Jean-Emmanuel Deschaud

Invariant EKF Design for Scan Matching-Aided Localization

Localization in indoor environments is a technique that estimates the robots pose by fusing data from onboard motion sensors with readings of the environment, in our case obtained by scan matching point clouds captured by a low-cost Kinect depth camera. We develop both an invariant extended Kalman filter (IEKF)-based and a multiplicative extended Kalman filter-based solution to this problem. The two designs are successfully validated in experiments and demonstrate the advantage of the IEKF design.

Experimental implementation of an Invariant Extended Kalman Filter-based scan matching SLAM

We describe an application of the Invariant Extended Kalman Filter (IEKF) design methodology to the scan matching SLAM problem. We review the theoretical foundations of the IEKF and its practical interest of guaranteeing robustness to poor state estimates, then implement the filter on a wheeled robot hardware platform. The proposed design is successfully validated in experimental testing.

A simple nonlinear filter for low-cost ground vehicle localization system

This paper introduces a simple and intuitive nonlinear observer for low-cost ground vehicle localization system, using measurements from an inertial measurement unit, two wheel speed sensors, and a GPS. Taking advantage of the nonholonomic constraints, the design of the observer takes into account imperfections of the embedded sensors measurements, such as slowly time-varying gyroscope biases or some uncertainty on the angle between the vehicles frame and the road, to estimate the attitude, velocity and position of a ground vehicle. Thanks to a simple nonlinear structure based on the theory of symmetry-preserving observers, the estimator is easy to tune, easy to implement, and well-behaved even at very low speed. Moreover, the proposed filter presents some guaranteed convergence properties when GPS is available. Simulations and experiments in urban area illustrate the good performances of this simple algorithm.

Paris-Lille-3D: a large and high-quality ground truth urban point cloud dataset for automatic segmentation and classification

This paper introduces a new urban point cloud dataset for automatic segmentation and classification acquired by mobile laser scanning (MLS). We describe how the dataset is obtained from acquisition to post-processing and labeling. This dataset can be used to train pointwise classification algorithms; however, given that a great attention has been paid to the split between the different objects, this dataset can also be used to train the detection and segmentation of objects. The dataset consists of around 2 k m of MLS point cloud acquired in two cities. The number of points and range of classes mean that it can be used to train deep-learning methods. In addition, we show some results of automatic segmentation and classification. The dataset is available at: http://caor-mines-paristech.fr/fr/paris-lille-3d-dataset/.

Automatic Ground Surface Reconstruction from mobile laser systems for driving simulation engines

Driving simulation engines represent a cost effective solution for vehicle development, being employed for performing feasibility studies and tests failure and for assessing new functionalities. Nevertheless, they require geometrically accurate and realistic three-dimensional (3D) models in order to allow driver training. This paper presents the Automatic Ground Surface Reconstruction method, a framework that exploits 3D data acquired by Mobile Laser Scanning systems. They are particularly attractive due to their fast acquisition at the terrestrial level. Nevertheless, such a mobile acquisition introduces several constraints for the existing 3D surface reconstruction algorithms. The proposed surface modeling framework produces a regular surface and recovers sharp depth features within a scalable and detail-preserving framework. Experimental results on real data acquired in urban environments allow us to conclude on the effectiveness of the proposed method.

Paris-rue-Madame Database

This paper describes a publicly available 3D database from the rue Madame, a street in the 6th Parisian district. Data have been acquired by the Mobile Laser Scanning (MLS) system L3D2 and correspond to a 160 m long street section. Annotation has been carried out in a manually assisted way. An initial annotation is obtained using an automatic segmentation algorithm. Then, a manual refinement is done and a label is assigned to each segmented object. Finally, a class is also manually assigned to each object. Available classes include facades, ground, cars, motorcycles, pedestrians, traffic signs, among others. The result is a list of (X, Y, Z, reflectance, label, class) points. Our aim is to offer, to the scientific community, a 3D manually labeled dataset for detection, segmentation and classification benchmarking. With respect to other databases available in the state of the art, this dataset has been exhaustively annotated in order to include all available objects and to allow point-wise comparison.