Autonomous navigation requires accurate and reliable localization. In urban environments, infrastructure such as buildings and bridges disrupts Global Navigation Satellite Systems (GNSS), which requires the implementation of robust perception systems combined with inertial navigation. Roadside poles like traffic signs or light poles can serve as stable landmarks for map-based localization. When georeferenced in high-definition vector maps, these features enable reliable localization through detection pipelines and data association methods. While lidar captures their 3D geometry, distinguishing mapped poles in raw point clouds remains challenging. To train pole detectors tailored to the specific map used, we propose an automatic annotation framework that integrates lidar data, a vector map, and offline semantic segmentation to generate precise labeled data. By combining annotated pole clusters from the map with semantic segmentation, annotation errors can be minimized. This enables the training of a map-specific classifier optimized to detect mapped poles while filtering out irrelevant structures. It eliminates the need for manual labeling and ensures adaptability to the map used for online localization. Thanks to real data acquired in real-world urban scenarios, we show that this approach enhances significantly localization accuracy.

In urban environments where GNSS performance is degraded, localization can be performed using stable and geo-referenced map features detected by on-board sensors. Prior maps are prone to errors which have a direct impact on localization accuracy. By exchanging observed features and sharing their maps, vehicles can simultaneously improve their localization and update the map. This paper deals with indirect collaboration, where vehicles do not observe each other directly. The features are obtained from building facades using 3D lidar sensors. The paper emphasizes real-time decentralized collaboration with direct communication between vehicles, without the need for a central server. The collaboration takes place when vehicles perceive the same geo-referenced facades. Vehicle poses and maps are collaboratively updated using a Schmidt Kalman filter that carefully manages the cross-covariance terms. To maintain consistent estimates, the Kullback-Leibler Average is used. We also present a lidar data processing pipeline to obtain reliable observations from building facades. Real tests carried out with experimental vehicles on the university campus are reported. The results show that indirect collaboration makes a significant contribution to localization and map update when compared to a standalone method.

Detecting road features is a key enabler for autonomous driving and localization. For instance, a reliable detection of poles which are widespread in road environments can improve localization. Modern deep learning-based perception systems need a significant amount of annotated data. Automatic annotation avoids time-consuming and costly manual annotation. Because automatic methods are prone to errors, managing annotation uncertainty is crucial to ensure a proper learning process. Fusing multiple annotation sources on the same dataset can be an efficient way to reduce the errors. This not only improves the quality of annotations, but also improves the learning of perception models. In this paper, we consider the fusion of three automatic annotation methods in images: feature projection from a high accuracy vector map combined with a lidar, image segmentation and lidar segmentation. Our experimental results demonstrate the significant benefits of multi-modal automatic annotation for pole detection through a comparative evaluation on manually annotated images. Finally, the resulting multi-modal fusion is used to fine-tune an object detection model for pole base detection using unlabeled data, showing overall improvements achieved by enhancing network specialization. The dataset is publicly available.

Localization integrity consists in providing a real-time measure of the level of trust to be placed in the localization estimates as vehicles operate. It provides a means of knowing whether position estimates are usable for navigation purposes. This paper formalizes the integrity concept and its underlying principles. Vehicles operate in different navigation environments, and so multiple sensors are used to ensure the required performance. Different sources of error exist. They must be bounded according to the acceptable level of risk for the application. This paper presents a generic approach for addressing integrity. It combines measurement rejection (for measurements considered to be faults) and position error characterization. For this purpose, a multi-sensor data fusion with a Fault Detection and Exclusion algorithm is constituted using a bank of information filters. These filters allow detected faults to be isolated without any prior assumption regarding the number of simultaneous errors. In addition, external integrity is expressed as a Protection Level of the localization solution. It uses a Student’s$t$-distribution in order to bound the distribution of the position error applicable to small integrity risks after a learning step. The approach is tested on data acquired on public roads using an experimental vehicle equipped with off-the-shelf proprioceptive and exteroceptive sensors together with an HD map. The results obtained validate the proposed approach.

Although autonomous vehicle technology has evolved significantly in recent years, the navigation of self-driving vehicles in complex scenarios is still an open issue. One of the major challenges in these conditions is safe navigation on roads open to public traffic. The main issue is the interaction of the autonomous vehicle with regular traffic, as the behaviors and intentions of human-driven vehicles are hard to predict and understand. In this paper we propose a strategy to allow an autonomous vehicle to safely cross a multi-lane roundabout. Our approach uses a High-Definition (HD) map to predict at lane level the future situation, harnessing the concept of virtual instances of road users, which is a key concept in anticipating the situation in a roundabout that can be represented by a navigation graph with loops. This paper presents a methodology that uses intervals representing road occupancy by vehicles, with the road being widened to reflect uncertainties in localization. Our method safely avoids collisions and guarantees that no priority constraints are violated during the insertion maneuver. Moreover, the method does not provide an overly cautious insertion policy,i.e., an autonomous vehicle does not wait for a long time before the insertion. The performance of our strategy was evaluated using the SUMO simulation framework. To better evaluate the complexity of the simulation scenario, a highly interactive vehicle flow was generated using real dynamic traffic data from the INTERACTION dataset. We report real tests carried out with an experimental self-driving vehicle on a test circuit. Our results show that this approach is easy to integrate into an embedded system and that it allows roundabouts to be crossed with a high level of safety.

In dynamic localization problems, the observations used from exteroceptive sensors are usually obtained from a single measurement. However, there are cases where the current measurement is not sufficient to detect the referenced landmark or to get a sufficient level of accuracy. In this study, a point cloud accumulation strategy is used to improve the resolution of a LiDAR sensor along its sparse axis. In particular, we are interested in the detection of markings transverse to the road axis in order to improve the accuracy of localization of an autonomous vehicle when approaching intersections or roundabouts. We present a method that allows the construction of an accurate observation with an associated observation model based on a High-Definition (HD) map through an accumulation of scans as the vehicle moves, by compensating the vehicle motion. The parameters of the accumulator are studied in terms of detection and accuracy. The quality of the observations and their impact on the localization quality are analyzed using real experiments carried out with an experimental vehicle equipped with a low-cost GNSS receiver, dead-reckoning sensors and a ground truth system.

In the paper a fast and consistent method to manage uncertainties on detected traffic agents providing reliable results is presented. The information provided by a LiDAR-based object detector is combined with a high-definition map to identify the drivable space of the carriage way. Because the use of a HD map requires the use of a localization system, the uncertainty of the estimated pose shall be handled carefully. A novel approach taking into account the localization uncertainty in the perception task by direct propagation of it onto the LiDAR points is proposed. It is compared with a classical propagation that relies on linearized approximation. The good performances of this approach in terms of integrity are demonstrated by the use of real data acquired at the entrance of a roundabout being a particularly complex situation.

Autonomous vehicles navigation in complex scenarios is still an open issue. One of the major challenges is the safe navigation of autonomous vehicles on roads open to public traffic. Indeed, behaviors and intentions of human-driven vehicles are hard to predict and understand. In this paper, we propose a strategy to make an autonomous vehicle able to cross safely a roundabout. Our approach relies on High-Definition (HD) maps with lane level description which allows to predict the future situation thanks to the concept of virtual vehicles. This method handles safely collision avoidance and guarantees that no priority constraint is violated during the insertion maneuver without being overly cautious. The performance is evaluated with the SUMO simulation framework. An highly interactive vehicles flow has been generated using real data from the INTERACTION dataset. We also propose strategies to extend our algorithm to multi-lane roundabouts and report how these extensions behave in terms of safety and traffic flow.

For an autonomous vehicle, situation understanding is a key capability towards safe and comfortable decision-making and navigation. Information is in general provided by multiple sources. Prior information about the road topology and traffic laws can be given by a High Definition (HD) map while the perception system provides the description of the space and of road entities evolving in the vehicle surroundings. In complex situations such as those encountered in urban areas, the road user behaviors are governed by strong interactions with the others, and with the road network. In such situations, reliable situation understanding is therefore mandatory to avoid inappropriate decisions. Nevertheless, situation understanding is a complex task that requires access to a consistent and non-misleading representation of the vehicle surroundings. This paper proposes a formalism (an interaction lane grid) which allows to represent, with different levels of abstraction, the navigable and interacting spaces which must be considered for safe navigation. A top-down approach is chosen to assess and characterize the relevant information of the situation. On a high level of abstraction, the identification of the areas of interest where the vehicle should pay attention is depicted. On a lower level, it enables to characterize the spatial information in a unified representation and to infer additional information in occluded areas by reasoning with dynamic objects.

Localization is one of the main challenges to be addressed to develop autonomous vehicles able to perform complex maneuvers on roads opened to public traffic. Having an accurate dead-reckoning system is an essential step to reach this objective. This paper presents a dead-reckoning model for car-like vehicles that performs the data fusion of complementary and redundant sensors: wheel encoders, yaw rate gyro and steering wheel measurements. In order to get an accurate dead-reckoning system with a drift reduced to the minimum, the parameters have to be well calibrated and the procedure has to be simple and efficient. We present a method able to accurately calibrate the parameters without knowing the ground truth by using a Rauch-Tung-Striebel smoothing scheme which enables to obtain state estimates as close to the ground truth as possible. The smoothed estimates are then used within a optimization process to calibrate the model parameters. The method has been tested using data recorded from an experimental vehicle on public roads. The results show a significant diminution of the dead-reckoning drift compared to a commonly used calibration method. We evaluate finally the average distance a vehicle can navigate without exteroceptive sensors by using the proposed four-wheeled dead reckoning system.

Localization with high integrity is crucial for highly autonomous vehicles. This requires that the localization system send a warning to a client application when it should not be used. The concept of integrity was firstly developed for aviation applications and recently became an active research area for autonomous vehicles. GNSS information merged with dead reckoning sensors is not sufficient for lane level localization in all navigation environments. Map-aided localization with vision sensors is essential to provide redundant and complementary information. In this work, a multi-sensor data fusion method that takes advantage of a high definition (HD) map is presented and the integrity of the obtained solution is quantified. A Fault Detection and Exclusion (FDE) step is added to exclude the faulty measurements from the fusion procedure. A second step is to bound the estimation errors in the Along Track (AT) and Cross Track (CT) directions through Protection Levels (PL). For this step, the usual Gaussian distribution is replaced by a Student's distribution with an adapted degree of freedom chosen according to the navigation environment. The performance of the approach is evaluated with an experimental vehicle equipped with a camera able to detect up to four lane markings simultaneously.

This work describes a cooperative pose estimation solution where several vehicles can perceive each other and share a geometrical model of their shape via wireless communication. We describe two formulations of the cooperation. In one case, a vehicle estimates its global pose from the one of a neighbor vehicle by localizing it in its body frame. In the other case, a vehicle uses its own pose and its perception to help localizing another one. An iterative minimization approach is used to compute the relative pose between the two vehicles by using a LiDAR-based perception method and a shared polygonal geometric model of the vehicles. This study shows how to obtain an observation of the pose of one vehicle given the perception and the pose communicated by another one without any filtering to properly characterize the cooperative problem independently of any other sensor. Accuracy and consistency of the proposed approaches are evaluated on real data from on-road experiments. It is shown that this kind of strategy for cooperative pose estimation can be accurate. We also analyze the advantages and drawbacks of the two approaches on a simple case study.

Maps can greatly improve vehicle localization using perception sensors that detect features georeferenced in the map. This relies on two assumptions. Firstly, the detected features and the elements of the map have to be correctly associated. Secondly, the features of the map have to be accurately referenced. In this paper, solutions regarding these issues are presented. The case study of localization using a camera detecting road markings is considered. A Kalman smoothing process is used to obtain the best possible estimate of the trajectory that enables to evaluate the reliability of markings stored in the map. A likelihood maximization technique is used to best associate the observed markings to those referenced in the map. By using these two methods, map errors are detected after a first passage in an area and can be mitigated in later passes. Experimental results are reported to evaluate the performance of this approach. It is shown that mapping errors can be correctly handled.

Model-based positioning methods involve nonlinear equations as is the case when using satellite pseudoranges on global navigation satellite systems (GNSSs) and local measurements on road features. As these are nonlinear models, classical estimation methods cannot provide guaranteed position estimation and can converge to local optima, sometimes far away from the global optimum or the true value. Based on interval analysis, set inversion, and constraints propagation on real values provide a framework that guarantees to find the true position with a characterized confidence domain. This paper describes an error bounded set membership algorithm that computes the absolute position of a road vehicle by using raw GNNS pseudoranges, lane boundary measurements, and a 2D road network map as geometric constraints. The algorithm is based on set inversion using interval analysis, and bounds are set on the measurements by taking into account a chosen risk. The GNSS pseudoranges errors are modeled carefully, and road constraints are formalized to provide additional information in the data fusion process. The proposed algorithm, named lane boundary augmented set-membership GNSS positioning (LB-ASGP), provides a novel and inexpensive approach to improve position estimation performance for road vehicles guaranteeing the enclosure of the computed solution with high confidence. Results from simulations and field experiments show that the LB-ASGP significantly reduces GNSS errors in the direction perpendicular to the lane thanks to the lane boundary measurements.

This paper proposes a set-membership based method for simultaneous localization and mapping. A box particle filter is exploited and improved to estimate robot states and feature positions. An interval constraint propagation is used to reduce box sizes, i.e., to decrease the uncertainty of the estimates. Buffers are also used to get q-satisfied results when empty estimates arise, on the one hand. On the other hand, historical data are used to improve the estimation through buffer contraction. Illustrations of the proposed method are given over simulations and experiments, with comparisons with a particle filter based method. The results show that the proposed method can reach the same simultaneous localization and mapping accuracy as a particle filter based method but with fewer particles. Moreover, this approach is comparatively more robust to system and measurement noises.

Despite the tremendous growth of research regarding fully autonomous vehicles in the past few years, many safety critical scenarios, such as the crossing of roundabouts, are still open issues. One of the main challenge is to deal with the lack of visibility in complex environments. Vehicle-to-vehicle and vehicle-to-infrastructure communications offer an appealing solution to handle these situations in a cooperative way. To avoid computing an ad hoc control strategy for every possible scenario, we propose in this paper to adapt the concept of virtual platooning to roundabout crossing. This idea allows a single platooning control law to handle complex scenarios such as intersection and roundabout crossings. This work combines the use of high definition maps and a curvilinear coordinates framework to deal with any kind of roundabouts. The proposed approach is not limited to communicating autonomous vehicles but can also be used with manually driven communicating vehicles or non-communicating vehicles with the help on the infrastructure. A formal proof of the correctness of this approach is given and simulations have been carried out with a high definition map of a real roundabout. We also introduce a novel graphical representation called safety diagram to study de performances of our approach.

Localization is a key problem for autonomous vehicle navigation. The use of high-definition maps and perception algorithms allows now to have lane-level accurate pose estimation in terms of cross-track and heading error. In this paper, we focus on the along-track localization of cooperative vehicles. We introduce a one-dimensional formulation of the localization problem by considering curvilinear coordinates. The covariance intersection filter is derived in one dimension leading to a minimum variable filter which allows multiple vehicles to cooperate while keeping consistent localization estimates. We show that the along-track localization error is directly dependent on the relative orientation between the trajectories followed by the cooperating vehicles. Experiments with two autonomous electric vehicles were conducted to evaluate the proposed approach.

Navigation maps provide important information for Advanced Driving Assistance Systems (ADAS) and Autonomous Vehicles. This paper presents a method estimating a set of likely map-matched hypotheses containing the correct solution with a high probability. This addresses the problems encountered when using a high definition map when a large number of ambiguities arise. These occur for instance, when only inaccurate prior information on position is available at initialization. The method uses lane-level accurate maps with dedicated attributes, such as connectedness and adjacency, and an automotive Global Navigation Satellite System (GNSS) receiver assisted with dead-reckoning (DR) sensors. GNSS can be so inaccurate that map-matching relies mainly on DR estimates, the GNSS fixes being used as uncertain estimates with protection levels. This paper proposes a formalization of the map-matching integrity problem as well as a sequential method using a Particle Filter providing a reliable set of map-matched hypotheses. The performance is evaluated using data acquired in public roads.

Fully distributed localization methods with no central server are relevant for autonomous vehicles that need real-time cooperation. In this paper, mobile vehicles share estimates of GNSS pseudoranges common errors also known as biases. The biases that affect the pseudoranges are mainly due to signal propagation and inaccurate ephemeris data. By describing the measurements models as geometric constraints on intervals, cooperative localization turns into distributed set inversion problem. The solution of this problem is guaranteed to contain the true vehicles positions. We consider vehicles which cooperate and exchange information in order to improve the absolute and relative estimation by fusing pseudoranges corrections shared between them. Results using real measurements are presented to illustrate the performance of the proposed approach in comparison with a standalone method.

This paper addresses the problem of fault detection, isolation, and adaptation (FDIA) in navigation systems on board passenger vehicles. The aim is to prevent malfunctions in systems such as advanced driving assistance systems and autonomous driving functions that use data provided by the navigation system. The integrity of the estimation of the vehicle position provided by the navigation system is continuously monitored and assessed. The proposed approach uses an additional estimate of vehicle position that is independent of the navigation system and based on data from standard vehicle sensors. First, fault detection consists in comparing the two estimates using a sequential statistical test to detect discrepancies despite the presence of noise. Second, fault isolation and adaptation is introduced to identify faulty estimates and to provide a correction where necessary. The FDIA framework presented here utilizes repeated trips along the same roads as a source of redundancy. Relevant properties of this formalism are given and verified experimentally using an equipped vehicle in rural and urban conditions and with various map faults. Results show that sequential FDIA performed well, even in difficult GNSS conditions.

Satellite positioning is a key technology for autonomous navigation in outdoors environments. When using standalone computation with mono-frequency receivers, positioning errors are not in accordance with the required performance. Nevertheless, since errors are strongly time-correlated, a GPS fix is quite informative if a shaping model of the positioning errors is carefully handled and made possible by exteroceptive sensors. When driving in a road with a camera detecting lane markings, the lateral error is directly observable by using a lane marking map. It can be well modeled by mixing auto-regressive and random constant models. An algebraic observability study is conducted to prove that this modeling is completely observable in a road frame. A new road invariant Extended Kalman Filter (EKF) is then presented to conserve the observability of every component of the state vector for any road whatever its orientation. The filter manages road changes by using bijective transformations that are detailed. Real experimental results indicate that the performance of the estimation process is significantly improved compared to a classic EKF that is implemented in a fixed working frame with a less informative error modeling.

Occupancy grids have shown interesting properties to model the environment for intelligent vehicles perception. In this paper, we present a novel approach to build 2D occupancy grid maps with stereo-vision. Our approach proposes a fitted sensor model based on the disparity space to interpret the stereo-vision information onto an occupancy grid map. The evidential model deals with sensor uncertainties by using Dempster-Shafer theory. Our approach exploits the U-disparity space to model the obstacle information and the V-disparity space to model the road space information. The fusion of these two sources of complementary information results to an enhanced environmental model. In a first experimental data set, results based on real road data and comparisons with Lidar grids show that the proposed evidential sensor model can model efficiently the environment. In a second one, the mapping of a road environment is reported to show the performance of the proposed model with another stereo-vision system.

When mobile robots need to cooperate, mutual localization is a key issue. The objective is to enable cooperative localization capabilities, such that each robot determines the partners positions in a common frame with reliable confidence estimates. Exteroceptive sensors can measure distances to known beacons in order to provide absolute information. It often exists biases that affect these measurements because of particular environment conditions or because of an inaccurate knowledge of the beacons positions. In this work, each robot is also equipped with proprioceptive sensors, but no sensor can measure the inter-distance between the robots. The method that we consider is fully distributed between the robots, which share positions and biases estimates. In order to handle the data incest problem, we use constraint propagation techniques on intervals. The distributed cooperative localization method gives sets that always contain the true positions of the robots without any over-convergence. Simulation results show that the so-called method improves localization performance compared to standalone methods.

For the development of driving assistance systems and autonomous vehicles, a reference perception equipment including navigable space determination and obstacles detection is a key issue. The Velodyne sensor which provides high definition and omnidirectional information can be used for this purpose. Nevertheless, when scanning around the vehicle, uncertainty necessarily arises due to unperceived areas and noisy measurements. This paper proposes an inverse evidential model for the Velodyne in order to exploit its measurements in a 2D occupancy grid mapping framework. The evidential sensor model interprets the data acquired from the Velodyne and successively maps it to a Carthesian evidential grid using a fusion process based on the least commitment principle to guarantee information integrity. Experimental results prove that this approach can handle efficiently the uncertainties of the sensor and thus a highly reliable local reference map near the vehicle can be built for every timestamped perception system that needs evaluation or calibration.

Currently, Advanced Driving Assistance Systems (ADAS) increasingly rely on information stored in vehicle on board digital maps. The vehicle position is projected onto the map to establish oncoming road context. However, errors might exist in the road geometry stored in the maps. The integrity of this map-matched estimate must be monitored in real-time to avoid errors that can lead to hazardous situations. This paper presents a monitoring system and fault detection, isolation and adaptation formalism which benefits of multiple vehicle journeys (e.g. commuting). We demonstrate that it is possible to assert correct navigation information within the first journey to a new area and to isolate areas where the road geometry is erroneous after the second journey. The approach takes into account errors that might occur on the estimation of the global vehicle position. The proposed formalism was experimentally validated using a passenger vehicle driven in different map and GNSS conditions.

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-vehicle's 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 road's 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.

Estimating the pose in real-time is a primary function for intelligent vehicle navigation. Whilst different solutions exist, most of them rely on the use of high-end sensors. This paper proposes a solution that exploits an automotive type L1-GPS receiver, features extracted by low-cost perception sensors and vehicle proprioceptive information. A key idea is to use the lane detection function of a video camera to retrieve accurate lateral and orientation information with respect to road lane markings. To this end, lane markings are mobile-mapped by the vehicle itself during a first stage by using an accurate localizer. Then, the resulting map allows for the exploitation of camera-detected features for autonomous real-time localization. The results are then combined with GPS estimates and dead-reckoning sensors in order to provide localization information with high availability. As L1-GPS errors can be large and are time correlated, we study in the paper several GPS error models that are experimentally tested with shaping filters. The approach demonstrates that the use of low-cost sensors with adequate data-fusion algorithms should lead to computer-controlled guidance functions in complex road networks.

Being able to predict the trajectory of a human driver's potential lane change behavior in urban high way scenario is crucial for lane change risk assessment task. A good prediction of the driver's lane change trajectory makes it possible to evaluate the risk and warn the driver beforehand. Rather than generating such a trajectory only using a mathematical model, this paper develops a lane change trajectory prediction approach based on real human driving data stored in a database. In real-time, the system generates parametric trajectories by interpolating k human lane change trajectory instances from the pre-collected database that are similar to the current driving situation. In order to build this real lane change database, a human lane change data collection vehicle platform is developed. Extensive experiments have been carried out in urban highway environments to build a significant database with more than 200 lane changes. Real results show that this approach produces lane change trajectories that are quite similar to real ones which makes it suitable to predict humanlike lane change maneuvers.

International audience

Recent and future driver assistance systems use more and more sensors, that have individual tracking modules. For target tracking, it becomes necessary to find techniques to manage as simply as possible the use of a great number of independent and heterogeneous sensors, at the different stages of the process. This paper presents a modular highlevel track-fusion architecture for a multisensor environment. This architecture allows the variation of the number and the types of the used sensors with no major change in the tracking algorithm. The paper also tackles the multisensor track-to-track association issue with a new algorithm based on a particular track-to-track distance computation. An example of target tracking method is shown to make use of the proposed architecture and the track-to-track association algorithm.

The characterization in real-time of the drivable space in front of the vehicle is a key issue for safe autonomous navigation or driving assistance. This paper presents a method that uses a lidar (a multilayer laser scanner) integrated in the front bumper of an automotive vehicle. A grid processing is first applied to detect and localize objects in the immediate environment after having compensated the movement of the vehicle. Accurate map information is then introduced in the perception scheme to refine the characterization of the drivable space. The paper details the different processing stages necessary to implement this method and presents the design of the system that has been prototyped on board an experimental vehicle. We report real experiments carried out in challenging urban environments to illustrate the performance of this approach which has been evaluated thanks to a precise retro-projection of the estimated drivable space in a wide-angle scene camera.

Passenger vehicles are evolving into sensor-based computer controlled platforms with different levels of autonomy. Digital maps representing road networks are being used as an a priori source of information to provide context and to anticipate oncoming situation. On top of it, world models are built for machine understanding. However, these can have local errors, affecting location based functions. A common one is due to the rapid deployment of roundabouts, as they are introduced widely, with navigation maps ignoring their presence. This work introduces a novel approach to make the vehicle able to detect the presence of a roundabout while it is driven. It is then possible to update the map by the vehicle itself. The approach is based on graphical pattern recognition methods using a Bayesian classifier. The approach has been demonstrated experimentally using data acquired in real-traffic conditions.

Map matching means determining the location of a mobile with respect to a road network description stored in a digital map. This problem is usually addressed using Global Positioning System (GPS)-like fixes. Unfortunately, there are many situations in urban areas where few satellites are visible because of outages due to tall buildings. In this paper, map matching is solved using raw GPS measurements (pseudoranges and Doppler measurements), avoiding the necessity to compute a global position. The problem is formalized in a general Bayesian framework to handle noise, which can perform multihypothesis map matching when there is not enough information to make unambiguous decisions. This tightly coupled GPS-map fusion has to simultaneously cope with identifying the road and estimating the mobile's position on that road. A marginalized particle filter is proposed to efficiently solve this hybrid estimation problem. Real experimental results are reported to show that this approach can be initialized with fewer than four satellites. It can also track the location with only two satellites once the road selection has been solved.

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.

A global positioning method based on a precise 3-D drivable area map and on GPS pseudorange measurements is presented. Map and GPS measurements are represented by geometric constraints, thus turning the localization problem into a constraint satisfaction problem whose solution is the confidence domain of position. Interval analysis is employed to solve the problem by using contractions and bisections of a prior position box. If more than 3 satellites are visible, the method is robust to wrong pseudorange measurements. The system is also able to compute multiple position hypotheses in the case of ambiguities. An experimental validation using real GPS pseudorange measurements and a precise 3-D map is reported to illustrate the performance of the method with real data in an urban area, with reduced satellite visibility. Confidence domains are consistent with the truth during the whole 1 km experiment, and a 6.5 m 95% accuracy is achieved with at least two satellites in view.

Advanced Driving Assistance Systems exploit exteroceptive sensors to help the driver in perceiving the dynamic environment, like other vehicles or pedestrians. This paper proposes an original approach to deal with this perception challenge in urban environments. The method detects mobile objects motions using grids elaborated thanks to a lidar range scanner and an enhanced map of the drivable space. The data fusion is performed using the Dempster-Shafer theory which provides an interesting framework particularly well adapted to manage the uncertainties of the sensors. By analyzing conflicting information, objects movements can be efficiently characterized. This formalism provides also the interesting possibility to introduce decay factors that are useful for forgetting old information. Experimental results obtained with an IBEO Alasca and an Applanix positioning system show that such a perception strategy can be effective compared to deterministic accumulation strategies.

In urban environments, detection of moving obstacles and free space determination are key issues for driving assistance systems or autonomous vehicles. This paper presents a lidar-based perception system for passenger-cars, able to do simultaneously mapping and moving obstacles detection. Nowadays, many lidars provide multi-layer and multi-echo measurements. A smart way to handle this multi-modality is to use grids projected on the road surface in both global and local frames. The global one generates the mapping and the local is used to deal with moving objects. An approach based on both positive and negative accumulation has been developed to address the remnant problem of quickly moving obstacles. This method is also well suited for multi-layer and multi-echo sensors. Experimental results carried out with an IBEO Alasca and an Applanix positioning system show the performance of such a perception strategy.

A robust 2-D vehicle-positioning system based on constraint propagation on a data horizon is proposed. Using asynchronous unreliable absolute positions and reliable proprioceptive measurements, the proposed method outputs the bounds of the pose at any desired rate. A bounded error approach is used to propagate the imprecision of the input data to the final pose estimation. Measurements are represented by intervals taking errors into account. Integrity is assumed on proprioceptive measurements error bounds. In opposition, the bounds set on exteroceptive positions are not required to be guaranteed. Indeed, a relaxed intersection of constraints is applied to achieve robustness, given a maximum ratio of erroneous positions. This approach is implemented for an automotive vehicle equipped with a GPS receiver and a CAN gateway. An real experimental validation is carried out with a dataset including wrong GPS measurements and the crossing of a tunnel.

Reliable obstacle detection and localization is a key issue for driving assistance systems particularly in urban environments. In this article, a multi-modal perception approach is studied in order to enhance vehicle localization and dynamic objects tracking, in a world-centric map. 3D ego-localization is done by merging a stereo vision system and proprioceptive information coming from vehicle sensors. Mobile objects are detected using a multi-layer lidar that is simultaneously used to characterize a zone of interest in order to reduce the complexity of the perception process. Objects localization and tracking is then performed in the fixed frame which simplifies the scene analysis and understanding. Real experimental results are reported to evaluate the performance of the multi-modal system.

For ground vehicle localization, hybrid-GNSS localizers now use commonly dead-reckoning sensors, like odometers or inertial units. They are designed to increase the accuracy, the integrity and the availability of the localization information, particularly in areas where the satellite signals are subject to outages and multipaths. In this paper, a data-fusion method is proposed to take benefits of 2D navigable road-maps in a tightly-coupled approach. In such a problem, 3D modeling is mandatory to process the pseudo-range information of the satellites. Our proposal is to use a 2D map as a heading measure in a Earth tangential frame. This is called ¿map-aided odometry¿. A Kalman filter, gating the normalized innovation signals, is applied to merge the redundant exteroceptive information in a cautious way. Experimental results are reported to quantify the performance gain of the proposed approach relying on the map-aided technique. We show that this fusion scheme increases the accuracy and the availability of the provided localization specially in GNSS-challenging environments.

]For mobile robots to navigate autonomously, knowing with certainty their location is fundamental. However, this is difficult when operating in complex outdoors environments, and often results are inaccurate. To guarantee the certainty of the location estimates, the notion of integrity is used. This is a measure of the degree of confidence that provides a guaranteed location zone. The process consists in removing outliers amongst the measurements using Fault Detection and Exclusion (FDE) algorithms and then to compute Protection Levels (PL) that quantify the integrity zone. This is applicable mainly to Global Navigation Satellite Sytems (GNSS) in the aerospace domain where data redundancy exists and few multipath, which is not the case for land applications. In this paper, a new approach to localization integrity for land mobile robots is proposed by combining vehicle and GNSS data, stored within a short-term memory, the data horizon. This formulation allows for the application of FDE algorithms on the combined data set. It also leads to a gain of redundancy that enables PLs to be reduced and to increase the availability of integrity algorithms.

Over the last years, particle filters (PF) have attracted considerable attention in the field of nonlinear state estimation due to their relaxation of the linear and Gaussian restrictions in the state space model. However, for some applications, PF are not adapted for a real-time implementation. In this paper we propose a new method, called box particle filter (BPF), for dynamic nonlinear state estimation, which is based on particle filters and interval frameworks and which is well adapted for real time applications. Interval framework will allow to explain regions with high likelihood by a small number of box particles instead of a large number of particles in the case of PF. Experiments on real data for global localization of a vehicle show the usefulness and the efficiency of the proposed approach.

This paper presents a new fusion strategy that mixes interval analysis techniques and particle filters for data fusion and state estimation purposes occurring in many robotic perception problems. The method requires a small number of "box particles". This, in fact, answers one of major problems when using particle filters techniques. We report the case study of a land vehicle localization problem and we make a comparison based on real data between the performance of a particle filter and the new developed strategy.

This paper presents a road selection strategy for novel road-matching methods that are designed to support real-time navigational features within Advanced Driving-Assistance Systems (ADAS). Selecting the most likely segment(s) is a crucial issue for the road-matching problem. The selection strategy merges several criteria using Belief theory. Particular attention is given to the development of belief functions from measurements and estimations of relative distances, headings, and velocities. Experimental results using data from antilock brake system sensors, the differential Global Positioning System receiver, and the accurate digital roadmap illustrate the performances of this approach, particularly in ambiguous situations.

This paper presents a localization strategy for vehicles in urban environments by mapping and updating natural landmarks provided by a 2D ladar (laser range scanner) when GPS data is unavailable or has a too poor quality because of multi-tracks or bad satellite visibility. The method relies on an approach that takes profit of successive passages in the same area. From the modelling point of view, a particularity of the method is due to the use of linear landmarks - sidewalk edges - which implies the management of topological connections. Real experiments carried out in real conditions prove the feasibility of this approach

In order to implement a continuous and robust dynamic localization of a mobile robot, the fusion of dead reckoning and absolute sensors is often used. Depending on the objectives of precision or integrity, the choice of an algorithm could be crucial. For example, if the models used for the fusion are non linear, classical tools (such as a Kalman filter) cannot guarantee maximum error estimation. There are bounded error approaches that are insensitive to non linearity. In this context, the random errors are only modeled by their maximum bound. This paper compares a technique based on constraints propagation on intervals, with the usual Extended Kalman Filter for the data fusion of redundant sensors. We have thus developed both techniques and we consider the fusion of wheel encoders, a gyro and a differential GPS receiver. Experimental results show that the precision of a constraints propagation technique can be very good with guaranteed estimations. Moreover, such an approach is well adapted to a real time implementation.

This paper describes a method that provides an estimated location of an outdoor vehicle relative to a digital road map using Belief Theory and Kalman filtering. Firstly, an Extended Kalman Filter combines the DGPS and odometer measurements to produce an approximation of the vehicle’s pose, which is then used to select the most likely segment from a road network database. The selection strategy merges several criteria based on distance, direction and velocity measurements using Belief Theory. In this work, a particular attention is given to the elaboration of a Localization Uncertainty Gauge which takes into account imprecision of data sources (the sensors and the map) and uncertainty of the techniques used in the fusion process. This Gauge indicates the level of confidence assigned to the selected road by the system. Real experimental results illustrate this approach.

In order to get continuous dynamic localization of a mobile robot, dead reckoning and absolute sensors are usually merged. The models used for this fusion are non linear and, therefore, classical tools (such as Kalman filter) cannot guarantee a maximum error estimation. In some applications, integrity is essential and the ability to guaranty the result is a crucial point. There are ensemblist approaches that are insensitive to non linearity. In this context, the random errors are only modeled by their maximum bound. This paper presents a new technique to merge the data of redundant sensors with a guaranteed result based on constraints propagation techniques on intervals. We have thus developed an approach for the fusion of the 4 ABS wheel encoders, a measure of the angle of the driving wheel and a differential GPS receiver. Experimental results show that the precision that one can obtain is very good with a guaranteed result. Moreover, constraints propagation techniques are well adapted to a real time implementation.

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.

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.

We present a localization system which computes, by extended Kalman filtering, the position and heading of a vehicle using both odometry and the measurement of the relative azimuth angles of known landmarks. Observability of the continuous system is studied and gives information on situations where the performance of the filter may deteriorate. Results of extensive real outdoor experiments with a wheel-type robot moving on a slightly uneven floor are reported. We show that the system achieves a precision of a few centimetres.