Zusammenfassung
Driver assistance systems have increasingly relied on more sensors for new functions. As advanced driver assistance system continue to improve towards automated driving, new methods are required for processing the data in an efficient and economical manner from the sensors for such complex systems. In this thesis, an environment model approach for the detection of dynamic objects is presented in order to realize an effective method for sensor data fusion. A scalable high-level fusion architecture is developed for fusing object data from several sensors in a single system. The developed high-level sensor data fusion architecture and its algorithms are evaluated using a prototype vehicle equipped with 12 sensors for surround environment perception. The work presented in this thesis has been extensively used in several research projects as the dynamic object detection platform for automated driving applications on highways in real traffic.
Contents
Abbreviations VIII
List of Symbols X
Abs...
Schlagworte
Sensor Fusion Perception Autonomous Driving Driver Assistance Track-to-Track / Fusion Tracking Object Detection- 1–26 1 Introduction 1–26
- 116–132 6 Classification 116–132
- 133–151 7 Evaluation 133–151
- 172–202 References 172–202
8 Treffer gefunden
- „... vehicle-to-vehicle and vehicle-to-infrastructure (Car2X) communication technology. A prototype vehicle developed by ...” „... shown in (d). 134 7.2 Overtaking Maneuver with Ground Truth H vtarget vhost x y Figure 7.2: Illustration ...” „... (front/rears) Laser scanner (side) Laser scanner (front/rear) Fusion (b) 0 0.5 1.0 1.5 2.0 0 5 10 15 20 25 |v x ...”
- „... ., “Car2X-Based Perception in a High-Level Fusion Architecture for Cooperative Perception Systems,” in ...” „... Systems Conference, The Hague, Netherlands, October 2013, pp. 1408–1415. [2] AdaptiVe. [Online]. Available ...” „... : Audi A7 Piloted Driving Car Completes 550-mile Automated Test Drive. [Online]. Available: https ...”
- „... systems such as ACC and Forward Collision 2 1.2 Automation in Driver Assistance and Safety Systems Warning ...” „... with respect to their level of automation is given in the following section. 1.2 Automation in Driver ...” „... Introduction Sensor 1 Sensor 2 . . . Sensor N Application 1 . . . Application N (a) Sensor 1 Sensor 2 ...”
- „... pG,vehf p S,veh f pG,vehf1 pG,vehf2 pS,vehf1 pS,vehf2 Setup Association State Vector xGa x S a Perform ...” „... , pG(∃x) and pS(∃x) (see Chapter 5). From the χ2 inverse cumulative distribution function, a term based on ...” „... the existence probabilities are added onto the statistical distance d2G,S(p(∃x)) = F−1χ2nxa (1− p G(∃x ...”
- „... Car, 2,334 Truck and 4,398 Motorcycle). After empirical analysis of the training data set, it was ...” „... determined that the width, w, and range r, where r = √ x2 + y2, were the attributes that best separate the ...” „... 0 50 100 150 200 0 0.5 1.0 1.5 2.0 2.5 3.0 w (m) r (m ) Car Truck Motorcycle Figure 6.1 ...”
- „... 50 60 Cycle # p (∃ x ) 1 missed detection 2 missed detections several missed detections Generalized ...” „... quality: ptrackd (x̂k|k) = 1− P{χ2(x;Knz) ≤ K ̄z̃(k)}. (5.38) The larger the inconsistency of the track ...” „... existence probabilities from many sensors at the fusion-level is presented in Section 5.2. At the ...”
- „... , . . . , ON} (2.3) where Oi is a a single object in the list, defined as Oi = {x̂,P, d̂,dσ2 , p(∃x), c, f ...” „... object dimension vector, dσ2 the dimension uncertainty vector, p(∃x) is the probability of existence, c ...” „... vector for the object model is defined in this thesis as x = [ x y vx vy ax ay ψ ψ̇ ]′ (2.5) where x and ...”
- „... + ỹ(k) 2 i (4.40) where x̃(k) is the error in the x-direction and ỹ(k) is the error in the y-direction ...” „... of the 80 4.3 Track-to-Track Fusion with the Common State H x y (a) 0 1 2 -1 -2 5 10 15 Time (s) A cc ...” „... · ( 1− Pdmax 2 [ 1 + erf ( xdi − dS σSd √ 2 )]) , xdi ≤ dS −p(mdi ) 1 + e−k(x d i− d S+dmax 2 ) + p(mdi ...”