Papers by Sebastian Brechtel
Proceedings Ieee International Conference on Robotics and Automation, May 3, 2010
Bayesian Occupancy Filtering is an alternative
Discrete POMDPs of medium complexity can be approximately solved in reasonable time. However, mos... more Discrete POMDPs of medium complexity can be approximately solved in reasonable time. However, most applications have a continu-ous and thus uncountably infinite state space. We propose the novel concept of learning a discrete representation of the continuous state space to solve the integrals in con-tinuous POMDPs efficiently and generalize sparse calculations over the continuous space. The representation is iteratively refined as part of a novel Value Iteration step and does not depend on prior knowledge. Consistency for the learned generalization is asserted by a self-correction algorithm. The presented con-cept is implemented for continuous state and observation spaces based on Monte Carlo ap-proximation to allow for arbitrary POMDP models. In an experimental comparison it yields higher values in significantly shorter time than state of the art algorithms and solves higher-dimensional problems.
IEEE Intelligent Transportation Systems Magazine, 2015
ABSTRACT Estimating and predicting traffic situations over time is an essential capability for so... more ABSTRACT Estimating and predicting traffic situations over time is an essential capability for sophisticated driver assistance systems and autonomous driving. When longer prediction horizons are needed, e.g., in decision making or motion planning, the uncertainty induced by incomplete environment perception and stochastic situation development over time cannot be neglected without sacrificing robustness and safety. Building consistent probabilistic models of drivers interactions with the environment, the road network and other traffic participants poses a complex problem. In this paper, we model the decision making process of drivers by building a hierarchical Dynamic Bayesian Model that describes physical relationships as well as the driver's behaviors and plans. This way, the uncertainties in the process on all abstraction levels can be handled in a mathematically consistent way. As drivers behaviors are difficult to model, we present an approach for learning continuous, non-linear, context-dependent models for the behavior of traffic participants. We propose an Expectation Maximization (EM) approach for learning the models integrated in the DBN from unlabeled observations. Experiments show a significant improvement in estimation and prediction accuracy over standard models which only consider vehicle dynamics. Finally, a novel approach to tactical decision making for autonomous driving is outlined. It is based on a continuous Partially Observable Markov Decision Process (POMDP) that uses the presented model for prediction.
16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013), 2013
Estimating and predicting traffic situations over time is an essential capability for sophisticat... more Estimating and predicting traffic situations over time is an essential capability for sophisticated driver assistance systems or autonomous driving. When longer prediction horizons are needed, e.g., in decision making or motion planning, the uncertainty induced by incomplete environment perception and stochastic situation development over time cannot be neglected without sacrificing robustness and safety. Especially describing the unknown behavior of other traffic participants poses a complex problem. Building consistent probabilistic models of their manifold and changing interactions with the environment, the road network and other traffic participants by hand is errorprone. Further, the results could hardly cover the complete diversity of human behaviors. This paper presents an approach for learning continuous, non-linear, context dependent process models for the behavior of traffic participants from unlabeled observations. The resulting models are naturally embedded into a Dynamic Bayesian Network (DBN) that enables the prediction and estimation of traffic situations based on noisy and incomplete measurements. Using a hybrid state representation it combines discrete and continuous quantities in a mathematically sound way. Experiments show a significant improvement in estimation and prediction accuracy by the learned context dependent models over standard models, which only consider vehicle dynamics.
17th International IEEE Conference on Intelligent Transportation Systems (ITSC), 2014
This paper presents a generic approach for tactical decision-making under uncertainty in the cont... more This paper presents a generic approach for tactical decision-making under uncertainty in the context of driving. The complexity of this task mainly stems from the fact that rational decision-making in this context must consider several sources of uncertainty: The temporal evolution of situations cannot be predicted without uncertainty because other road users behave stochastically and their goals and plans cannot be measured. Even more important, road users are only able to perceive a tiny part of the current situation with their sensors because measurements are noisy and most of the environment is occluded. In order to anticipate the consequences of decisions a probabilistic approach, considering both forms of uncertainty, is necessary. We address this by formulating the task of driving as a continuous Partially Observable Markov Decision Process (POMDP) that can be automatically optimized for different scenarios. As driving is a continuous-space problem, the belief space is infinite-dimensional. We do not use a symbolic representation or discretize the state space a priori because there is no representation of the state space that is optimal for every situation. Instead, we employ a continuous POMDP solver that learns a good representation of the specific situation.
Informatik aktuell, 2009
Zusammenfassung In dieser Arbeit wird eine Erweiterung des zellbasierten Belegtheitsfilters BOFUM... more Zusammenfassung In dieser Arbeit wird eine Erweiterung des zellbasierten Belegtheitsfilters BOFUM 1 um Objektgruppen zum BOFUG (Bayesian Occupancy Filtering using Groups) vorgenommen. Diese ermöglicht die Einteilung und Klassifikation der Gruppenzugehörigkeit von Belegtheit, allein auf Basis von statischen Belegtheitsmessungen. Exemplarisch wird für Fußgänger und Fahrzeuge gezeigt, dass die Definition unterschiedlicher Dynamikmodelle ausreicht, um auf Objektinformationen zu schließen und das Filterergebnis nachhaltig zu verbessern. Die implizite Gruppeninferenz stellt einen ersten Schritt zur Vereinigung von Objekt-und Zellebene dar.
13th International IEEE Conference on Intelligent Transportation Systems, 2010
This paper presents a filter that is able to simultaneously estimate the behaviors of traffic par... more This paper presents a filter that is able to simultaneously estimate the behaviors of traffic participants and anticipate their future trajectories. This is achieved by recognizing the type of situation derived from the local situational context, which subsumes all information relevant for the drivers decision making. By explicitly taking into account the interactions between vehicles, it achieves a comprehensive situational understanding, inevitable for autonomous vehicles and driver assistance systems. This provides the necessary information for safe behavior decision making or motion planning. The filter is modeled as a Dynamic Bayesian Network. The factored state space, modeling the causal dependencies, allows to describe the models in a compact fashion and reduces the computational complexity of the inference process. The filter is evaluated in the context of a highway scenario, showing a good performance even with very noisy measurements. The presented framework is intended to be used in traffic environments but can be easily transferred to other robotic domains.
2010 IEEE International Conference on Robotics and Automation, 2010
Bayesian Occupancy Filtering is an alternative
2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC), 2011
This paper presents a method for high-level decision making in traffic environments. In contrast ... more This paper presents a method for high-level decision making in traffic environments. In contrast to the usual approach of modeling decision policies by hand, a Markov Decision Process (MDP) is employed to plan the optimal policy by assessing the outcomes of actions. Using probability theory, decisions are deduced automatically from the knowledge about how road users behave over time. This approach does neither depend on an explicit situation recognition nor is it limited to only a variety of situations or types of descriptions. Hence it is versatile and powerful. The contribution of this paper is a mathematical framework to derive abstract symbolic states from complex continuous temporal models encoded as Dynamic Bayesian Networks (DBN). For this purpose discrete MDP states are interpreted by random variables. To make computation feasible this space grows adaptively during planning and according to the problem to be solved.
2009 IEEE Intelligent Vehicles Symposium, 2009
Building a model of the environment is essential for mobile robotics. It allows the robot to reas... more Building a model of the environment is essential for mobile robotics. It allows the robot to reason about its sourroundings and plan actions according to its intentions. To enable safe motion planning it is vital to anticipate object movements. This paper presents an improved formulation for occupancy filtering. Our approach is closely related to the Bayesian Occupancy Filter (BOF) presented in . The basic idea of occupancy filters is to represent the environment as a 2dimensional grid of cells holding information about their state of occupancy and velocity. To improve the accuracy of predictions, prior knowledge about the motion preferences is used, derived from map data that can be obtained from navigation systems. In combination with a physically accurate transition model, it is possible to estimate the environment dynamics. Experiments show that this yields reliable estimates even for occluded regions.
Uploads
Papers by Sebastian Brechtel