Search

International audience; For an efficient integration of autonomous vehicles on roads, human-like reasoning and decision making in complex traffic situations are needed. One of the key factors to achieve this goal is the estimation of the future behavior of the vehicles present in the scene. In this work, we propose a new approach to predict the motion of vehicles surrounding a target vehicle in a highway environment. Our approach is based on an LSTM encoder-decoder that uses a social pooling mechanism to model the interactions between all the neighboring vehicles. The originality of our social pooling module is that it combines both local and non-local operations. The non-local multi-head attention mechanism captures the relative importance of each vehicle despite the inter-vehicle distances to the target vehicle, while the local blocks represent nearby interactions between vehicles. This paper compares the proposed approach with the state-of-the-art using two naturalistic driving datasets: Next Generation Simulation (NGSIM) and the new highD Dataset. The proposed method outperforms existing ones in terms of RMS values of prediction error, which shows the effectiveness of combining local and non-local operations in such a context.

Full text is available at http://ojs.c3sl.ufpr.br/ojs2/index.php/bcg/article/view/17003/11221; International audience; Over the past decade, laser terrestrial Mobile Mapping Systems (MMS) have been developed for the digital mapping of outdoor environments. While the applications of MMS are various (urban security, road control, virtual world, entertainment, etc.), one may imagine that for each application the system designs could be different. Hence, a comparative analysis of different designs may be useful to find the best solution adapted to each application. The objective of this paper is to propose a methodology to compare point-cloud data quality from different MMS designs by modifying spatial configuration of laser imaging system. For this methodology, we define several quality criteria such as precision, resolution, completeness. We illustrate this in the case of urban architecture digital mapping based on the use of a simulator.