latent state dynamics are parametrized as neural networks and integrated in the conventional lumped parameter dynamic robot model. The complete dynamics model is directly learned from the noisy encoder measurements in the robot joints. We use the Expectation-Maximisation (EM) algorithm to find a Maximum Likelihood Estimate (MLE) of the model parameters. The effectiveness of the proposed method is validated in terms of open-loop prediction accuracy in comparison with baseline methods, using the Kuka KR6 R700 as a test platform.

cs.RO↗

arXiv2024

Deterministic Trajectory Optimization through Probabilistic Optimal Control

In this article, we discuss two algorithms tailored to discrete-time deterministic finite-horizon nonlinear optimal control problems or so-called deterministic trajectory optimization problems. Both algorithms can be derived from an emerging theoretical paradigm that we refer to as probabilistic optimal control. The paradigm reformulates stochastic optimal control as an equivalent probabilistic inference problem and can be viewed as a generalisation of the former. The merit of this perspective is that it allows to address the problem using the Expectation-Maximization algorithm. It is shown that the application of this algorithm results in a fixed point iteration of probabilistic policies that converge to the deterministic optimal policy. Two strategies for policy evaluation are discussed, using state-of-the-art uncertainty quantification methods resulting into two distinct algorithms. The algorithms are structurally closest related to the differential dynamic programming algorithm and related methods that use sigma-point methods to avoid direct gradient evaluations. The main advantage of the algorithms is an improved balance between exploration and exploitation over the iterations, leading to improved numerical stability and accelerated convergence. These properties are demonstrated on different nonlinear systems.

math.OC↗

arXiv2024

Introducing DAIMYO: a first-time-right dynamic design architecture and its application to tail-sitter UAS development

In recent years, there has been a notable evolution in various multidisciplinary design methodologies for dynamic systems. Among these approaches, a noteworthy concept is that of concurrent conceptual and control design or co-design. This approach involves the tuning of feedforward and/or feedback control strategies in conjunction with the conceptual design of the dynamic system. The primary aim is to discover integrated solutions that surpass those attainable through a disjointed or decoupled approach. This concurrent design paradigm exhibits particular promise in the context of hybrid unmanned aerial systems (UASs), such as tail-sitters, where the objectives of versatility (driven by control considerations) and efficiency (influenced by conceptual design) often present conflicting demands. Nevertheless, a persistent challenge lies in the potential disparity between the theoretical models that underpin the design process and the real-world operational environment, the so-called reality gap. Such disparities can lead to suboptimal performance when the designed system is deployed in reality. To address this issue, this paper introduces DAIMYO, a novel design architecture that incorporates a high-fidelity environment, which emulates real-world conditions, into the procedure in pursuit of a `first-time-right' design. The outcome of this innovative approach is a design procedure that yields versatile and efficient UAS designs capable of withstanding the challenges posed by the reality gap.

math.OC↗

arXiv2024

KeyCLD: Learning Constrained Lagrangian Dynamics in Keypoint Coordinates from Images

We present KeyCLD, a framework to learn Lagrangian dynamics from images. Learned keypoints represent semantic landmarks in images and can directly represent state dynamics. We show that interpreting this state as Cartesian coordinates, coupled with explicit holonomic constraints, allows expressing the dynamics with a constrained Lagrangian. KeyCLD is trained unsupervised end-to-end on sequences of images. Our method explicitly models the mass matrix, potential energy and the input matrix, thus allowing energy based control. We demonstrate learning of Lagrangian dynamics from images on the dm_control pendulum, cartpole and acrobot environments. KeyCLD can be learned on these systems, whether they are unactuated, underactuated or fully actuated. Trained models are able to produce long-term video predictions, showing that the dynamics are accurately learned. We compare with Lag-VAE, Lag-caVAE and HGN, and investigate the benefit of the Lagrangian prior and the constraint function. KeyCLD achieves the highest valid prediction time on all benchmarks. Additionally, a very straightforward energy shaping controller is successfully applied on the fully actuated systems. Please refer to our project page for code and additional results: https://rdaems.github.io/keycld/

cs.LG↗

arXiv2023

Variational Inference for SDEs Driven by Fractional Noise

We present a novel variational framework for performing inference in (neural) stochastic differential equations (SDEs) driven by Markov-approximate fractional Brownian motion (fBM). SDEs offer a versatile tool for modeling real-world continuous-time dynamic systems with inherent noise and randomness. Combining SDEs with the powerful inference capabilities of variational methods, enables the learning of representative function distributions through stochastic gradient descent. However, conventional SDEs typically assume the underlying noise to follow a Brownian motion (BM), which hinders their ability to capture long-term dependencies. In contrast, fractional Brownian motion (fBM) extends BM to encompass non-Markovian dynamics, but existing methods for inferring fBM parameters are either computationally demanding or statistically inefficient. In this paper, building upon the Markov approximation of fBM, we derive the evidence lower bound essential for efficient variational inference of posterior path measures, drawing from the well-established field of stochastic analysis. Additionally, we provide a closed-form expression to determine optimal approximation coefficients. Furthermore, we propose the use of neural networks to learn the drift, diffusion and control terms within our variational posterior, leading to the variational training of neural-SDEs. In this framework, we also optimize the Hurst index, governing the nature of our fractional noise. Beyond validation on synthetic data, we contribute a novel architecture for variational latent video prediction,-an approach that, to the best of our knowledge, enables the first variational neural-SDE application to video perception.

cs.LG↗

arXiv2023

Flatness-based MPC using B-splines transcription with application to a Pusher-Slider System

This work discusses the use of model predictive control (MPC) for the manipulation of a pusher-slider system. In particular we leverage the differential flatness of the pusher-slider in combination with a B-splines transcription to address the computational demand that is typically associated to real-time implementation of an MPC controller. We demonstrate the flatness based B-spline MPC controller in simulation and compare it to a standard MPC implementation approach using direct multiple shooting. We evaluate the computational advantage of the flatness based MPC empirically and document computational acceleration up to 65%.

math.OC↗

arXiv2023

Differential Flatness of Slider-Pusher Systems for Constrained Time Optimal Collision Free Path Planning

In this work we show that the differential kinematics of slider-pusher systems are differentially flat assuming quasi-static behaviour and frictionless contact. Second we demonstrate that the state trajectories are invariant to time-differential transformations of the path parametrizing coordinate. For one this property allows to impose arbitrary velocity profiles on the slider without impacting the geometry of the state trajectory. This property implies that certain path planning problems may be decomposed approximately into a strictly geometric path planning and an auxiliary throughput speed optimization problem. Building on these insights we elaborate a numerical approach tailored to constrained time optimal collision free path planning and apply it to the slider-pusher system.

math.DS↗

arXiv2023

A Supervisory Learning Control Framework for Autonomous & Real-time Task Planning for an Underactuated Cooperative Robotic task

We introduce a framework for cooperative manipulation, applied on an underactuated manipulation problem. Two stationary robotic manipulators are required to cooperate in order to reposition an object within their shared work space. Control of multi-agent systems for manipulation tasks cannot rely on individual control strategies with little to no communication between the agents that serve the common objective through swarming. Instead a coordination strategy is required that queries subtasks to the individual agents. We formulate the problem in a Task And Motion Planning (TAMP) setting, while considering a decomposition strategy that allows us to treat the task and motion planning problems separately. We solve the supervisory planning problem offline using deep Reinforcement Learning techniques resulting into a supervisory policy capable of coordinating the two manipulators into a successful execution of the pick-and-place task. Additionally, a benefit of solving the task planning problem offline is the possibility of real-time (re)planning, demonstrating robustness in the event of subtask execution failure or on-the-fly task changes. The framework achieved zero-shot deployment on the real setup with a success rate that is higher than 90%.

cs.RO↗

arXiv2022

Evolutionary sparse data-driven discovery of complex multibody system dynamics

The value of unknown parameters of multibody systems is crucial for prediction, monitoring, and control, sometimes estimated using a biased physics-based model leading to incorrect outcomes. Discovering motion equations of multibody systems from time-series data is challenging as they consist of complex rational functions, constants as function arguments, and diverse function terms, which are not trivial to guess. This study aims at developing an evolutionary symbolic sparse regression approach for the system identification of multibody systems. The procedure discovers equations of motion and system parameters appearing as either constant values in function arguments or coefficients of function expressions. A genetic programming algorithm is written to generate symbolic function expressions, in which a hard-thresholding regression method is embedded. In an evolutionary manner, the complex functional forms, constant arguments, and unknown coefficients are identified to eventually discover the governing equation of a given system. A fitness measure is presented to promote parsimony in distilled equations and reduction in fit-to-data error. Hybrid discrete-continuous dynamical systems are also investigated, for which an approach is suggested to determine both mode number and system submodels. The performance and efficiency of the suggested evolutionary symbolic sparse regression methodology are evaluated in a simulation environment. The capability of the developed approach is also demonstrated by studying several multibody systems. The procedure is efficient and gives the possibility to estimate system parameters and distill respective governing equations. This technique reduces the risk that the function dictionary does not cover all functionality required to unravel hidden physical laws and the need for prior knowledge of the mechanism of interest.

cs.CE↗

arXiv2022

Physics Informed LSTM Network for Flexibility Identification in Evaporative Cooling Systems

In energy intensive industrial systems, an evaporative cooling process may introduce operational flexibility. Such flexibility refers to a systems ability to deviate from its scheduled energy consumption. Identifying the flexibility, and therefore, designing control that ensures efficient and reliable operation presents a great challenge due to the inherently complex dynamics of industrial systems. Recently, machine learning models have attracted attention for identifying flexibility, due to their ability to model complex nonlinear behavior. This research presents machine learning based methods that integrate system dynamics into the machine learning models (e.g., Neural Networks) for better adherence to physical constraints. We define and evaluate physics informed long-short term memory networks (PhyLSTM) and physics informed neural networks (PhyNN) for the identification of flexibility in the evaporative cooling process. These physics informed networks approximate the time-dependent relationship between control input and system response while enforcing the dynamics of the process in the neural network architecture. Our proposed PhyLSTM provides less than 2% system response estimation error, converges in less than half iterations compared to a baseline Neural Network (NN), and accurately estimates the defined flexibility metrics. We include a detailed analysis of the impact of training data size on the performance and optimization of our proposed models.

eess.SY↗

arXiv2021

Adaptive control of a mechatronic system using constrained residual reinforcement learning

We propose a simple, practical and intuitive approach to improve the performance of a conventional controller in uncertain environments using deep reinforcement learning while maintaining safe operation. Our approach is motivated by the observation that conventional controllers in industrial motion control value robustness over adaptivity to deal with different operating conditions and are suboptimal as a consequence. Reinforcement learning on the other hand can optimize a control signal directly from input-output data and thus adapt to operational conditions, but lacks safety guarantees, impeding its use in industrial environments. To realize adaptive control using reinforcement learning in such conditions, we follow a residual learning methodology, where a reinforcement learning algorithm learns corrective adaptations to a base controller's output to increase optimality. We investigate how constraining the residual agent's actions enables to leverage the base controller's robustness to guarantee safe operation. We detail the algorithmic design and propose to constrain the residual actions relative to the base controller to increase the method's robustness. Building on Lyapunov stability theory, we prove stability for a broad class of mechatronic closed-loop systems. We validate our method experimentally on a slider-crank setup and investigate how the constraints affect the safety during learning and optimality after convergence.

eess.SY↗