Bayesian Environment Representation, Prediction, and Criticality Assessment for Driver Assistance Systems
Zusammenfassung
This work deals with the questions i) how to represent the driving environment in an environment model, ii) how to obtain such a representation, and iii) how to predict the traffic scene for criticality assessment. Bayesian inference provides the common framework of all designed methods. First, Parametric Free Space (PFS) maps are introduced, which compactly represent the vehicle environment in form of relevant, drivable free space while suppressing irrelevant details of common occupancy grids. They are obtained by a novel method for grid mapping and tracking in dynamic environments. In addition, a maneuver-based, long-term trajectory prediction and criticality assessment system is introduced together with the Time-To-Critical-Collision-Probability (TTCCP) metric for uncertain, multi-object driving situations. Finally, the Advanced Driver Assistance System (ADAS) PRORETA 3 is described, which constitutes an integrated approach to collision avoidance and vehicle automation.
...
Schlagworte
Matthias Schreier Advanced Driver Assistance Systems Bayesian Inference Collision Avoidance Criticality Assessment Environment Representation Multiple Model Filtering Occupancy Grid Map Parametric Free Space Map Target Tracking Trajectory Prediction- Kapitel Ausklappen | EinklappenSeiten
- 207–211 8 Summary and Outlook 207–211
- 221–254 Bibliography 221–254
8 Treffer gefunden
- „... , while environment representation-related algorithms have additionally been fully implemented and tested ...” „... proprioceptive sensors. Environment knowledge is not taken into account. Therefore, so-called Advanced Driver ...” „... choice and development of an adequate environment model, i.e. a suitable representation of the driving ...”
- „... 6 2 Environment Representations for ADAS The present chapter first gives an overview of common ...” „... metric environment representations and compares them with respect to their suitability for future ADAS ...” „... . Subsequently, the proposed representation is introduced, which combines dynamic object maps with a novel ...”
- „... obtain such a representation, and iii) how to predict the future traffic scene evolution for proper ...” „... criticality assessment. At the beginning of this thesis, different metric environment representations known ...” „... future ADAS in Chapter 2. Based on the found shortcomings, a novel representation has been derived, which ...”
- „... have seen how to estimate and represent the current state of the environment. This representation forms ...” „... Several seconds Required environment knowledge Low High High Abstraction level Low Low – Medium High ...” „... knowledge about driving lanes or road boundaries as realized in [162,192,200]. These methods allow greater ...”
- „... environment representation. 5.1 Introduction and Motivation The PFS map as the proposed representation for ...” „... continuous, 2D bird’s-eye view representation of the local static environment around the ego vehicle, which ...” „... Fig. 5.1. PFS mapping is therefore also a method of free space detection. Knowledge about drivable ...”
- „... representation, trajectory planning, and Human Machine Interface (HMI) is given. Afterwards, a variety of driving ...” „... upon the same holistic environment representation, the same integrated trajectory planning, and the ...” „... (HMI), Matthias Schreier (Environment Representation and Prediction), Felix Lotz (System Architecture ...”
- „... environment representation: target tracking and occupancy grid mapping – both presented subsequently. 3.1 ...” „... sequence z1:k = {z1, . . . ,zk−1,zk}. In this pdf, the complete probabilistic knowledge about the state is ...” „... subsumed. If a relationship between states and measurements is known and prior knowledge about states is ...”
- „... Compact Medium Level Representation of the 3D-World. In DAGM Symposium on Pattern Recognition, Jena ...” „... Spatial Databases with Noise. In Proc. of the International Conference on Knowledge Discovery and Data ...” „... , Gold Coast, Australia, June 2013. [145] J. Leal. Stochastic Environment Representation. PhD thesis ...”