Abstract

Inland navigation transport takes part in the Trans-European network program (TEN-T ), which aims at promoting this mode of transport by creating favorable conditions for the further development of this sector. The NAIADES Action Program comprises numerous actions and measures to boost transport on inland waterways. Among these actions, the infrastructure issue is dealt with. It requires the inventory of the existing infrastructure and the study of the possible effects of the expected climate change. This was one of the objectives of the GEPET-Eau project (2013-2016), which led to the proposal of multi-scale modeling approaches and adaptive and predictive control architectures. The resilience of inland waterways against the increase of navigation demand and the expected extreme drought and flood events was studied by considering deterministic models. The proposed architecture is suitable to consider two scales of space and time to optimize the water resource allocation among the inland networks and to guarantee the navigation conditions by proposing advanced control and fault detection tools. These approaches, which were designed by considering inland waterways in the north of France, are still being improved. Indeed, it is firstly necessary to consider all the uncertainties that are inherent to large-scale and environmental systems. Secondly, the advanced control and fault detection tools require further development to deal with the very complex dynamics that characterize inland waterways. The main objective of this work is to present the current state of the tools that have been developed in order to study and manage the inland waterways in a climate change context. The global framework that allows describing the link between these two management scales will be detailed. The water resource allocation approach can be based on three different techniques: the Constraint Satisfaction Problem (CSP), the quadratic optimization and the Markov Decision Process (MDP). The MDP-based approach will be emphasized due to its suitability to study complex systems with uncertainties, and its main advantages and drawbacks will be discussed and compared to the other techniques. Advanced control and fault detection tools require an in-depth knowledge of the inland waterway dynamics. Characteristics of navigation reaches, i.e. slope, resonance phenomenon, uncontrolled inputs and interconnections, need to be taken into account. A big effort has been made to improve the modeling step of the navigation reaches by considering the IDZ (Integrator Delay Zero) model. The designed tools are based on this accurate model, and they aim at improving the water level control of each reach of the inland waterways and at performing predictive maintenance strategies by detecting, isolating and forecasting faults on sensors and actuators (limnimeters, gates, locks, etc.). The designed management tools will be presented by considering a part of the real inland navigation network in the north of France. Perspectives and future developments will be described. Peer Reviewed Document type: Article

Abstract

International audience; Precise localization in dense urban areas is a challenging task for both mobile mapping and driver assistance systems. This paper proposes a strategy to use road markings as localization landmarks for vision based systems. First step consists in reconstructing a map of road marks. A mobile mapping system equipped with precise georeferencing devices is applied to scan the scene in 3D and to generate an ortho-image of the road surface. A RJMCMC sampler that is coupled with a simulated annealing method is applied to detect occurrences of road marking templates instanced from an extensible database of road mark patterns. The detected objects are reconstructed in 3D using the height information obtained from 3D points. A calibrated camera and a low cost GPS receiver are embedded on a vehicle and used as localization devices. Local bundle adjustment (LBA) is applied to estimate the trajectory of the vehicle. In order to reduce the drift of the trajectory, images are matched with the reconstructed road marks frequently. The matching is initialized by the initial poses that are estimated by LBA and optimized by a MCMC algorithm. The matching provides ground control points that are integrated in the LBA in order to refine the pose parameters. The method is evaluated on a set of images acquired in a real urban area and is compared with a precise ground-truth.