Linked e-resources
Details
Table of Contents
Intro; Acknowledgements; Table of contents; List of Figures; List of Tables; Summary; Zusammenfassung; 1 Introduction, motivation and structure of the thesis; 1.1 Motivation of the thesis; 1.2 Thesis research questions; 1.3 Thesis contributions; 1.4 Thesis outline; 2 Preliminaries; 2.1 Introduction to motion planning; 2.2 Terminology; 2.3 Taxonomy of planning methods; 2.4 Motion planning for automated cars; 2.4.1 Diversity of driving environments; 2.4.2 Planning assessment criteria and driving modes; 2.5 Problem statement; 3 Related work
3.1 From advanced driver assistance systems towards automated cars3.1.1 Trajectory planning; 3.1.2 On-road swerve path generation; 3.1.3 Collision checking and avoidance; 3.2 Optimization methods; 3.3 Driving mode selection; 3.3.1 Multi-layered search space representations; 3.3.2 Hierarchical driving mode state machine; 3.3.3 End-to-end machine learning approaches for autonomous driving applications; 4 A framework for universal driving strategy planning; 4.1 Planning in high dimensional state space; 4.1.1 Identifying key components of sampling based planning
4.1.2 PSP integration into existing architecture4.1.3 Challenges and opportunities: Modeling a universal drive; 4.1.4 Non-functional requirements: safety, comfort and acceptance; 4.2 PSP world representations; 4.3 Visualizing high dimensional solutions; 5 Sampling-based planning in phase space; 5.1 Schematic of a complete planning sequence; 5.2 State space setup and exploration; 5.2.1 State propagation strategies; 5.2.2 Vehicle motion guided sampling; 5.2.3 Random state sampling; 5.3 Trajectory planning; 5.3.1 Generating path segments with clothoids; 5.3.2 Generating velocity profiles
5.4 Trajectory optimization5.4.1 Extended planning horizon with multiple layers; 5.4.2 Directed graph optimization using dynamic programming; 5.4.3 Other PSP optimization methods; 5.5 Rules and heuristics; 5.5.1 Simplification of the state space; 5.5.2 How to choose a planning horizon length?; 6 A universal approach for driving strategies; 6.1 Modeling driving behaviors: Cost functions; 6.1.1 State transition costs; 6.1.2 Optimizing for a universal driving experience; 6.2 Situation awareness: Observing the most relevant things; 6.2.1 Optimizing the vehicle's sensor coverage
6.2.2 Interpretation of a sensor coverage cost map6.3 Simulation experiments; 6.3.1 Validation of driving strategy generation; 6.3.2 Evaluation of smart positioning; 6.3.3 PSP performance analysis; 7 Modeling ego motion uncertainty; 7.1 Why modeling uncertainty matters; 7.2 Ego motion uncertainty; 7.2.1 A post-processing planning extension; 7.2.2 State estimation and model correction; 7.2.3 Re-evaluate trajectory collision probability; 7.2.4 Collision detection algorithm; 7.3 Simulation experiments; 8 Summary, outlook and contributions; References; A Supplemental material
3.1 From advanced driver assistance systems towards automated cars3.1.1 Trajectory planning; 3.1.2 On-road swerve path generation; 3.1.3 Collision checking and avoidance; 3.2 Optimization methods; 3.3 Driving mode selection; 3.3.1 Multi-layered search space representations; 3.3.2 Hierarchical driving mode state machine; 3.3.3 End-to-end machine learning approaches for autonomous driving applications; 4 A framework for universal driving strategy planning; 4.1 Planning in high dimensional state space; 4.1.1 Identifying key components of sampling based planning
4.1.2 PSP integration into existing architecture4.1.3 Challenges and opportunities: Modeling a universal drive; 4.1.4 Non-functional requirements: safety, comfort and acceptance; 4.2 PSP world representations; 4.3 Visualizing high dimensional solutions; 5 Sampling-based planning in phase space; 5.1 Schematic of a complete planning sequence; 5.2 State space setup and exploration; 5.2.1 State propagation strategies; 5.2.2 Vehicle motion guided sampling; 5.2.3 Random state sampling; 5.3 Trajectory planning; 5.3.1 Generating path segments with clothoids; 5.3.2 Generating velocity profiles
5.4 Trajectory optimization5.4.1 Extended planning horizon with multiple layers; 5.4.2 Directed graph optimization using dynamic programming; 5.4.3 Other PSP optimization methods; 5.5 Rules and heuristics; 5.5.1 Simplification of the state space; 5.5.2 How to choose a planning horizon length?; 6 A universal approach for driving strategies; 6.1 Modeling driving behaviors: Cost functions; 6.1.1 State transition costs; 6.1.2 Optimizing for a universal driving experience; 6.2 Situation awareness: Observing the most relevant things; 6.2.1 Optimizing the vehicle's sensor coverage
6.2.2 Interpretation of a sensor coverage cost map6.3 Simulation experiments; 6.3.1 Validation of driving strategy generation; 6.3.2 Evaluation of smart positioning; 6.3.3 PSP performance analysis; 7 Modeling ego motion uncertainty; 7.1 Why modeling uncertainty matters; 7.2 Ego motion uncertainty; 7.2.1 A post-processing planning extension; 7.2.2 State estimation and model correction; 7.2.3 Re-evaluate trajectory collision probability; 7.2.4 Collision detection algorithm; 7.3 Simulation experiments; 8 Summary, outlook and contributions; References; A Supplemental material