Emmanuel Seignez

Real-time Bounded-error State Estimation for Vehicle Tracking

Estimating the configuration of a vehicle is crucial for its navigation. Most approaches are based on (extended) Kalman filtering or particle filtering. An attractive alternative is considered here, which relies on interval analysis. Contrary to classical extended Kalman filtering it allows global localization, and contrary to particle filtering it provides guaranteed results in the sense that a set is computed that contains all of the configurations that are consistent with the data and hypotheses. This paper presents a real-time implementation of the process including a description of the platform and its modeling, the integration of the errors on the model and the localization method itself.

Experimental vehicle localization by bounded-error state estimation using interval analysis

Estimating the configuration of a vehicle is crucial for navigation. The most classical approaches are Kalman filtering and Bayesian localization, often implemented via particle filtering. This paper reports on-going experimentation with an attractive alternative approach recently developed and based on interval analysis. Contrary to classical extended Kalman filtering, this approach allows global localization, and contrary to Bayesian localization it provides guaranteed results in the sense that a set is computed that contains all of the configurations that are consistent with the data and hypotheses. The approach is particularly robust to outliers.

A-Contrario Modeling for Robust Localization Using Raw GNSS Data

In Global Navigation Satellite System (GNSS) positioning, urban environments represent an issue particularly because of multipath and nonline-of-sight effects. The latter effects induce erroneous pseudorange observations that then should be discarded in order not to affect the estimation of the receiver position. This paper proposes a new approach for the detection of outliers in the pseudorange observations. Based on two models representing the distribution of inconsistent data (naive models), two criteria are proposed to partition the data between inliers and outliers and to estimate the location parameters. These criteria are then implemented in two localization algorithms. In addition, by considering hypotheses specific to GNSS localization, pseudorange selection and a regularization step are implemented in order to reduce the complexity and to improve the problem conditioning. Using simulated and actual datasets, the proposed algorithms are compared with popular and recent methods addressing the GNSS positioning problem. We show that the outlier detection improves the estimation of the receiver location and outperforms the classical approaches particularly when the environment is constrained.

Lane marking based vehicle localization using particle filter and multi-kernel estimation

Vehicle localization is the primary information needed for advanced tasks like navigation. This information is usually provided by the use of Global Positioning System (GPS) receivers. However, the low accuracy of GPS in urban environments makes it unreliable for further treatments. The combination of GPS data and additional sensors can improve the localization precision. In this article, a marking feature based vehicle localization method is proposed, able to enhance the localization performance. To this end, markings are detected using a multi-kernel estimation method from an on-vehicle camera. A particle filter is implemented to estimate the vehicle position with respect to the detected markings. Then, map-based markings are constructed according to an open source map database. Finally, vision-based markings and map-based markings are fused to obtain the improved vehicle fix. The results on road traffic scenarios using a public database show that our method leads to a clear improvement in localization accuracy.

Outlier Detection in GNSS Pseudo-Range/Doppler Measurements for Robust Localization.

In urban areas or space-constrained environments with obstacles, vehicle localization using Global Navigation Satellite System (GNSS) data is hindered by Non-Line Of Sight (NLOS) and multipath receptions. These phenomena induce faulty data that disrupt the precise localization of the GNSS receiver. In this study, we detect the outliers among the observations, Pseudo-Range (PR) and/or Doppler measurements, and we evaluate how discarding them improves the localization. We specify a contrario modeling for GNSS raw data to derive an algorithm that partitions the dataset between inliers and outliers. Then, only the inlier data are considered in the localization process performed either through a classical Particle Filter (PF) or a Rao-Blackwellization (RB) approach. Both localization algorithms exclusively use GNSS data, but they differ by the way Doppler measurements are processed. An experiment has been performed with a GPS receiver aboard a vehicle. Results show that the proposed algorithms are able to detect the ‘outliers’ in the raw data while being robust to non-Gaussian noise and to intermittent satellite blockage. We compare the performance results achieved either estimating only PR outliers or estimating both PR and Doppler outliers. The best localization is achieved using the RB approach coupled with PR-Doppler outlier estimation.

Autonomous parking carrier for intelligent vehicle

In this paper, we consider a parking method for autonomous vehicle in an underground car park. The implemented method is decomposed into three tasks. Starting from configuration given by the vehicle owner, the first one is the motion control of the vehicle from his residence to the car park. After joining the underground car park thanks to the implementation of a path tracking method, the next step is the scrutation of a free space in the car park followed by the operations used for the parking maneuver. The last one, during all the previously seen stages, is the localization mechanisms that allows the vehicle to keep a correct position in the global frame during the whole displacement.

Vehicle safety evaluation based on driver drowsiness and distracted and impaired driving performance using evidence theory

Vehicle safety is the study and practice for minimizing the occurrences and consequences of traffic accidents. It is found that driver behaviors such as drowsiness, impaired driving and distraction are contributing factors to traffic accidents. In complex road surroundings, comprehensive analysis is more robust than separate evaluations which are broadly proceeded with. In this paper, we propose a vision-based nonintrusive system involving lane and drivers eye features to analyze driver behaviors. In the framework of evidence theory, evaluations of driver drowsiness and distracted and impaired driving performance are integrated to evaluate vehicle safety in real time. The system was validated in real world scenarios, and experimental results demonstrate that it is promising to improve the robustness and temporal response of vehicle safety vigilance.

Vision-based estimation of driver drowsiness with ORD model using evidence theory

Driver drowsiness influences critically the driving safety and the lack of discerning the drowsy level precisely causes failure to take measures to prevent the accidents. In this paper, a novel intelligent surveillance system is proposed to estimate driver drowsiness based on the Observer Rating of Drowsiness (ORD) model integrated into evidence theory via fusion of lane and eye features. ORD is a subjective assessment of drowsiness that is reflected in peoples physical appearance, behaviors and mannerisms. Its drowsiness model in five levels, which acts as the framework in evidence theory, is used to describe the drivers state. Based on expert knowledge and data statistics, various visual eye features are studied to enhance the robustness of this system. The system is validated in real world scenarios, and experiment results demonstrate that it is promising to improve the robustness and temporal response of driver surveillance in real-time.

Monocular multi-kernel based lane marking detection

Lane marking detection provides key information for scene understanding in structured environments. Such information has been widely exploited in Advanced Driving Assistance Systems and Autonomous Vehicle applications. This paper presents an enhanced lane marking detection approach intended for low-level perception. It relies on a multi-kernel detection framework with hierarchical weights. First, the detection strategy performs in Birds Eye View (BEV) space and starts with an image filtering using a cell-based blob method. Then, lane marking parameters are optimized following a parabolic model. Finally, a self-assessment process provides an integrity indicator to improve the output performance of detection results. An evaluation using images from a public dataset confirms the effectiveness of the method.

Probabilistic error model for a lane marking based vehicle localization coupled to open source maps

Recent works have focused on lane marking feature based vehicle localization using enriched maps. The localization precision of existing methods depends strongly on the accuracy of the maps which are specially customized. In this article, we propose a marking feature based vehicle localization using open source map. Our method makes use of multi-criterion confidences to infer potential errors, and in advance, to enhance the vehicle localization. At first, the vision-based lane marking models are obtained. Meanwhile, the map-based lane markings of current state are derived from map databases. Both lane marking sources are fused together to implement vehicle localization, using a multi-kernel based algorithm. In order to further improve the localization performance, a probabilistic error model is employed to identify the possible errors. The experiments have been carried out on public database. The results show that error modeling leads to a lower average lateral error in localization result.