Catalogue : Details

Robin Schubert

Integrated Bayesian Object and Situation Assessment for Lane Change Assistance

ISBN:

978-3-8440-0322-2

Series:

Forschungsberichte der Professur Nachrichtentechnik
Herausgeber: Prof. Dr.-Ing. Gerd Wanielik
Chemnitz

Volume:

Keywords:

Advanced Driver Assistance Systems; Lane Change Assistant; Data Fusion; Multi Object Tracking; Situation Assessment; Bayesian Networks; Decision Networks; Unscented Kalman Filter; Adaptive Likelihood Nodes; Meta Model Filter

Type of publication:

Thesis

Language:

English

Pages:

224 pages

Figures:

64 figures

Weight:

333 g

Format:

21 x 14,8 cm

Binding:

Paperback

Price:

49,80 € / 99,60 SFr

Published:

August 2011

Buy:

Download:

Available PDF-Files for this title:

You need the Adobe Reader, to open the files. Here you get help and information, for the download.

These files are not printable.


	Document		Abstract
	Type		PDF
	Costs		free
	Action		Display of file - 64 kB (65098 Byte)
	Action		Download of file - 64 kB (65098 Byte)


	Document		Document
	Type		PDF
	Costs		37,35 EUR
	Action		Purchase in obligation and display of file - 1,9 MB (1953709 Byte)
	Action		Purchase in obligation and download of file - 1,9 MB (1953709 Byte)


	Document		Table of contents
	Type		PDF
	Costs		free
	Action		Display of file - 110 kB (112504 Byte)
	Action		Download of file - 110 kB (112504 Byte)

User settings for registered users

You can change your address here or download your paid documents again.

User:	Not logged in.
Actions:	Login / Register Forgotten your password?

Recommendation:

You want to recommend this title?

Review copy:

Here you can order a review copy.

Link:

You want to link this page? Click here.

Export citations:

Text
BibTex
RIS

Abstract:

In-vehicle advanced driver assistance systems are based on the perception and interpretation of the vehicle's environment. These tasks are often based on probabilistic object and situation assessment algorithms such as Bayes filters or Bayesian networks. However, though these techniques are subject to intensive research, the interface between them has not yet been sufficiently addressed.
Thus, the main research objective of this work is to provide a generic, bidirectional, probabilistic interface between object and situation assessment in order to allow a unified view on these tasks. For that purpose, it is firstly shown that by a new technique called adaptive likelihood nodes, uncertainties from the probabilistic perception of the vehicle's surrounding can be directly entered into a Bayesian network in order to influence the situation assessment. In addition, it is investigated how uncertain knowledge about the current situation can be exploited in order to support the tracking performance. For that, an extension of the interacting multiple model filter is proposed which is called the meta model filter. This technique models possible maneuvers of vehicles using a Bayesian network in order to adaptively adjust the transition probabilities of the interacting multiple model filter according to the current situation. With this approach, a situation-dependent multiple model filtering can be achieved.
The benefits of these theoretical contributions are demonstrated on the example of an advanced driver assistance system which supports lane change maneuvers on highways. The aim of this lane change assistant is to sense the surrounding of the host vehicle in order to assess the current traffic situation and automatically determine optimal lane change maneuver decisions. This work describes all data fusion components of this system including probabilistic filtering, situation assessment, and decision taking. It is shown how by using both of the newly proposed concepts – adaptive likelihood nodes and the meta model filter – a unified Bayesian data processing chain from the sensors to the final maneuver decision can be achieved. Finally, the performance of the lane change assistant and the benefits of the proposed techniques are analyzed using both simulated and empirical data.