Search our Publications
Latest Publications
Andreas Johannes Richter, Mario Botsch, Stefan Menzel , "Evolvability of Representations in Complex System Engineering: a Survey", 2015 IEEE Congress on Evolutionary Computation (CEC2015), 2015.
AbstractThe choice of a good representation for the optimization of human made systems is a complicated task. It covers the issue of, e.g., parametrization type, parameter quantity and placement, or physical modeling. The representation’s quality has a tremendous influence in the optimization procedure, e.g., regarding optimization speed and solution quality. On the other hand the representation is influenced by the used optimization routine and the give...
Download Bibtex file
Daniel Sieger, Stefan Menzel, Mario Botsch , "On Shape Deformation Techniques for Simulation-based Design Optimization", New Challenges in Grid Generation and Adaptivity for Scientific Computing, pp. 281-303, 2015.
AbstractWe present an in-depth analysis and benchmark of shape deformation techniques for their use in simulation-based design optimization scenarios. We first introduce classical free-form deformation, its direct manipulation variant, as well as deformations based on radial basis functions. We compare these techniques in a set of representative synthetic benchmarks, including computational performance, numerical robustness, quality, and adaptivity. Fina...
Download Bibtex file
Julian Eggert, Florian Damerow, Stefan Klingelschmitt , "The Foresighted Driver Model", Intelligent Vehicles Symposium (IV) 2015, 2015.
AbstractThe Intelligent Driver Model (IDM) is a mesoscopic, time continuous car following model for the simulation of freeway and urban traffic. Its popularity is grounded in its simplicity (it consists of a single differential equation) and its capacity to describe from single vehicle to traffic jam behavior. Nevertheless, it lacks a series of properties that would be desirable for more realistic agent models. In this paper, we propose as an alternative...
Download Bibtex file
Florian Damerow and Julian Eggert , "Optimal Kinodynamic Risk Aversive Behavior Planning using Predictive Risk Maps", Intelligent Vehicles Symposium (IV) 2015, 2015.
AbstractThis paper addresses the problem of future behavior evaluation and planning for ADAS in general traffic situations. Complex traffic situations require the estimation of future behavior alternatives in terms of predictive risks. Based on the predicted future dynamics of traffic scene entities, we present an approach where a continuous, probabilistic model for future risks is used to build so-called predictive risk maps. These maps indicate how ris...
Download Bibtex file
Stefan Klingelschmitt, Florian Damerow, Julian Eggert , "Managing the Complexity of Inner-City Scenes: An Efficient Situation Hypotheses Selection Scheme", Intelligent Vehicles Symposium (IV) 2015, 2015.
AbstractDue to the large number and the high variability of possible traffic situations, intersections are among the most accident-prone spots in inner-city traffic. To reliably assist the driving tasks elaborated risk assessment systems are needed. Current approaches are mainly based on the prediction of possible future trajectories of the involved traffic participants. However, considering the variability and combinatorics of intersection-relate...
Download Bibtex file
Jens Schmüdderich, Sven Rebhan, Thomas H Weisswange, Marcus Kleinehagenbrock, Robert Kastner, Morimichi Nishigaki, Shunsuke Kusuhara , "A novel approach to driver behavior prediction using scene context and physical evidence for intelligent Adaptive Cruise Control (i-ACC)", Future Active Safety Technology Towards zero traffic accidents (FAST-zero), 2015.
AbstractConventional driver assistance systems react to another traffic participant’s behavior as soon as it becomes apparent. In other words, they react as soon as the host vehicle’s sensors detect the start of another vehicle’s change of behavior. ACC systems, for example, react to a cutting-in vehicle when the sensors measure a significant lateral motion or displacement. However, a change of behavior is usually the effect of adapting to the current dr...
Download Bibtex file
Simon Manschitz, Jens Kober, Michael Gienger, Jan Peters , "Learning Movement Primitive Attractor Goals and Sequential Skills from Kinesthetic Demonstrations", Robotics and Autonomous Systems, vol. 74, pp. 97–107, 2015.
AbstractWe present an approach for learning sequential robot skills through kinesthetic teaching. Finding the transitions between consecutive movement primitives is treated as multiclass classification problem. We show how the goal parameters of linear attractor movement primitives can be learned from the demonstrations and how the observed movement primitive order can help to improve the movement reproduction. The improvement is achieved by restrict...
Download Bibtex file
Simon Manschitz, Jens Kober, Michael Gienger, Jan Peters , "Probabilistic Progress Prediction and Sequencing of Concurrent Movement Primitives", International Conference on Intelligent Robots and Systems (IROS), 2015.
AbstractConcurrent execution of separate movement primitives is a crucial ability of humans needed by anthropomorphic robots. Concurrency is, for example, required in order to execute both a foot step forward and a grasping or striking movement with the arms. We present an approach for predicting the progress of a movement primitive in a probabilistic manner. The progress is learned using kernel logistic regression and interpreted as (de-)activ...
Download Bibtex file
Christian Maag, Norbert Schneider, Thomas Lübbeke, Thomas H Weisswange, Christian Goerick , "Car Gestures – Advisory Warning Using Additional Steering Wheel Angles", Accident Analysis & Prevention, vol. 83, pp. 143–153, 2015.
AbstractAdvisory warning systems (AWS) notify the driver about upcoming hazards. The driving simulator study (N=24) compared an AWS based on additional steering wheel angles (Car Gestures) with a visual warning presented in a simulated head-up display (HUD). A condition of unassisted driving was added to the experimental design. The subjects were confronted with potential hazards in a variety of urban situations (e.g. pedestrian standing on the curbs). S...
Download Bibtex file
Yu Setoguchi, Kaname Narukawa, Hisao Ishibuchi , "A Knee-based EMO Algorithm with an Efficient Method to Update Mobile Reference Points", The 8th International Conference on Evolutionary Multi-Criterion Optimization, 2015.
AbstractA number of evolutionary multi-objective optimization (EMO) algorithms have been designed to search for non-dominated solutions around a reference point, which is usually assumed to be given by a decision maker (DM) based on his/her preference. However, setting the reference point needs a priori knowledge that the DM sometimes does not have. In order to obtain favorable solutions without a priori knowledge, “knee points” can be used. Some algorit...
Download Bibtex file
1 ... 99 100 101 102 103 104 ... 183
Follow us
