Grid-based online road model estimation for advanced driver assistance systems

Thomas, Julian; Stiens, Kai; Rauch, Sebastian; Rojas, Raúl

doi:10.1109/ivs.2015.7225665

Cited by 6 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The majority of this error comes from the longitudinal position, where the lateral position error is much less. This demonstrated performance meets the requirements of ADAS and automated driving applications, where there are higher performance requirements on the lateral position than the longitudinal position, for example when matching an object onto a lane, doing lane-change prediction [340,341] or estimating a road model using object data [286]. Furthermore, performance requirements from ADAS are higher for the front area of the host vehicle than for the side and the rear, which also matches the presented results.…”

Section: Discussionsupporting

confidence: 80%

Object-Level Fusion for Surround Environment Perception in Automated Driving Applications

Aeberhard¹

2017

View full text Add to dashboard Cite

Driver assistance systems have increasingly relied on more sensors for new functions. As advanced driver assistance system continue to improve towards automated driving, new methods are required for processing the data in an efficient and economical manner from the sensors for such complex systems. In this thesis, an environment model approach for the detection of dynamic objects is presented in order to realize an effective method for sensor data fusion. A scalable high-level fusion architecture is developed for fusing object data from several sensors in a single system. The developed high-level sensor data fusion architecture and its algorithms are evaluated using a prototype vehicle equipped with 12 sensors for surround environment perception. The work presented in this thesis has been extensively used in several research projects as the dynamic object detection platform for automated driving applications on highways in real traffic. Contents Abbreviations VIII List of Symbols X Abs...

show abstract

Section: Discussionsupporting

confidence: 80%

Object-Level Fusion for Surround Environment Perception in Automated Driving Applications

Aeberhard¹

2017

View full text Add to dashboard Cite

show abstract

“…It is important to note that this road model formulation makes no assumptions about the geometrical shapes lanes can have. Additional information such as the type of lane boundaries can easily be added later by extending the definition of B or p. In contrast to [23] this work is based on the theory of belief functions as brought forward by Dempster and reformulated by Shafer [24]- [26]. Dempster-Shafer theory (DST) is a generalization of Bayesian probability theory and allows to calculate the belief in a specific hypothesis taking all available evidence from different sources into account.…”

Section: Related Workmentioning

confidence: 99%

“…Higher-level functions like prediction and maneuver planning require a continuous and consistent description of the lane geometry and topology graph to work. Different methods to extract these representations from grids were already proposed in [19], [23]. In this paper, lane geometries are extracted by first searching for drivable paths using the belief Bel(L) of m all 1:t with the path planning method with unknown goal pose described in [32].…”

Section: Road Model Extractionmentioning

confidence: 99%

Semantic Grid-Based Road Model Estimation for Autonomous Driving

Thomas

Tatsch

Ekeren³

et al. 2019

2019 IEEE Intelligent Vehicles Symposium (IV)

Self Cite

View full text Add to dashboard Cite

For autonomous driving, knowledge about the current environment and especially the driveable lanes is of utmost importance. Currently this information is often extracted from meticulously (hand-)crafted offline high-definition maps, restricting the operation of autonomous vehicles to few wellmapped areas and making it vulnerable to temporary or permanent environment changes. This paper addresses the issues of map-based road models by building the road model solely from online sensor measurements. Based on Dempster-Shafer theory and a novel frame of discernment, sensor measurements, such as lane markings, semantic segmentation of drivable and nondrivable areas and the trajectories of other observed traffic participants are fused into semantic grids. Geometrical lane information is extracted from these grids via an iterative pathplanning method. The proposed approach is evaluated on real measurement data from German highways and urban areas.

show abstract

“…There are multiple methods of building detailed representations for the road model, and they can result in different models based on various purposes. For example, in [1,2], the authors presented approaches for grid-based road model estimation for advanced driver assistance systems. Their measurements from sensors are transformed into a grid-based road model and a geometrical description is extracted out of this model by the use of a path-planning based method.…”

Section: Introductionmentioning

confidence: 99%

High-Resolution Representation for Mobile Mapping Data in Curved Regular Grid Model

Miyazaki

Tamaki

et al. 2019

Sensors

View full text Add to dashboard Cite

As mobile mapping systems become a mature technology, there are many applications for the process of the measured data. One interesting application is the use of driving simulators that can be used to analyze the data of tire vibration or vehicle simulations. In previous research, we presented our proposed method that can create a precise three-dimensional point cloud model of road surface regions and trajectory points. Our data sets were obtained by a vehicle-mounted mobile mapping system (MMS). The collected data were converted into point cloud data and color images. In this paper, we utilize the previous results as input data and present a solution that can generate an elevation grid for building an OpenCRG model. The OpenCRG project was originally developed to describe road surface elevation data, and also defined an open file format. As it can be difficult to generate a regular grid from point cloud directly, the road surface is first divided into straight lines, circular arcs, and and clothoids. Secondly, a non-regular grid which contains the elevation of road surface points is created for each road surface segment. Then, a regular grid is generated by accurately interpolating the elevation values from the non-regular grid. Finally, the curved regular grid (CRG) model files are created based on the above procedures, and can be visualized by OpenCRG tools. The experimental results on real-world data show that the proposed approach provided a very-high-resolution road surface elevation model.

show abstract

Grid-based online road model estimation for advanced driver assistance systems

Cited by 6 publications

References 11 publications

Object-Level Fusion for Surround Environment Perception in Automated Driving Applications

Object-Level Fusion for Surround Environment Perception in Automated Driving Applications

Semantic Grid-Based Road Model Estimation for Autonomous Driving

High-Resolution Representation for Mobile Mapping Data in Curved Regular Grid Model

Contact Info

Product

Resources

About