The Handbook of Intelligent Vehicles provides a complete coverage of the fundamentals, new technologies, and sub-areas essential to the development of intelligent vehicles; it also includes advances made to date, challenges, and future trends. Significant strides in the field have been made to date; however, so far there has been no single book or volume which captures these advances in a comprehensive format, addressing all essential components and subspecialties of intelligent vehicles, as this book does. Since the intended users are engineering practitioners, as well as researchers and graduate students, the book chapters do not only cover fundamentals, methods, and algorithms but also include how software/hardware are implemented, and demonstrate the advances along with their present challenges. Research at both component and systems levels are required to advance the functionality of intelligent vehicles. This volume covers both of these aspects in addition to the fundamentals listed above.

We provide a sensor fusion framework for solving the problem of joint egomotion and road geometry estimation. More specifically we employ a sensor fusion framework to make systematic use of the measurements from a forward looking radar and camera, steering wheel angle sensor, wheel speed sensors and inertial sensors to compute good estimates of the road geometry and the motion of the ego vehicle on this road. In order to solve this problem we derive dynamical models for the ego vehicle, the road and the leading vehicles. The main difference to existing approaches is that we make use of a new dynamic model for the road. An extended Kalman filter is used to fuse data and to filter measurements from the camera in order to improve the road geometry estimate. The proposed solution has been tested and compared to existing algorithms for this problem, using measurements from authentic traffic environments on public roads in Sweden. The results clearly indicate that the proposed method provides better estimates.

This paper presents an extended target tracking framework which uses polynomials in order to model extended objects in the scene of interest from imagery sensor data. State-space models are proposed for the extended objects which enables the use of Kalman filters in tracking. Different methodologies of designing measurement equations are investigated. A general target tracking algorithm that utilizes a specific data association method for the extended targets is presented. The overall algorithm must always use some form of prior information in order to detect and initialize extended tracks from the point tracks in the scene. This aspect of the problem is illustrated on a real life example of road-map estimation from automotive radar reports along with the results of the study.

Mapping stationary objects is essential for autonomous vehicles and many autonomous functions in vehicles. In this contribution the probability hypothesis density (PHD) filter framework is applied to automotive imagery sensor data for constructing such a map, where the main advantages are that it avoids the detection, the data association and the track handling problems in conventional multiple-target tracking, and that it gives a parsimonious representation of the map in contrast to grid based methods. Two original contributions address the inherent complexity issues of the algorithm: First, a data clustering algorithm is suggested to group the components of the PHD into different clusters, which structures the description of the prior and considerably improves the measurement update in the PHD filter. Second, a merging step is proposed to simplify the map representation in the PHD filter. The algorithm is applied to multi-sensor radar data collected on public roads, and the resulting map is shown to well describe the environment as a human perceives it.

This paper presents a Gaussian-mixture implementation of the phd filter for tracking extended targets. The exact filter requires processing of all possible measurement set partitions, which is generally infeasible to implement. A method is proposed for limiting the number of considered partitions and possible alternatives are discussed. The implementation is used on simulated data and in experiments with real laser data, and the advantage of the filter is illustrated. Suitable remedies are given to handle spatially close targets and target occlusion.

This paper presents a framework for tracking extended targets which give rise to a structured set of measurements per each scan. The concept of a measurement generating point (MGP) which is defined on the boundary of each target is introduced. The tracking framework contains an hybrid statespace where MGP:s and the measurements are modeled by random finite sets and target states by random vectors. The target states are assumed to be partitioned into linear and nonlinear components and a Rao-Blackwellized particle filter is used for their estimation. For each state particle, a probability hypothesis density (PHD) filter is utilized for estimating the conditional set of MGP:s given the target states. The PHD kept for each particle serves as a useful means to represent information in the set of measurements about the target states. The early results obtained show promising performance with stable target following capability and reasonable shape estimates.

Measurements of individual wheel speeds and absolute position from a global navigation satellite system (gnss) are used for high-precision estimation of vehicle tire radii in this work. The radii deviation from its nominal value is modeled as a Gaussian process and included as noise components in a vehicle model. The novelty lies in a Bayesian approach to estimate online both the state vector of the vehicle model and noise parameters using a marginalized particle filter. No model approximations are needed such as in previously proposed algorithms based on the extended Kalman filter. The proposed approach outperforms common methods used for joint state and parameter estimation when compared with respect to accuracy and computational time. Field tests show that the absolute radius can be estimated with millimeter accuracy, while the relative wheel radius on one axle is estimated with submillimeter accuracy.