Metrics for the Evaluation of localisation Robustness

Yi, Siqi; Nebot, E.

doi:10.1109/ivs.2019.8814106

Cited by 13 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further robustness challenges can be found in environment changes and dynamic objects [1]. The first metrics to analyze certain areas of robustness of a localization system were defined in [37], namely the following:…”

Section: Robustness Of Vehicle Self-localizationmentioning

confidence: 99%

Investigation on Robustness of Vehicle Localization Using Cameras and LiDAR

Albrecht

Behre²,

Herrmann³

et al. 2022

Vehicles

View full text Add to dashboard Cite

Vehicle self-localization is one of the most important capabilities for automated driving. Current localization methods already provide accuracy in the centimeter range, so robustness becomes a key factor, especially in urban environments. There is no commonly used standard metric for the robustness of localization systems, but a set of different approaches. Here, we show a novel robustness score that combines different aspects of robustness and evaluate a graph-based localization method with the help of fault injections. In addition, we investigate the influence of semantic class information on robustness with a layered landmark model. By using the perturbation injections and our novel robustness score for test drives, system vulnerabilities or possible improvements are identified. Furthermore, we demonstrate that semantic class information allows early discarding of misclassified dynamic objects such as pedestrians, thus improving false-positive rates. This work provides a method for the robustness evaluation of landmark-based localization systems that are also capable of measuring the impact of semantic class information for vehicle self-localization.

show abstract

Section: Robustness Of Vehicle Self-localizationmentioning

confidence: 99%

Investigation on Robustness of Vehicle Localization Using Cameras and LiDAR

Albrecht

Behre²,

Herrmann³

et al. 2022

Vehicles

View full text Add to dashboard Cite

show abstract

“…The second and third layers contain the location dependant sensor model of GPS and lidar respectively. The methodology of lidar feature localisation pipeline can be found in [23], and is therefore not repeated here.…”

Section: B Building a Geographically Registered Multi-sensor Map Data...mentioning

confidence: 99%

A Persistent and Context-aware Behavior Tree Framework for Multi Sensor Localization in Autonomous Driving

Yi¹,

Nebot²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Fig. 1. Vehicle trajectories of 53 rosbags in the University of Sydney Campus Dataset output from the GPS+lidar main filter are superimposed together onto a satellite image. No manual alignment of trajectory is performed. The color of trajectory points indicates the state of update used by the filter. Green: lidar feature updating. Blue: dead reckoning. Red: GPS updating. The blue dead reckoning area in the middle of the image is an underground carpark.

show abstract

“…Corners, on the other hand, are characterized as a vertical stack of the intersections between detected straight line segments with similar properties. In the urban environment, the straight lines are often observed from lidar returns on the walls of buildings [36]. It is worth mentioning that for the initial construction of the map, the parameters for the feature detectors were set to be very rigid in order to ensure that the features included in the initial map were stationary and increase the chance that the loop closure is successful.…”

Section: B Initial Feature Mapmentioning

confidence: 99%

Long-term map maintenance pipeline for autonomous vehicles

Berrío¹,

Shan²,

Nebot³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

For autonomous vehicles to operate persistently in a typical urban environment, it is essential to have high accuracy position information. This requires a mapping and localisation system that can adapt to changes over time. A localisation approach based on a single-survey map will not be suitable for long-term operation as it does not incorporate variations in the environment. In this paper, we present new algorithms to maintain a featured-based map. A map maintenance pipeline is proposed that can continuously update a map with the most relevant features taking advantage of the changes in the surroundings. Our pipeline detects and removes transient features based on their geometrical relationships with the vehicle's pose. Newly identified features became part of a new feature map and are assessed by the pipeline as candidates for the localisation map. By purging out-of-date features and adding newly detected features, we continually update the prior map to more accurately represent the most recent environment. We have validated our approach using the USyd Campus Dataset [1] [2], which includes more than 18 months of data. The results presented demonstrate that our maintenance pipeline produces a resilient map which can provide sustained localisation performance over time.

show abstract

Metrics for the Evaluation of localisation Robustness

Cited by 13 publications

References 13 publications

Investigation on Robustness of Vehicle Localization Using Cameras and LiDAR

Investigation on Robustness of Vehicle Localization Using Cameras and LiDAR

A Persistent and Context-aware Behavior Tree Framework for Multi Sensor Localization in Autonomous Driving

Long-term map maintenance pipeline for autonomous vehicles

Contact Info

Product

Resources

About