Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top

2018 | Book

Introduction, motivation and structure of the thesis Read chapter Read first chapter

Planning Universal On-Road Driving Strategies for Automated Vehicles

Author: Steffen Heinrich

Publisher: Springer Fachmedien Wiesbaden

Book Series : AutoUni – Schriftenreihe

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Login to get access
insite
SEARCH

About this book

Steffen Heinrich describes a motion planning system for automated vehicles. The planning method is universally applicable to on-road scenarios and does not depend on a high-level maneuver selection automation for driving strategy guidance. The author presents a planning framework using graphics processing units (GPUs) for task parallelization. A method is introduced that solely uses a small set of rules and heuristics to generate driving strategies. It was possible to show that GPUs serve as an excellent enabler for real-time applications of trajectory planning methods. Like humans, computer-controlled vehicles have to be fully aware of their surroundings. Therefore, a contribution that maximizes scene knowledge through smart vehicle positioning is evaluated. A post-processing method for stochastic trajectory validation supports the search for longer-term trajectories which take ego-motion uncertainty into account.

About the Author

Steffen Heinrich has a strong background in robotics and artificial intelligence. Since 2009 he has been developing algorithms and software components for self-driving systems in research facilities and for automakers in Germany and the US.

Table of Contents

Frontmatter
Chapter 1. Introduction, motivation and structure of the thesis
Abstract
The vision of self-driving vehicles has reached the mainstream as it promises nothing less than the next mobility revolution. The potential benefits of automating the most popular transportation vehicle include reduction of road fatalities and CO2 emissions, an improvement in road utilization and free time for the person who would previously have been driving the vehicle in high automation systems. Automated driving is being discussed by society, governments, regulators, customers and potential mobility service consumers. In addition to traditional car makers and automotive suppliers, the development is also being led by IT companies.
Steffen Heinrich
Chapter 2. Preliminaries
Abstract
This Chapter provides the theoretical background and is to be understood as a preface to the ideas contained in, and the contributions made by this thesis, which are presented later. First, an introduction to terms and nomenclature is given. Second, strict distinctions of automated driving as a special case of motion planning are emphasized. Third, a categorization of basic driving maneuvers for passenger cars is undertaken and definitions for each group are given. Finally, the general problem statement is presented.
Steffen Heinrich
Chapter 3. Related work
Abstract
This chapter gives an overview of the current state of the art in motion planning. It summarizes key aspects of publications that are relevant to the field. Additionally, it presents literature from other robotic domains. In the hierarchical model of sense, plan and act planning systems for automated vehicles operate in the latter two phases. Donges [30] transfers this model into the context of driving tasks and maneuvering and established three categories: navigation, motion planning and stabilization.
Steffen Heinrich
Chapter 4. A framework for universal driving strategy planning
Abstract
This chapter presents the overall planning philosophy of this thesis. In Section 4.1 the integration into the existing software ecosystem is outlined and it being a valuable source with respect to perception and control systems. The first research question of this thesis is about the benchmarking of planning systems. Exchangeability in defined stages of the planning process is therefore the main driver of the framework’s architecture.
Steffen Heinrich
Chapter 5. Sampling-based planning in phase space
Abstract
The architecture of the PSP framework was introduced in Chapter 4. In this chapter, we want to focus on the implementations and solutions developed. It is begins with a detailed overview of a complete planning sequence in Section 5.1. this is followed by the three planning stages of the PSP modules: State space exploration (Section 5.2), trajectory generation (Section 5.3) and optimization (Section 5.4). The trajectory generation is based on related work by Kelly and Nagy.
Steffen Heinrich
Chapter 6. A universal approach for driving strategies
Abstract
All planners within PSP operate in one overall state (drive). The intention is to have no driving behavior state machine (or automaton) that guides the planning process on a higher level. Hence, every decision is made within the optimization process.
Steffen Heinrich
Chapter 7. Modeling ego motion uncertainty
Abstract
In Chapters 4 to 6, the full planning stack was introduced and evaluated. In this chapter, a post-processing method is presented which compensates for ego motion uncertainty. So far, it has been assumed that the optimized trajectory would be executed by the vehicle’s control and actuator systems with no or only minor deviations. The trajectory actually driven can differ far more than that, however. Even though the planning results are still completely safe, these circumstances would cause frequent re-initializations.
Steffen Heinrich
Chapter 8. Summary, outlook and contributions
Abstract
The objective of this thesis has been to generate universal driving strategies to minimize the need for multiple special purpose planning methods. A proposal for a centralized decision-making entity has been provided as well as benchmarking criteria. The thesis provides a set of simple but adaptable driving behaviors. The implementation has been done for CPU and GPU platforms and experiments on both systems have been evaluated.
Steffen Heinrich
Backmatter
Metadata
Title
Planning Universal On-Road Driving Strategies for Automated Vehicles
Author
Steffen Heinrich
Copyright Year
2018
Electronic ISBN
978-3-658-21954-3
Print ISBN
978-3-658-21953-6
DOI
https://doi.org/10.1007/978-3-658-21954-3