Thèse soutenue

FR  |  
EN
Auteur / Autrice : Meng Keat Tay
Direction : Christian Laugier
Type : Thèse de doctorat
Discipline(s) : Informatique
Date : Soutenance en 2009
Etablissement(s) : Grenoble INPG

Mots clés

FR

Mots clés contrôlés

Résumé

FR  |  
EN

The development of autonomous vehicles garnered an increasing amount of attention in recent years. The interest for automotive industries is to produce safer and more user friendly cars. A common reason behind most traffic accidents is the failure on the part of the driver to adequately monitor the vehicle's surroundings. In this thesis we address the problem of estimating the collision risk for a vehicle for the next few seconds in urban traffic conditions. Current commercially available crash warning systems are usually equipped with radar based sensors on the front, rear or sides to measure the velocity and distance to obstacles. The algorithms for determining the risk of collision are based on variants of time-to-collision (TTC). However, it might be misleading in situations where the roads are curved and the assumption that motion is linear does not hold. In these situations, the risk tends to be underestimated. Furthermore, instances of roads which are not straight can be commonly found in urban environments, like the roundabout or cross junctions. An argument of this thesis is that simply knowing that there is an object at a certain location at a specific instance in time does not provide sufficient information to asses its safety. A framework for understanding behaviours of vehicle motion is indispensable. In addition, environmental constraints should be taken into account especially for urban traffic environments. A bottom up approach towards the final goal of constructing a model to estimate the risk of collision for a vehicle is presented. The simpler case of “free” motion is first presented. The thesis then proposes to take collision risk estimation further by being more “environmentally aware” where environmental structures and constraints are explicitly taken into account for urban traffic scenarios. This thesis proposes a complete probabilistic model motion at the trajectory level based the Gaussian Process (GP). Its advantage over current methods is that it is able to express future motion independently of state space discretization. Driving behaviours are modelled with a variant of the Hidden Markov Model. The combination of these two models provides a complete probabilistic model for vehicle evolution in time. Additionally a general method of probabilistically evaluating collision risk is presented, where different forms of risk values with different semantics can be obtained, depending on its applications.