Philippe Bonnifait

A Road-Matching Method for Precise Vehicle Localization Using Belief Theory and Kalman Filtering

This paper describes a novel road-matching method designed to support the real-time navigational function of cars for advanced systems applications in the area of driving assistance. This method provides an accurate estimation of position for a vehicle relative to a digital road map using Belief Theory and Kalman filtering. Firstly, an Extended Kalman Filter combines the DGPS and ABS sensor measurements to produce an approximation of the vehicle’s pose, which is then used to select the most likely segment from the database. The selection strategy merges several criteria based on distance, direction and velocity measurements using Belief Theory. A new observation is then built using the selected segment, and the approximate pose adjusted in a second Kalman filter estimation stage. The particular attention given to the modeling of the system showed that incrementing the state by the bias (also called absolute error) of the map significantly increases the performance of the method. Real experimental results show that this approach, if correctly initialized, is able to work over a substantial period without GPS.

Data fusion of four ABS sensors and GPS for an enhanced localization of car-like vehicles

A localization system using GPS, ABS sensors and a driving wheel encoder is described and tested through real experiments. An odometric technique using the four ABS sensors is presented. Due to the redundancy of the measurements, the precision is better than the one of differential odometry using the rear wheels only. The sampling is performed when necessary and when a GPS measurement is performed. This implies a noticeable reduction of the GPS latency, simplifying thus the data fusion process and improving the quality of its results.

Brief Paper: Box particle filtering for nonlinear state estimation using interval analysis

In recent years particle filters have been applied to a variety of state estimation problems. A particle filter is a sequential Monte Carlo Bayesian estimator of the posterior density of the state using weighted particles. The efficiency and accuracy of the filter depend mostly on the number of particles used in the estimation and on the propagation function used to re-allocate weights to these particles at each iteration. If the imprecision, i.e. bias and noise, in the available information is high, the number of particles needs to be very large in order to obtain good performances. This may give rise to complexity problems for a real-time implementation. This kind of imprecision can easily be represented by interval data if the maximum error is known. Handling interval data is a new approach successfully applied to different real applications. In this paper, we propose an extension of the particle filter algorithm able to handle interval data and using interval analysis and constraint satisfaction techniques. In standard particle filtering, particles are punctual states associated with weights whose likelihoods are defined by a statistical model of the observation error. In the box particle filter, particles are boxes associated with weights whose likelihood is defined by a bounded model of the observation error. Experiments using actual data for global localization of a vehicle show the usefulness and the efficiency of the proposed approach.

Constraints propagation techniques on intervals for a guaranteed localization using redundant data

In order to estimate continuously the dynamic location of a car, dead reckoning and absolute sensors are usually merged. The models used for this fusion are non-linear and, therefore, classical tools (such as Bayesian estimation) cannot provide a guaranteed estimation. In some applications, integrity is essential and the ability to guaranty the result is a crucial point. There are bounded-error approaches that are insensitive to non-linearity. In this context, the random errors are only modeled by their maximum bounds. This paper presents a new technique to merge the data of redundant sensors with a guaranteed result based on constraints propagation techniques on real intervals. We have thus developed an approach for the fusion of the two ABS wheel encoders of the rear wheels of a car, a fiber optic gyro and a differential GPS receiver in order to estimate the absolute location of a car. Experimental results show that the precision that one can obtain is acceptable, with a guaranteed result, in comparison with an extended Kalman filter. Moreover, constraints propagation techniques are well adapted to a real-time context.

Design and experimental validation of an odometric and goniometric localization system for outdoor robot vehicles

A 2D mobile robot localization system which uses odometry and the azimuth angles of known landmarks is presented. Observability analysis helps to determine situations where such a system may undergo difficulties, and gives information on its behavior when one of the beacons is hidden. Experimental results are presented.

Credibilist occupancy grids for vehicle perception in dynamic environments

In urban environments, moving obstacles detection and free space determination are key issues for driving assistance systems and autonomous vehicles. When using lidar sensors scanning in front of the vehicle, uncertainty arises from ignorance and errors. Ignorance is due to the perception of new areas and errors come from imprecise pose estimation and noisy measurements. Complexity is also increased when the lidar provides multi-echo and multi-layer information. This paper presents an occupancy grid framework that has been designed to manage these different sources of uncertainty. A way to address this problem is to use grids projected onto the road surface in global and local frames. The global one generates the mapping and the local one is used to deal with moving objects. A credibilist approach is used to model the sensor information and to do a global fusion with the world-fixed map. Outdoor experimental results carried out with a precise positioning system show that such a perception strategy increases significantly the performance compared to a standard approach.

Extrinsic calibration between a multi-layer lidar and a camera

In this paper, we present a novel approach for solving the extrinsic calibration between a camera and a multi-layer laser range finder. Our approach is oriented for intelligent vehicle applications, where the separation distance between sensors frames are frequently very important. For this purpose, we use a circle-based calibration object because its geometry allows us to obtain not only an accurate estimation pose by taking advantage of the 3D multi-layer laser range finder perception but also a simultaneous estimation of the pose in the camera frame and the camera intrinsic parameters. These advantages simplify the calibration task in outdoor environments. The method determines the relative position of the sensors by estimating sets of corresponded features and by solving the classical absolute orientation problem. The proposed method is evaluated by using different synthetics environments and real data. An error propagation analysis is made in order to estimate the calibration accuracy and the confidence intervals. Finally, we present a laser data projection into images to validate the consistency of the results.

Vehicle trajectory prediction based on motion model and maneuver recognition

Predicting other traffic participants trajectories is a crucial task for an autonomous vehicle, in order to avoid collisions on its planned trajectory. It is also necessary for many Advanced Driver Assistance Systems, where the ego-vehicles trajectory has to be predicted too. Even if trajectory prediction is not a deterministic task, it is possible to point out the most likely trajectory. This paper presents a new trajectory prediction method which combines a trajectory prediction based on Constant Yaw Rate and Acceleration motion model and a trajectory prediction based on maneuver recognition. It takes benefit on the accuracy of both predictions respectively a short-term and long-term. The defined Maneuver Recognition Module selects the current maneuver from a predefined set by comparing the center lines of the roads lanes to a local curvilinear model of the path of the vehicle. The overall approach was tested on prerecorded human real driving data and results show that the Maneuver Recognition Module has a high success rate and that the final trajectory prediction has a better accuracy.

Enhancement of global vehicle localization using navigable road maps and dead-reckoning

This paper presents a data fusion strategy for the global localization of car-like vehicles. The system uses raw GNSS measurements, dead-reckoning sensors and road map data. We present a new method to use the map information as a heading observation in a Kalman filter. Experimental results show the benefit of such a method when the GPS information is not available. Then, we propose a conservative localization strategy that relies mainly on dead-reckoned navigation. The GNSS measurements and the map information are not used when consistency tests are doubtful. Experimental tests indicate that the performance is effectively better when using only the available consistent information.

Map-Matching Integrity Using Multihypothesis Road-Tracking

Efficient and reliable map-matching algorithms are essential for Advanced Driver Assistance Systems. While most existing solutions fail to provide trustworthy outputs when the situation is ambiguous (such as at road intersections, at roundabouts, or when roads are parallel), we present a new map-matching method that overcomes this limitation. It is based on multihypothesis road-tracking that takes advantage of the geographical database road connectivity to provide a reliable road-matching solution with a confidence indicator that can be used for integrity-monitoring purposes. The presented multihypothesis road-tracking method combines proprioceptive sensors (odometers and gyrometers) with global positioning system and map information. While usually the algorithmic complexity of a multihypothesis method is exponential, because each hypothesis can generate new hypotheses at each sampling step, we propose using road connectivity information to overcome this drawback, so that new hypotheses are created only when they are really necessary. The proposed decision rule of the integrity monitoring strategy takes account of the estimated location with the map, as well as the respective probabilities of the different hypotheses to handle ambiguity zones. The performance of the method presented in this article is illustrated by tests that were carried out in real-world road conditions.