login
english version rss feed
Detailed view PhD thesis
Institut National Polytechnique de Grenoble - INPG (2009-06-08), Christian Laugier (Dir.)
Attached file list to this document: 
PDF
main.pdf(4.8 MB)
ANNEX
presentazione.pdf(4.3 MB)
IROS1_results.mp4(30.4 MB)
gp_results.avi(679.4 KB)
simulator_results.mp4(9.3 MB)
1_prrt_animation.avi(2.6 MB)
Navigation autonome en environnement dynamique utilisant des modèles probabilistes de perception et de prédiction du risque de collision.
Chiara Fulgenzi1

La navigation autonome en environnement dynamique représente encore un défi important pour la robotique moderne. Dans cette thèse nous abordons le problème de la prise en compte explicite des incertitudes liées à la perception et à la prédiction de l'état d'un environnement dynamique inconnu pour la decision sur les mouvements futures du robot. Nous proposons d'abord un algorithme réactif basé sur l'intégration de l'extension probabiliste de la méthode Velocity Obstacle et d'une grille d'occupation dynamique. Nous presentons ensuite une nouvelle extension probabiliste de l'algorithme RRT et nous l'utilisons pour une approche de navigation ”anytime” : les décisions du robot sont mises a jour avec les observations les plus récentes. Nous considérons d'abord le cas de prédiction à court terme et ensuite le cas de prédiction a moyen terme, basée sur les trajectoires typiques des obstacles, apprises a priori.
1:  INRIA Grenoble Rhône-Alpes / LIG Laboratoire d'Informatique de Grenoble - E-MOTION
navigation – environnement dynamique – incertitude – prediction probabiliste – risque de collision

Autonomous navigation in dynamic uncertain environment using probabilistic models of perception and collision risk prediction.
In this document we address the problem of autonomous navigation in dynamic unknown environ- ments. The key of the problem is to guarantee safety for all the agents moving in the space (people, vehicles and the robot itself) while moving toward a predefined goal. In contrast with static or controlled environments, high dynamic environments present many difficult issues: the detection and tracking of moving obstacles, the prediction of the future state of the world and the on-line motion planning and navigation. We moved our research starting from the fact that the decision about motion must take into account the limits of sensor perception, the velocity and future trajectory of the moving obstacles and that it must be related with the on-line updating of the world perception. Our approach is based on the use of probabilistic frameworks to represent the uncertainty about the static environment and the dynamic obstacles and we have developed decision methods that take explicitly into account such information for the autonomous navigation task. At first we focused our attention on reactive approaches. The developed approach is based on the integration between a probabilistic extension of the Velocity Obstacle framework within a dynamic occupancy grid (Bayesian Occupancy Filter). The dynamic occupancy grid gives a probabilistic and explicit representation of the perception limits and of the model error and noise while the Probabilistic Velocity Obstacles compute a probability of collision in time. The probability of collision and hence the choice of the next control, take into account limited sensor range, occlusions, obstacles shape and velocity estimation errors. Simulation results show the robot adapting its behaviour to different conditions of perception, avoiding static and moving obstacles and moving toward the goal. In the second part of the document we move toward more complex strategies, integrating a Partial Motion Planning algorithm with probabilistic representation of the environment and collision risk prediction. We propose a novel probabilistic extension of the well known Rapidly-exploring Random Trees framework and we integrate this search algorithm into a partial planning anytime approach, updating on-line the decisions of the robot with the last observations. We consider at first the case of a short-term prediction based on a classic Multi-Target-Tracking algorithm. Secondly, we consider the case of a longer term prediction based on a priori known typical patterns. We compare two kinds of patterns representation: the Hidden Markov Model representation and the continuous Gaussian Processes representation. The search and planning algorithm is adapted to these different kinds prediction and simulation results for navigation among multiple moving obstacles are shown.
navigation – dynamic environment – uncertainty – probabilistic prediction – collision risk

all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...