Tom Lefebvre

Dr. Tom Lefebvre

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 January 2022 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
TSTom Staessens
Tom Staessens
TLTom Lefebvre
Tom Lefebvre
GCGuillaume Crevecoeur
Guillaume Crevecoeur
In this article, 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 adapts 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.

26 November 2020 in IEEE Control Systems Letters
Verified
Journal Article
Closed access
TLTom Lefebvre
Tom Lefebvre
Polynomial Chaos Expansions (PCEs) offer an efficient alternative to assess the statistical properties of a model output taking into account the statistical properties of several uncertain model inputs, particularly, under the restriction of probing the forward model as little as possible. The use of PCE knows a steady increase in recent literature with applications spanning from mere system analysis to robust control design and optimization. The principle idea is to model the output as a series expansion, with the expansion basis depending only on the stochastic variables. The basis is then chosen so that it is better suited to support the uncertainty propagation. Once the expansion coefficients have been identified, accessing the statistical moments benefits the linearity of the expansion and the properties of the moment operator. As a result, the first two statistical moments of the model output can be computed easily using well known analytical expressions. For high-order moments, analytical expressions also exist but are inefficient to evaluate. In this letter we present three strategies to efficiently calculate high-order moments from the expansion model and provide an empirical study of the associated computation time supporting any potential users in making an informed choice.

3 June 2022 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
SWSander De Witte
Sander De Witte
THThijs Van Hauwermeiren Van Hauwermeiren
Thijs Van Hauwermeiren Van Hauwermeiren
TLTom Lefebvre
Tom Lefebvre
GCGuillaume Crevecoeur
Guillaume Crevecoeur
Cooperative multiagent manipulation systems allow to extend on the manipulative limitations of individual agents, increasing the complexity of the manipulation tasks the ensemble can handle. Controlling such a system requires meticulous planning of subsequent subtasks, queried to the individual agents, in order to execute the master task successfully. Real-time (re)planning is essential to ensure the task can still be achieved when subtasks execution suffers from uncertainty or when the master task changes intermittently requiring real-time reconfiguration of the plan. In this article, we develop a supervisory control architecture tailored to the cooperation of two robotic manipulators equipped with standard pick-and-place facilities in the plane. We control the planar position and orientation of an object using two underactuated manipulators so that only the position of the object can be controlled directly. The desired orientation follows from the accumulation of alternating relative angles. A time-invariant policy function is trained using deep reinforcement learning, which can determine a finite sequence of pick-and-place maneuvers to manipulate the object to a desired configuration. Two policy architectures are compared. The first uses the kinematic model to determine the final step, whilst the second policy makes this decision itself. The more information is given to the policy, the easier it trains. In return, it becomes less adaptable and loses some of its generalizability.

3 October 2020 in Entropy
Verified
Journal Article
Open access
PDF file
TLTom Lefebvre
Tom Lefebvre
GCGuillaume Crevecoeur
Guillaume Crevecoeur
In this article, we present a generalized view on Path Integral Control (PIC) methods. PIC refers to a particular class of policy search methods that are closely tied to the setting of Linearly Solvable Optimal Control (LSOC), a restricted subclass of nonlinear Stochastic Optimal Control (SOC) problems. This class is unique in the sense that it can be solved explicitly yielding a formal optimal state trajectory distribution. In this contribution, we first review the PIC theory and discuss related algorithms tailored to policy search in general. We are able to identify a generic design strategy that relies on the existence of an optimal state trajectory distribution and finds a parametric policy by minimizing the cross-entropy between the optimal and a state trajectory distribution parametrized by a parametric stochastic policy. Inspired by this observation, we then aim to formulate a SOC problem that shares traits with the LSOC setting yet that covers a less restrictive class of problem formulations. We refer to this SOC problem as Entropy Regularized Trajectory Optimization. The problem is closely related to the Entropy Regularized Stochastic Optimal Control setting which is often addressed lately by the Reinforcement Learning (RL) community. We analyze the theoretical convergence behavior of the theoretical state trajectory distribution sequence and draw connections with stochastic search methods tailored to classic optimization problems. Finally we derive explicit updates and compare the implied Entropy Regularized PIC with earlier work in the context of both PIC and RL for derivative-free trajectory optimization.

14 January 2021 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
FOFrederik Ostyn
Frederik Ostyn
TLTom Lefebvre
Tom Lefebvre
Bram VanderborghtBram Vanderborght
Bram Vanderborght
GCGuillaume Crevecoeur
Guillaume Crevecoeur
Industrial robots can collide due to malfunctioning, wrong user input or unforeseen changes in the environment in which they operate. Different solutions exist to minimize the damage caused by a collision, either absorbed by the environment or by the robot itself. The specific solution depends on the type, size and dynamics of the robot. For high-speed industrial robots, the challenge is in dealing with the large kinetic energy upon impact without compromising the dynamic response during normal operation. The Combined Friction Cam Clutch (CFCC) is proposed as a solution for this problem. We provide a custom mechanical design and derive equations to calculate the threshold and residual torque which are identified as key design metrics. The concept is validated experimentally on a test bench using a prototype of the set-up.

6 July 2023 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Open access
VVVictor Vantilborgh
Victor Vantilborgh
TLTom Lefebvre
Tom Lefebvre
KEKerem Eryilmaz
Kerem Eryilmaz
GCGuillaume Crevecoeur
Guillaume Crevecoeur
There is an emerging industrial demand for predictive maintenance algorithms that exhibit high levels of predictive accuracy. Such condition monitoring tools must estimate dynamic quantities, such as Remaining Useful Lifetime (RUL) and the State of Health (SOH), based on a, typically, restricted set of measurements that can be obtained in an operational setting. These quantities exhibit inherent stochasticity and can only be approximately determined a posteriori to system failure. This paper proposes a generic prognostic tool for probabilistic condition monitoring of mechatronic systems, with the aim to improve the probabilistic prediction of condition metrics, specifically RUL and SOH. Therefore we propose to identify a Hidden Markov Model (HMM) from a fully instrumented measurement set, that is only available for a restricted set of run-to-failure experiments, typically gathered in an R&D setting. Although being artificial and retrospectively constructed metrics, we interpret RUL and SOH as physical measurements with the purpose to identify accurate degradation dynamics. Once the degradation model is identified, we practice the mathematical flexibility of the HMM framework to estimate several of the no longer available dynamic quantities of interest in real-time, from the limited set of measurements that are available in an operational setting. This modelling paradigm is known as virtual sensing. Predictive performance and computational efficiency are further improved by domain knowledge based pre-processing of the measurements. We apply our methodology to solenoid valves (SV), a widely used and often critical component in many industrial systems, which display a large variation in useful lifetime. Benchmark results show that the predictive capabilities of the presented methodology compares with prognostic techniques that are more computationally and memory demanding. Note to Practitioners —The motivation for this research is twofold. First there is a pending industrial need for improved diagnostic and prognostic tools. Second there is the observation that lifetime tests usually take place in an R&D setting and that expert labelling of Remaining Useful Lifetime (RUL) or State of Health (SOH) of a component or system is often based on measurement data that is not available in the industrial setting where the prognostic tools are to be deployed in the end. These two observations suggest that there is large potential in methods that can correlate the expert labelling, in particular RUL & SOH signals, with measurement data that is available in the industrial setting. Our approach has been tested in detail on the case of Solenoid Valves, which are widely used in industry and that are often safety critical. Our experiments demonstrate that the method compares with brute force approaches that overpower ours both in terms of computational as well as memory requirements. The method is furthermore generic and there is no reason to assume it would not work for other applications.