Shared transportation systems in urban environments are the current trend to improve transportation problems toward eco-friendly cities. As an example, Vélib bike sharing system in Paris allows users to have bikes available all around the city. However, the associate problem of these transportation systems is mainly related to the relocation strategies in order to always have availability in all the stations. Specifically for Vélib, operators manually displace more than 3000 bikes daily using trucks, corresponding to 3% of the total fleet motion. For car-sharing systems, relocation strategies require more sophisticated techniques for their implementation on cities. As automatic relocation cannot be achieved for legal reasons, an alternative is to get a leader vehicle, driven by a human, which comes to pick up and drop off vehicles over the stations. The VALET project proposes a novel approach for solving car-sharing vehicles redistribution problem using vehicle platoons guided by professional drivers. An optimal routing algorithm is in charge of defining platoons drivers’ routes to the parking areas where the followers are parked in a complete automated mode. The main idea of VALET is to retrieve vehicles parked randomly on the urban parking network by users. These parking spaces may be in electric charging stations (if we have a fleet of electric vehicles), parking for car sharing vehicles (e.g. Autolib in Paris) or in regular parking places. As for the vehicles, they may be car-sharing vehicles, rental cars, future automated taxis, etc. Once the vehicles are collected and guided in a platooning mode, the objective is then to guide them to their allocated parking area or to their respective parking lots. Then each vehicle is assigned a parking place into which it has to park in an automated mode. Furtherfore, VALET project proposes to endow autonomous vehicles with smart behaviors (cooperation, negotiation, socially acceptable movements) that better suit complex urban situations (with the presence of pedestrians, man-driven vehicles and other autonomous vehicles). It will integrate models of human behaviors (pedestrian and/or drivers), proxemics (human management of space) and traffic rules, as well as smart navigation strategies that will manage interdependent behaviors of road users and of cybercars. The final system will be tested on real demonstrations in an urban environment. The starting point of VALET project is the different prototype autonomous vehicles that partners already have (4-5 vehicles).