Showing papers in "IFAC-PapersOnLine in 2020"

TL;DR: It is stressed that common deep nets such as feedforward and cascadeforward nets are nonlinear ARX (NARX) models, and can thus be easily incorporated in System Identification code and practice, and the case of LSTM nets is an example of NonLinear State-Space (NLSS) models.

TL;DR: Open Optimization Engine (OpEn) is an open-source code generation tool for real-time embedded nonconvex optimization, which implements a novel numerical method that involves very simple algebraic operations such as vector products and has a low memory footprint.

TL;DR: HPIPM as discussed by the authors is a high-performance framework for quadratic programming (QP) designed to provide building blocks to efficiently and reliably solve model predictive control problems, and it provides interior point method (IPM) solvers as well (partial) condensing routines.

TL;DR: A multi-agent version of emphatic temporal difference learning for off-policy policy evaluation is developed, and convergence under linear function approximation is proved, to develop and give convergence guarantees for a new multi- agent off-Policy actor-critic algorithm.

TL;DR: An overview of the historical development of the machine learning field with a focus on the development of mathematical apparatus in its first decades is provided and a number of little-known facts published in hard to reach sources are presented.

TL;DR: This paper presents physics-informed neural ordinary differential equations (PINODE), a hybrid model that combines the two modeling techniques to overcome the aforementioned problems and demonstrates a method that beneficially merges physical insight with real data.

TL;DR: In this paper, the progress made since the first wave energy control systems were suggested in the 1970s, and examines current outstanding challenges for the control community, and discusses the potential of wave energy to provide a carbon-free solution to the world's increasing appetite for energy.

TL;DR: The aim of this paper is to investigate the impacts of Industry 4.0 technologies on the different roles of logistics operators that work in the main logistics domains and areas.

TL;DR: It is proved that this setpoint is exponentially stable for the closed loop of the proposed MPC, if it is reachable by the system dynamics and constraints, and for an unreachable setpoint, the scheme guarantees closed-loop exponential stability of the optimal reachable equilibrium.

TL;DR: Disropt as discussed by the authors is a Python package for distributed optimization over networks, in which an optimization problem must be solved by peer-to-peer processors (without central coordinators) that have access only to partial knowledge of the entire problem.

TL;DR: It is argued, that Gated Units are easier to optimize not because they solve the vanishing gradient problem, but because they circumvent the emergence of large local gradients.

TL;DR: A multi-sensor information fusion based wheeling-legged cooperative control strategy is proposed to solve the problem of attitude stability control for the six wheeled-legged robot-BIT-NAZA-II to ensure the maximum motion space of single leg.

TL;DR: This work model the hose as a series of smaller discrete links and derive a generalized coordinate-free dynamics for the hose, and shows that certain configurations of this under-actuated system are differentially-flat.

TL;DR: A relatively simple tumor growth model describing the antitumor effect of pegylated liposomal doxorubicin (PLD) validated with real experimental data obtained in a genetically engineered mouse model of breast cancer is created.

TL;DR: A hierarchical control framework for a kite-based marine hydrokinetic system that executes power-augmenting cross-current flight, along with simulation results based on a high-fidelity turbulent flow model that is representative of flow conditions in the Gulf Stream are presented.

TL;DR: In this article, the authors present a methodology to learn explicit Model Predictive Control (eMPC) laws from sample data points with tunable complexity, where the coefficients of two linear layers and a parametric quadratic program implicit layer are optimized to fit the training data.

TL;DR: In this paper, a policy approximation based on mixed-integer MPC schemes is proposed, and a computationally inexpensive technique is proposed to generate exploration in the mixed integer input space that ensures a satisfaction of the constraints.

TL;DR: A novel 4-D fractional order chaotic system has been introduced and has been synchronized in dislocated phase and anti-phase synchronization with its parallel systems by constructing non linear control inputs.

TL;DR: A data-based optimal tracking control approach is developed by involving the iterative dual heuristic dynamic programming algorithm for nonaffine systems and employing a model network to directly approximate the unknown system function instead of the error dynamics.

TL;DR: By exploiting the symmetry, it is shown that data from all the invariant sets are not required for constructing the global Koopman operator; that is, local knowledge of the system is enough to infer the global dynamics.

TL;DR: The development of Smart Silver Villages is considered as part of social infrastructure in rural areas, supporting the autonomy and independence of the rural population in their old age.

TL;DR: The experimental results show that the proposed method converges to nearly time-optimal behavior by maximizing the progress on the track and achieves competitive lap time results.

TL;DR: In this article, the authors show that the projection approach is generally disruptive in the context of Q-learning though a simple alternative solves the issue, while simple corrections can be used in order to ensure that the policy gradients are unbiased.

TL;DR: It will be shown that TCLab as an Arduino based portable kit, provides an excellent means to test digital controllers, as it is a compact and portable lab to be used by lecturers and students.

TL;DR: A hybrid system based on brain-computer interface and virtual reality is proposed, which can provide various training programs including action observation, motor imagery and physical therapy for post-stroke patients with different motor control levels and training demands.

TL;DR: A recently developed controller balancing between sliding mode and linear algorithms (SML) is considered for the application and the results obtained without any information on the platform or metal plate mass are compared to those of standard proportional-derivative (PD) based control schemes.

TL;DR: In this work, integral of the squared error (ISE) criterion is modified, and a new objective function is proposed for controller design which results in maximum sensitivity less than two which implies robust closed-loop performance.

TL;DR: An improved bridge surface crack detection algorithm based on a further developed You Only Look Once version 3 algorithm (YOLO v3) is proposed to realize the fast and accurate detection of bridge surface cracks for timely repair application scenarios.

TL;DR: This work has implemented RL and DRL based control for batch polymerization of Polymethyl methacrylate (PMMA), and both the controllers have been found to achieve the given setpoint, while the DRL controller being faster than the RL controllers.

TL;DR: The main contribution of the paper is the characterization of the trade-off between the tolerable DoS attack levels for leaderless and leader-follower consensus and the required data rates for the quantizers during the communication attempts among the agents.