Guillaume Sandou

Yoshinari Takayama, Alessio Iovine, Bart Besselink et al.

Real-world control systems must achieve long-horizon objectives (liveness) while respecting continuous-time safety constraints, a combination that motivates hierarchical layered control architectures (LCAs). Existing LCA research, however, lacks (i) a uniform specification language across discrete planning and continuous execution, (ii) formal guarantees that specifications are preserved when interconnecting subsystems at heterogeneous time scales, and (iii) compositional separation between layers, owing to reliance on naive input-filtering laws. This paper addresses all three gaps by importing the safety--liveness decomposition into a heterogeneous assume--guarantee framework: \emph{safety is enforced by invariance} at the continuous-time layer, while \emph{liveness is achieved through refinement} at the discrete-time layer, with inter-layer coordination formalized via vertical refinement and timing-compatibility conditions. We instantiate this contract with a novel LCA combining an MPC planner, an input-to-state stabilizing (ISS) low-level controller, and a reference-governor bridge, and validate it on a Hybrid Energy Storage System (HESS) comprising a battery and a supercapacitor.

Mohamad Koteich, Abdelmalek Maloum, Gilles Duc et al.

In the paper by Vaclavek et al. (IEEE Trans. Ind. Electron., vol. 60, no. 8, pp. 3047-3059, Aug. 2013), the local observability of both induction machine and permanent-magnet synchronous machine (PMSM) under motion-sensorless operation is studied. In this letter, the "slowly varying" speed assumption is discussed, and the PMSM observability condition at standstill is revisited.

Mohamad Koteich, Gilles Duc, Abdelmalek Maloum et al.

Electric drives control without shaft sensors has been an active research topic for almost three decades. It consists of estimating the rotor speed and/or position from the currents and voltages measurement. This paper deals with the observability conditions of electric drives in view of sensorless control. The models of such systems are strongly nonlinear. For this reason, a local observability approach is applied to analyze the deteriorated performance of sensorless drives in some operating conditions. The validity of the observability conditions is confirmed by numerical simulations and experimental data, using an extended Kalman filter as observer.

Jean Mercat, Nicole El Zoghby, Guillaume Sandou et al.

In the recent vehicle trajectory prediction literature, the most common baselines are briefly introduced without the necessary information to reproduce it. In this article we produce reproducible vehicle prediction results from simple models. For that purpose, the process is explicit, and the code is available. Those baseline models are a constant velocity model and a single-vehicle prediction model. They are applied on the NGSIM US-101 and I-80 datasets using only relative positions. Thus, the process can be reproduced with any database containing tracking of vehicle positions. The evaluation reports Root Mean Squared Error (RMSE), Final Displacement Error (FDE), Negative Log-Likelihood (NLL), and Miss Rate (MR). The NLL estimation needs a careful definition because several formulations that differ from the mathematical definition are used in other works. This article is meant to be used along with the published code to establish baselines for further work. An extension is proposed to replace the constant velocity assumption with a learned model using a recurrent neural network. This brings good improvements in accuracy and uncertainty estimation and opens possibilities for both complex and interpretable models.

Jean Mercat, Thomas Gilles, Nicole El Zoghby et al.

This paper presents a novel vehicle motion forecasting method based on multi-head attention. It produces joint forecasts for all vehicles on a road scene as sequences of multi-modal probability density functions of their positions. Its architecture uses multi-head attention to account for complete interactions between all vehicles, and long short-term memory layers for encoding and forecasting. It relies solely on vehicle position tracks, does not need maneuver definitions, and does not represent the scene with a spatial grid. This allows it to be more versatile than similar model while combining any forecasting capabilities, namely joint forecast with interactions, uncertainty estimation, and multi-modality. The resulting prediction likelihood outperforms state-of-the-art models on the same dataset.