检索结果-内蒙古大学图书馆

IEEE Symposium on Intelligent Vehicle

作者： Florian Damerow Benedict Flade Julian Eggert Control Methods and Robotics Lab Technical University of Darmstadt Darmstadt Germany Honda Research Institute (HRI) Europe Offenbach Germany

ISBN: (纸本)9781509018222

The Foresighted Driver Model (FDM) is a microscopic driver model which is based on the idea that a driver balances risk with utility. This paper deals with the modeling of advanced driving maneuvers for the FDM with a special focus on lateral positioning scenarios, such as lane changes in highway traffic. When driving at high speeds, tactical preparation for a safe lane change is of high importance. In this context, the paper presents maneuvers that allow for lane changes to be planned well in advance and carefully made without the restraint of requiring immediate action. Furthermore, the paper presents a continuous lateral control which allows driving on arbitrary paths other than the centerline, depending on the current traffic situation. Since more complex lateral maneuvers require more detailed considerations of the environment, an approach is presented to model the lane and the environmental influences. This paves the way for a modeling of variables such as lane markings, roadblocks, hard shoulders and more. Simulations illustrate how the introduced maneuvers allow successful preparation for upcoming lane changes and how traffic obstructions can be bypassed without performing a lane change but by using the continuous lateral control.

关键词： Vehicles Trajectory Frequency division multiplexing Adaptation models Cost function Predictive models Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Early Evolution of LOLP: Evaluating Generating Capacity Requirements [History]

引用

IEEE Power and Energy Magazine 2015年第4期13卷 88-98页

作者： Billinton, Roy Chu, Kelvin Honda Research Institute (HRI) Offenbach Germany Control Methods and Robotics Lab Technical University of Darmstadt Darmstadt Germany

This article focuses ON the early application of probability methods in the evaluation of generating capacity adequacy and reserve capacity requirements in an electric power system. The primary objective is to illustrate the evolution of the loss of load probability (LOLP) from a concept to a numerical system index that has been widely accepted as a system standard for over 50 years. The observations in this article are supported by the Bibliography on Application of Probability methods in the Evaluation of Generating Capacity Requirements, presented by Roy Billinton at the IEEE Winter Power Meeting in New York, New York, 30 Januarya 4 February 1966 and designated as Conference Paper No. 31 CP 66-62. © 2003-2012 IEEE.

关键词： Probability

来源：评论

学校读者我要写书评

暂无评论

Probabilistic situation assessment framework for multiple, interacting traffic participants in generic traffic scenes

Probabilistic situation assessment framework for multiple, i...

引用

IEEE Symposium on Intelligent Vehicle

作者： Stefan Klingelschmitt Florian Damerow Volker Willert Julian Eggert Control Methods and Robotics Lab Technical University of Darmstadt Darmstadt Germany Honda Research Institute Europe GmbH Offenbach am Main Germany

ISBN: (纸本)9781509018222

Situation recognition is a prerequisite for many advanced driver assistance systems as well as for partially and fully automated vehicles. Current situation recognition approaches focus mainly on estimating maneuvers of single scene entities. However, assessing multiple, possibly interacting, traffic participants simultaneously is crucial in complex traffic scenes and has hardly been investigated. Considering the variability and combinatorics of such scenarios, having specialized situation recognition systems covering each case directly is unrealistic. In this paper, we present a flexible framework for assessing generic traffic scenes with multiple interacting traffic participants. It is able to construct a fully interaction-respecting probabilistic situation assessment, while relying on reusable state-of-the-art single-entity-based maneuver predictions. The benefits and applicability are presented on a real-world data set. The evaluation indicates that the approach is not only able to reconstruct underlying interdependent probability distributions; it outperforms specially designed models, due to the reduced complexities of the single-entity-based recognition models.

关键词： Vehicles Probability distribution Probabilistic logic Road transportation Random variables Complexity theory Context

来源：评论

学校读者我要写书评

暂无评论

Root locus design for the synchronization of multi-agent systems in general directed networks 5

Root locus design for the synchronization of multi-agent sys...

引用

5th IFAC Workshop on Distributed Estimation and control in Networked Systems, NecSys 2015

作者： Khodaverdian, Saman Lanfermann, Felix Adamy, Jürgen Institute of Automatic Control and Mechatronics Control Methods and Robotics Lab Technische Universität Darmstadt Germany

This paper considers the synchronization problem of multi-agent SISO systems with general unidirectional communication structures. A distributed control strategy is presented which relies on relative output differences of neighboring agents and, thus, does not need relative state information. We propose a root locus design method to determine the synchronization gain. Since in directed networks the characteristic equation for synchronization might be complex valued, we use tools from the complex root locus technique to solve the synchronization task. © 2015, IFAC (International Federation of Automatic control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Trajectory Similarity and its Application to Predicting Lack of Interaction in Traffic Situations

Spatio-Temporal Trajectory Similarity and its Application to...

引用

IEEE International Conference on Intelligent Transportation Systems

作者： Florian Damerow Stefan Klingelschmitt Julian Eggert Control Methods and Robotics Lab Technical University of Darmstadt 64283 Germany Honda Research Institute (HRI) Europe Carl-Legien-Str. 30 63073 Offenbach Germany

ISBN: (纸本)9781509018901

This work addresses two topics. On one hand we study the problem of general measures for spatio-temporal trajectory similarity based on the evaluation of longitudinal and lateral spatio-temporal distance. On the other hand we employ trajectory similarity measures to general situation classification problems for traffic scenarios, which include the well-known problem of lane assignment and driving maneuver recognition. We predict situation-specific prototypical trajectories using the interaction-aware Foresighted Driver Model (FDM) and compare the situation-dependent predicted trajectories with the actually measured trajectories resulting in estimations of how good a situation matches the actual behaviors. We then set up a situation classification system, which is able to detect incorrect traffic behavior in terms of lack of interaction between two traffic participants when interaction is necessary for a safe behavior. We evaluate our system using real world and simulated crash cases and show that it is able to warn the driver, that another traffic participant is not considering the own car, about 2 seconds ahead of a crash, which would be sufficient for a suitable evasive behavior.

关键词： Trajectory Predictive models Automobiles Hidden Markov models Planning Measurement uncertainty trajectory Automobiles Hidden Markov models measurement uncertainty Prediction models Cars Traffic Planning

来源：评论

学校读者我要写书评

暂无评论

Camera to map alignment for accurate low-cost lane-level scene interpretation

Camera to map alignment for accurate low-cost lane-level sce...

引用

International Conference on Intelligent Transportation

作者： Gaoya Cao Florian Damerow Benedict Flade Markus Helmling Julian Eggert Florian Damerow and Markus Helmling are with the Control Methods and Robotics Lab Technical University of Darmstadt Darmstadt Germany Benedict Flade and Julian Eggert are with the Honda Research Institute (HRI) Europe Offenbach Germany

ISBN: (纸本)9781509018901

To be able to predict the evolution of the driving context, estimate the expected risks and plan future behavior alternatives, it is crucial to know where traffic participants can go and where they will most likely go. Consequently, for future Advanced Driver Assistance Systems (ADAS), precise, lane-accurate localization of the ego- as well as the other vehicles is a key technology. The proposed standard solutions to lane-accurate localization are usually based on expensive detailed 3D maps and precise absolute position estimation sensors. To the contrary, in this paper we propose to improve the localization of scene items based on state-of-the-art map data, combined with a coarse and cheap position estimation as e.g. provided by standard GNSS. From the map data, we infer the structure of the contextual road geometry, and align it with the road view(s) as provided by a front camera. This results in an improved relative positioning of the sensed items on the map structures, allowing a better scene interpretation. The alignment occurs by best-match search based on a feature comparison between the real road view from the camera and virtually generated road views based on the map considering different assumed ego-vehicle positions. On standard road scenes, we validate the approach, and show that it can be used as a cheap means to support intelligent ADAS and improve localization.

关键词： Roads Cameras Vehicles Estimation Geometry Sensors Satellite navigation systems

来源：评论

学校读者我要写书评

暂无评论

Root Locus Design for the Synchronization of Multi-Agent Systems in General Directed Networks ∗

引用

IFAC-PapersOnLine 2015年第22期48卷 150-155页

作者： Saman Khodaverdian Felix Lanfermann Jürgen Adamy Institute of Automatic Control and Mechatronics Control Methods and Robotics Lab Technische Universität Darmstadt Germany

关键词： Synchronization multi-agent systems directed networks output coupling root locus

来源：评论

学校读者我要写书评

暂无评论

Multi-supplier power grid framework based on multicommodity routing

Multi-supplier power grid framework based on multicommodity ...

引用

International Energy and Sustainability Conference (IESC)

作者： Ivan Popov Control Methods and Robotics Lab TU Darmstadt Germany

Future power grid architectures need to efficiently incorporate new small-scale renewable energy suppliers in addition to large-scale power plants. We introduce a multi-producer multi-consumer congestion model of a power supply network, where production and transmission costs depend on the congestion in corresponding nodes and arcs of the network graph. The consumer goal is to meet their energy demand by purchasing energy from multiple suppliers while minimizing costs. We formulate the cost minimization problems for energy consumers with the assumption of constant-per-unit profit for energy producers. By adding a fictitious node to the graph with arcs toward the supplier nodes, we can formulate a networking game with a single source and multiple destinations. We apply multicommodity atomic routing methods and results to this system model in order to investigate the existence, the uniqueness and the efficiency of Nash equilibria for certain classes of cost functions. The efficiency is established in a simple example of this framework with a star-shaped network topology. Finally, we discuss possible extensions of the model.

关键词： Routing Production Cost function Minimization Games Smart grids

来源：评论

学校读者我要写书评

暂无评论

Fast synchronization with directed small-world networks

Fast synchronization with directed small-world networks

引用

International Conference on Electrical Engineering, Computing Science and Automatic control (CCE)

作者： Flavio Montalbano Saman Khodaverdian Jürgen Adamy Control Methods and Robotics Lab Technische Universität Darmstadt Darmstadt Germany

In different articles it is shown that multi-agent synchronization can be faster under certain undirected network topologies. In this paper, we present an algorithm which generates strongly connected directed small-world networks. The main goal is a further enhancement of convergence speed. The generated graphs solve the consensus problem significantly faster than regular networks with the same number of links. However, the produced structures are generally not balanced, i.e. the out-degree remains constant, while the in-degree can vary. In this case an averaging consensus will not be reached. To solve this inconvenience, we propose a heuristic sorting algorithm to balance the generated directed small-world networks. In addition, balancing has yet another positive influence on the convergence speed. The result is a balanced, directed small-world network which solves the consensus problem faster than undirected small-world networks.

关键词： Synchronization Convergence Eigenvalues and eigenfunctions Network topology Laplace equations Heuristic algorithms Graph theory

来源：评论

学校读者我要写书评

暂无评论

Artificial motivations based on drive-reduction theory in self-referential model-building control systems

Artificial motivations based on drive-reduction theory in se...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Moritz Schneider Jürgen Adamy Institute of Automatic Control and Mechatronics Laboratory of Control Methods and Robotics Technische Universität Darmstadt Darmstadt Germany

ISBN: (纸本)9781479919611

Motivation and emotion are inseparable component factors of value systems in living beings, which enable them to act purposefully in a partially unknown and sometimes unforgiving environment. Value systems that drive innate reinforcement learning mechanisms have been identified as key factors in self-directed control and autonomous development towards higher intelligence and seem crucial in the development of a concept of “self” in sentient beings [1]. This contribution is concerned with the relationship between artificial learning control systems and innate value systems. In particular, we adapt the state-of-the-art model of motivational processes based on reduction of generalized drives towards higher flexibility, expressivity and representation capability. A framework for modelling self-adaptive value systems, which develop autonomously starting from an inherited (or designed) innate representation, within a learning control system architecture is formulated. We discuss the relationship of anticipated effects in this control architecture with psychological theory on motivations and contrast our framework with related approaches.

关键词： Biology Artificial intelligence Cognition Adaptation models

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：