Robust vehicle localization in urban environments using probabilistic maps

By Jesse Levinson, Sebastian Thrun. 2010

606 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Automotive Engineering, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Automotive Engineering

In Electrical and Electronic Engineering

Citations in the corpus

Vehicle Detection from 3D Lidar Using Fully Convolutional Network (2016, background): “A large number of research have been done on exploiting the range scan data in robotic tasks including localization, mapping, object detection and scene parsing [16].”
Fast LIDAR localization using multiresolution Gaussian mixture maps (2015, methodology): “Despite attempts by Levinson et al. in [7] to model slight changes in appearance of these ground plane maps, all of these methods can fail when harsh weather is present in the environment—for example, rain puddles and snowdrifts can build up and occlude the view of the informative ground signal,…”
Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation (2019, background): “t of invalid and valid regions. Map-Guided Vision Applications. One of the major application domains of maps is robot localization, which is a large research ﬁeld on its own and has a rich literature [53], [54]. Maps have also been enriched to be leveraged for other vision tasks beyond localization ”
Autonomous Ground Vehicles—Concepts and a Path to the Future (2012, background): “Working with measurements which are not taken at one unique timestamp, it becomes important to compensate for the vehicle’s ego-motion in all measurements [7].”
Towards 3D object recognition via classification of arbitrary object tracks (2011, methodology): “The LIDAR is calibrated using the algorithm of [17].”
Efficient Surfel-Based SLAM using 3D Laser Range Data in Urban Environments (2018, neutral): “mapping systems mainly accomplish the estimation relying on feature-based solutions [34, 35], reduced map representations [14, 13], voxel grid-based methods [16], or point sub-sampling [30], which all effectively reduce the data used for alignment.”
Robust localization using 3D NDT scan matching with experimentally determined uncertainty and road marker matching (2017, neutral): “proposed a map-based localization method in [7].”
A Survey of the State-of-the-Art Localization Techniques and Their Potentials for Autonomous Vehicle Applications (2018, methodology): “the technique was further extended in [36] by incorporating the use of LDMs.”
Autonomous driving based on accurate localization using multilayer LiDAR and dead reckoning (2017, methodology): “also proposed a multilayer LiDARbased localization method [1], where localization is performed by using a reflection intensity map, which is built 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC)”
Autonomous Vehicle Navigation in Rural Environments Without Detailed Prior Maps (2018, background): “[11]–[13], [22]–[24]), we assume no precise metric highresolution global map.”
Towards fully autonomous driving: Systems and algorithms (2011, background): “Signiﬁcant changes have been made, primarily to enable a shift in focus from competition-mode to research.”
Variational Autoencoder for End-to-End Control of Autonomous Driving with Novelty Detection and Training De-biasing (2018, background): “These submodules can range from mapping and localization [3], [4], to perception [5]–[7], planning [8], [9], and control [10], [11].”
Sensor Fusion-Based Low-Cost Vehicle Localization System for Complex Urban Environments (2017, background): “Levinson et al. [9] compares infrared reﬂectivities of a multi-layer LIDAR with their means and standard deviations stored in the digital map.”
Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving (2017, neutral): “Finally, an interesting approach, first proposed in [177] then extended in [178], focuses on building high-quality road surface maps using a 3D laser.”
L3-Net: Towards Learning Based LiDAR Localization for Autonomous Driving (2019, methodology): “Thrun [19, 20] propose a LiDAR intensity-based localization method.”
Robust and Precise Vehicle Localization Based on Multi-Sensor Fusion in Diverse City Scenes (2017, methodology): “As exhibited, our proposed solution is able to achieve better performance over [12] consistently over time.”
Road marking detection using LIDAR reflective intensity data and its application to vehicle localization (2014, methodology): “In order to obtain better results, we also integrated the curb detector to delimit the road marking search area and the deterministic intensity calibration algorithm of [2].”
Visual localization within LIDAR maps for automated urban driving (2014, positive): “State-of-the-art methods [2], [3] use reflectivity measurements from 3D LIDAR scanners to create an orthographic map of ground-plane reflectivities.”