International audience

This paper introduces COR-MCTS (Conservation of Resources - Monte Carlo Tree Search), a novel tactical decision-making approach for automated driving focusing on maneuver planning over extended horizons. Traditional decision-making algorithms are often constrained by fixed planning horizons, typically up to 6 seconds for classical approaches and 3 seconds for learning-based methods, limiting their adaptability in particular dynamic driving scenarios. However, planning must be done well in advance in environments such as highways, roundabouts, and exits to ensure safe and efficient maneuvers. To address this challenge, we propose a hybrid method integrating Monte Carlo Tree Search (MCTS) with our prior utility-based framework, COR-MP (Conservation of Resources Model for Maneuver Planning). This combination enables long-term, real-time decision-making, significantly enhancing the ability to plan a sequence of maneuvers over extended horizons. Through simulations across diverse driving scenarios, we demonstrate that COR-MCTS effectively improves planning robustness and decision efficiency over extended horizons.

Uncertainty in perception tasks, such as localization, is critical for autonomous systems. Many localization systems fail to ensure that their reported uncertainties encompass the true pose. This paper addresses this issue using the integrity framework. We focus on two main aspects. First, fault-tolerant localization through qualitative evaluation. Second, quantitative estimation of error bounds using (horizontal) protection levels. We introduce PL-RAS (Protection Level-based Robust and Adaptive Solver). This solver aids robustness in non-linear least squares optimization, including factor graph-based localization systems. PL-RAS improves uncertainty awareness and enhances system integrity. It strengthens both qualitative and quantitative integrity aspects. We test the approach on urban road data collected using an acquisition vehicle at Valeo's Créteil VMTC site. The results confirm PL-RAS's effectiveness. In one dataset, the integrity risks are$4.0 \times 10^{-4}$(lateral) and$34.0 \times 10^{-3}$(longitudinal). In a more challenging dataset, the lateral risk becomes$3.0 \times 10^{-4}$, while the longitudinal risk increases to$92.3\times 10^{-3}$. These findings demonstrate PL-RAS's robustness in fault tolerance and protection level estimation.

International audience

Multiple approaches have already been proposed to mimic real driver behaviors in simulation. This article proposes a new one, based solely on the exploration of undisturbed observation of intersections. From them, the behavior profiles for each macro-maneuver will be discovered. Using the macro-maneuvers already identified in previous works, a comparison method between trajectories with different lengths using an Extended Kalman Filter (EKF) is proposed, which combined with an Expectation-Maximization (EM) inspired method, defines the different clusters that represent the behaviors observed. This is also paired with a Kullback-Liebler divergent (KL) criteria to define when the clusters need to be split or merged. Finally, the behaviors for each macro-maneuver are determined by each cluster discovered, without using any map information about the environment and being dynamically consistent with vehicle motion. By observation it becomes clear that the two main factors for driver’s behavior are their assertiveness and interaction with other road users.

The implementation of road user models that can reproduce a credible realistic behavior in a multi-agent simulation is still an open problem. We propose a data-driven approach to sift through trajectories from a specific scenario and separate them into macro-maneuvers from raw data. Two clustering methods are proposed, mixing the low complexity of the hierarchical clustering method class of algorithms with a post-processing split-merge mechanism based on the initial and final points of each trajectory. The proposed methods’ goal is to isolate non-representative trajectories in their own clusters and in the process to keep the integrity of the ones that are semantically compatible across scenarios. To evaluate the clustering results over a range of methods, a new metric is proposed, called spread on cluster. Combined with the Davies-Boudin (DB) index, it allows to assess the final results according to the existence of outliers and the excessive number of clusters. Considering pedestrians, cyclists and cars in a range of different scenarios, the results confirm the proposed methods effectiveness in detecting different macro-maneuvers while being resistant to the presence of erroneous trajectories in the input data.

Misbehavior detection which verifies the semantics of the V2X shared messages is a crucial research topic in Cooperative Intelligent Transport Systems (C-ITS). Misbehavior detection solutions aim to detect and identify the potential attackers which generate V2X messages with erroneous data. Providing efficient misbehavior detection solutions is even more challenging in the context of Cooperative Perception Services (CPS) in which communicating entities share their perception of the environment. This is because of the complexity of the attacks and the lack of the available experimental platforms that allow to evaluate and validate the misbehavior detection solutions. For these reasons, we propose a unified simulation framework to the research community that enables exploration and development of misbehavior detection and mitigation solutions as integrated parts of the CPS in various scenarios. We demonstrate the effectiveness of our framework in generating performance results and provide the corresponding datasets.

Collective Perception Services (CPS) enable communicating entities to share their perception data in the V2X communication network. Potential attacks on extended perception data affect the CPS and may consequently degrade the safety application that rely on collective perception data. In this paper, we build an architecture that allows the integration of misbehavior detection and mitigation mechanisms with the CPS. We implement the Intersection Movement Assist (IMA) application that uses the extended perception data to calculate potential collision risks in intersection areas. We define specific safety metrics and through extensive simulations in large scale scenarios, we quantify the impact of a large number of attacks and of misbehavior detection on the safety application. Our evaluation demonstrates the ability of misbehavior detection and mitigation mechanisms to filter malicious shard perception data and consequently the benefits of using such mechanisms in improving the robustness of the safety application in complex road scenarios.

The abilities to understand the social interaction behaviors between a vehicle and its surroundings while predicting its trajectory in an urban environment are critical for road safety in autonomous driving. Social interactions are hard to explain because of their uncertainty. In recent years, neural network-based methods have been widely used for trajectory prediction and have been shown to outperform hand-crafted methods. However, these methods suffer from their lack of interpretability. In order to overcome this limitation, we combine the interpretability of a discrete choice model with the high accuracy of a neural network-based model for the task of vehicle trajectory prediction in an interactive environment. We implement and evaluate our model using the INTERACTION dataset and demonstrate the effectiveness of our proposed architecture to explain its predictions without compromising the accuracy.

Collective Perception Messages (CPM) enable vehicles to share their perceived objects with their neighbors in V2X network. These perception data extend local vehicles' perception and consequently improve road safety awareness. However, attacks on perception data are challenging and require advanced and efficient misbehavior detection mechanism especially in specific road scenarios where contradictory information need to be analysed. In this work, we introduce a trust management framework to detect misbehaving nodes through transmitted CPM messages. Our framework is based on trust assessment built through several processing steps. It addresses conflict situation when contradictory data are received using the Subjective Logic mechanism. The results show that our solution is effective in detecting misbehaving nodes based on their attributed trust scores. In addition, we show the impact of our solution and some CPM configuration parameters on safety services and especially on risk anticipation in intersection scenarios.

Predicting the trajectories of surrounding agents is an essential ability for autonomous vehicles navigating through complex traffic scenes. The future trajectories of agents can be inferred using two important cues: the locations and past motion of agents, and the static scene structure. Due to the high variability in scene structure and agent configurations, prior work has employed the attention mechanism, applied separately to the scene and agent configuration to learn the most salient parts of both cues. However, the two cues are tightly linked. The agent configuration can inform what part of the scene is most relevant to prediction. The static scene in turn can help determine the relative influence of agents on each other's motion. Moreover, the distribution of future trajectories is multimodal, with modes corresponding to the agent's intent. The agent's intent also informs what part of the scene and agent configuration is relevant to prediction. We thus propose a novel approach applying multi-head attention by considering a joint representation of the static scene and surrounding agents. We use each attention head to generate a distinct future trajectory to address multimodality of future trajectories. Our model achieves state of the art results on the nuScenes prediction benchmark and generates diverse future trajectories compliant with scene structure and agent configuration.

This paper proposes a multi-model adaptive control (MMAC) algorithm based on Youla-Kucera (YK) theory to deal with heterogeneity in cooperative adaptive cruise control (CACC) systems. The main idea of MMAC is to choose the plant in a predefined set that best approximates the system dynamics, applying the corresponding predesigned controller. A set of linear plants describing different vehicle dynamics is defined. Different CACC controllers are designed depending on these linear plants. Simulation and experimental results prove how MMAC determines the closest plant in the set, choosing the CACC system able to ensure string stability.

Autonomous driving in urban environment needs to anticipate a number of dangerous events, such as the presence of moving vehicles in occluded areas. This paper presents an approach computing a safe motion along a fixed path in an urban environment with dynamic vehicles that may be occluded. The method works on the time-path space and uses a visibility graph to compute the speed profile, considering both safety and comfort. Evaluations performed on CARLA simulator on several typical scenarios show that the approach is able to drive safely in presence of hidden obstacles.

Self-vehicle localization is one of the fundamental tasks for autonomous driving. Most of current techniques for global positioning are based on the use of GNSS (Global Navigation Satellite Systems). However, these solutions do not provide a localization accuracy that is better than 2-3 m in open sky environments [1]. Alternatively, the use of maps has been widely investigated for localization since maps can be pre-built very accurately. State of the art approaches often use dense maps or feature maps for localization. In this paper, we propose a road sign perception system for vehicle localization within a third party map. This is challenging since third party maps are usually provided with sparse geometric features which make the localization task more difficult in comparison to dense maps. The proposed approach extends the work in [2] where a localization system based on lane markings has been developed. Experiments have been conducted on a Highway-like test track using GNSS/INS with RTK corrections as ground truth (GT). Error evaluations are given as cross-track and along-track errors defined in the curvilinear coordinates [3] related to the map.

For an efficient integration of autonomous vehicles on roads, human-like reasoning and decision making in complex traffic situations are needed. One of the key factors to achieve this goal is the estimation of the future behavior of the vehicles present in the scene. In this work, we propose a new approach to predict the motion of vehicles surrounding a target vehicle in a highway environment. Our approach is based on an LSTM encoder-decoder that uses a social pooling mechanism to model the interactions between all the neighboring vehicles. The originality of our social pooling module is that it combines both local and non-local operations. The non-local multi-head attention mechanism captures the relative importance of each vehicle despite the inter-vehicle distances to the target vehicle, while the local blocks represent nearby interactions between vehicles. This paper compares the proposed approach with the state-of-the-art using two naturalistic driving datasets: Next Generation Simulation (NGSIM) and the new highD Dataset. The proposed method outperforms existing ones in terms of RMS values of prediction error, which shows the effectiveness of combining local and non-local operations in such a context.

Urban environments are among the most challenging scenarios for car-following systems, since pedestrians may interfere with the platoon unexpectedly. To address this problem, this paper proposes a cooperative system using vehicle-to-vehicle and vehicle-to-pedestrian communication links. A fractional-order control-based cooperative adaptive cruise control benefits of communication for tighter inter-vehicle distances, while pedestrian communication is fused with LiDAR sensing to allow the detection of occluded pedestrians. The prediction of the pedestrians' trajectories is used to perform a speed reduction or an emergency braking that interrupts the car-following yif necessary. Whenever a platoon decoupling occurs, a gap-closing maneuver is executed so that the ego-vehicle rejoins the platoon in a string stable way. The complete system was tested on experimental platforms at inria facilities, providing encouraging results and demonstrating the correct performance of the integrated systems.

Convolutional neural networks are designed for dense data, but vision data is often sparse (stereo depth, point clouds, pen stroke, etc.). We present a method to handle sparse depth data with optional dense RGB, and accomplish depth completion and semantic segmentation changing only the last layer. Our proposal efficiently learns sparse features without the need of an additional validity mask. We show how to ensure network robustness to varying input sparsities. Our method even works with densities as low as 0.8% (8 layer lidar), and outperforms all published state-of-the-art on the Kitti depth completion benchmark.

We present here a framework to integrate into a motion planning method the interaction zones of a moving robot with its future surroundings, the reachable interaction sets. It can handle highly dynamic scenarios when combined with path planning methods optimized for quasi-static environments. As a demonstrator, it is integrated here with an artificial potential field reactive method and with a Bézler curve path planning. Experimental evaluations show that this approach significantly improves dynamic path planning methods, especially when the speeds of the obstacles are higher than the one of the robot. The presented approach is used together with a global planning approach in order to handle complex static environments in presence of fast-moving obstacles. When the ego vehicle is not holonomic the presented approach is able to take dynamic constraints into account, which improve the prediction accuracy.

Simultaneous Localization And Mapping (SLAM) is one of the major bricks needed to build truly autonomous mobile robots. The probabilistic formulation of SLAM is based on two models: the motion model and the observation model. In practice, these models, together with the SLAM map representation, do not model perfectly the robot's real dynamics, the sensor measurement errors and the environment. Consequently, systematic errors affect SLAM estimations. In this paper, we propose two approaches to predict corrections to be applied to SLAM estimations. Both are based on the Ensemble Multilayer Perceptron model. The first approach uses successive estimated poses to predict the errors, with no assumptions on the underlying SLAM process or sensor used. The second method is specific to 2D likelihood SLAM approaches, thus, the likelihood distributions are used to predict the corrections, making this second approach independent of the sensor used. We also build a hybrid correction module based on successive estimated poses and the likelihood distributions. The validity of both approaches is evaluated through two experiments using different evaluation metrics and sensor configurations.

We present research using the latest reinforcement learning algorithm for end-to-end driving without any mediated perception (object recognition, scene understanding). The newly proposed reward and learning strategies lead together to faster convergence and more robust driving using only RGB image from a forward facing camera. An Asynchronous Actor Critic (A3C) framework is used to learn the car control in a physically and graphically realistic rally game, with the agents evolving simultaneously on tracks with a variety of road structures (turns, hills), graphics (seasons, location) and physics (road adherence). A thorough evaluation is conducted and generalization is proven on unseen tracks and using legal speed limits. Open loop tests on real sequences of images show some domain adaption capability of our method.

In this paper, a novel method of WiFi fingerprinting for localizing intelligent vehicles in GPS-denied area, such as car parks, is proposed. Although the method itself is a popular approach for indoor localization application, adapting it to the speed of vehicles requires different treatment. By deploying an ensemble neural network for fingerprinting classification, the method shows a reasonable localization precision at car park speed. Furthermore, a Gaussian Mixture Model (GMM) Particle Filter is applied to increase localization frequency as well as accuracy. Experiments show promising results with average localization error of 0.6m.

Learning from human driver's strategies for solving complex and potentially dangerous situations including interaction with other road users has the potential to improve decision-making methods for automated vehicles. In this paper, we focus on simple unsignalized intersections and roundabouts in presence of another vehicle. We propose a human-like decision-making algorithm for these scenarios built up from human drivers recordings. The algorithm includes a risk assessment to avoid collisions in the intersection area. Three road topologies with different interaction scenarios were presented to human participants on a previously developed simulation tool. The same scenarios have been used to validate our decision-making process. The algorithm showed promising results with no collisions in all setups and the ability to successfully determine to go before or after another vehicle.

In spite of the large number of existing methods, pedestrian detection remains an open challenge. In recent years, deep learning classification methods combined with multi-modality images within different fusion schemes have achieved the best performance. It was proven that the late-fusion scheme outperforms both direct and intermediate integration of modalities for pedestrian recognition. Hence, in this paper, we focus on improving the late-fusion scheme for pedestrian classification on the Daimler stereo vision data set. Each image modality, Intensity, Depth and Flow, is classified by an independent Convolutional Neural Network (CNN), the outputs of which are then fused by a Multi-layer Perceptron (MLP) before the recognition decision. We propose different methods based on Cross-Modality deep learning of CNNs: (1) a correlated model where a unique CNN is trained with Intensity, Depth and Flow images for each frame, (2) an incremental model where a CNN is trained with the first modality images frames, then a second CNN, initialized by transfer learning on the first one is trained on the second modality images frames, and finally a third CNN initialized on the second one, is trained on the last modality images frames. The experiments show that the incremental cross-modality deep learning of CNNs improves classification performances not only for each independent modality classifier, but also for the multi-modality classifier based on late-fusion. Different learning algorithms are also investigated.

With cooperative intelligent transportation systems, vulnerable road users (VRU) safety can be enhanced by multiple means. On the one hand, perception systems are based on embedded sensors to protect VRUs. However, such systems may fail due to the sensors' visibility conditions and imprecision. On the other hand, vehicle-to-pedestrian (V2P) communication can contribute to the VRU safety by allowing vehicles and pedestrians to exchange information. This solution is, however, largely affected by the reliability of the exchanged information, which most generally is the GPS data. Since perception and communication have complementary features, we can expect that a fusion between these two approaches can be a solution to the VRU safety. In this paper, we propose a cooperative system that combines the outputs of communication and perception. After introducing theoretical models of both individual approaches, we develop a probabilistic association between perception and V2P communication information by means of multi-hypothesis tracking. Experimental studies are conducted to demonstrate the applicability of this approach in real-world environments. Our results show that the cooperative VRU protection system can benefit of the redundancy coming from the perception and communication technologies both in line-of-sight (LOS) and non-LOS conditions. We establish that the performances of this system are influenced by the classification performances of the perception system and by the accuracy of the GPS positioning transmitted by the communication system.

Recently, the problem of fully autonomous navigation of vehicle has gained major interest from research institutes and private companies. In general, these researches rely on GPS in fusion with other sensors to track vehicle in outdoor environment. However, as indoor environment such as car park is also an important scenario for vehicle navigation, the lack of GPS poses a serious problem. This study presents an approach to use WiFi Fingerprinting as a replacement for GPS information in order to allow seamlessly transition of localization architecture from outdoor to indoor environment. Often, movement speed of vehicle in indoor environment is low (10-12km/h) in comparison to outdoor scene but still surpasses human walking speed (3-5km/h, which is usually maximum movement speed for effective WiFi localization). This paper proposes an ensemble classification method together with a motion model in order to deal with the above issue. Experiments show that proposed method is capable of imitating GPS behavior on vehicle tracking.

Nowadays, the development of Intelligent Transportation System (ITS) is increasing due to its versatility, adaptability and use of clean energy. There are a number of pass and on-going projects worldwide dealing with the different challenges and approaches to solve road transport-related issues. Some of them are dealing with the Cybernetic Transportation Systems (CTS), which is an urban mobility concept based on the automation of door-to-door transport systems i.e. the Cybercars as a two-passenger CTS. This paper presents the functional architecture of the CTSs and the development of an automated global planner. Specifically, a new approach that considers the automatization of the global planner stage, which allows path calculations and modifications in real time, considering on-demand stopping points. The experimental tests show a proper behaviour in our facilities at INRIA-Rocquencourt (France).

In this paper, we study a use of Visible Light Communication (VLC) technology for a platoon of autonomous vehicles. We present a low-cost, low-latency and simple outdoor VLC prototype, which can be installed as a vehicular tail-lighting system. The architecture of our VLC system is introduced, followed by performance evaluation with an especial attention on the VLC link resilience to ambient noise and communication range. Through the experiments, we observe that a use of proper optical filter stage at the receiver side, together with narrowing the transmitter Field-of-view (FOV), result in an extended communication range and make the VLC system more resilient to the ambient noises. Experimental results show that the system can provide 30 meters of inter-vehicle communication with 36 ms of latency, yet on sunny day conditions. The benefit of using the VLC system for platooning control is showed using a Simulink system that integrates our VLC platform for inter-communications to simulates the performance of autonomous vehicles platoon.

This paper examines the already commercially available Adaptive Cruise Controller (ACC) system, and its evolution by adding vehicle-to-vehicle communications: the cooperative ACC (CACC) version. The transition between ACC and CACC controllers will be done through the new control technique called Plug&Play. This technique is able to deal with living systems and the changes in its sensors and actuators to preserve the system stable. The aim is to ensure the system stability during transitions between controllers when the vehicle-to-vehicle communication link is changing from unavailable to available or vice versa.

Intelligent vehicles have increased their capabilities for highly and, even fully, automated driving under controlled environments. Scene information is received using onboard sensors and communication network systems, i.e., infrastructure and other vehicles. Considering the available information, different motion planning and control techniques have been implemented to autonomously driving on complex environments. The main goal is focused on executing strategies to improve safety, comfort, and energy optimization. However, research challenges such as navigation in urban dynamic environments with obstacle avoidance capabilities, i.e., vulnerable road users (VRU) and vehicles, and cooperative maneuvers among automated and semi-automated vehicles still need further efforts for a real environment implementation. This paper presents a review of motion planning techniques implemented in the intelligent vehicles literature. A description of the technique used by research teams, their contributions in motion planning, and a comparison among these techniques is also presented. Relevant works in the overtaking and obstacle avoidance maneuvers are presented, allowing the understanding of the gaps and challenges to be addressed in the next years. Finally, an overview of future research direction and applications is given.

Emerging ITS applications such as fleet management and point of interest distribution require vehicles to have Internet access. However, allowing vehicles to access to the Internet is particularly challenging due to the special characteristics of the vehicular environment. So far, multicasting approaches have been demonstrated to be effective for supporting group communication in traditional networks. However, such Internet-to-VANET multicast service involves several challenges including efficient multicast mobility management and multicast message delivery. This paper proposes a scheme that combines the existing multicast mobility management scheme with vehicular networking solutions to achieve Internet-to-VANET multicasting. The proposed scheme aims to: (i) provide multicast mobility management with low control overhead and efficient bandwidth utilization, as well as (ii) extend the service coverage provided by VANET membership management and multicast message delivery protocol. Simulation results indicate that our Motion-MAODV scheme improves the performance of both MAODV and traditional flooding dissemination schemes in terms of both packet delivery ratio and end-to-end transmission latency.

Power consumption and battery life are two of the key aspect when it comes to improve electric transportation systems autonomy. This paper describes the design, development and implementation of a speed profile generation based on the calculation of the optimal energy consumption for electric Cybercar vehicles for each of the stretches that are covering. The proposed system considers a commuter daily route that is already known. It divides the pre-defined route into segments according to the road slope and stretch length, generating the proper speed reference. The developed system was tested on an experimental electric platform at Inria's facilities, showing a significant improvement in terms of energy consumption for a pre-defined route.

Locate a vehicle in an urban environment remains a challenge for the autonomous driving community. By fusing information from a LIDAR, a Global Navigation by Satellite System (GNSS) and the vehicle odometry, this article proposes a solution based on evidential grids and a particle filter to map the static environment and simultaneously estimate the position in a global reference at a high rate and without any prior knowledge.

This paper considers the parallel parking problem of automatic front-wheel steering vehicles. The problem of stabilizing the vehicle at desired position and orientation is seen as an extension of the tracking problem. A saturated control is proposed which achieves quick steering of the system near the desired position of the parking spot with desired orientation and can be successfully used in solving parking problems. In addition, in order to obtain larger area of the starting positions of the vehicle with respect to the parking spot for the first reverse maneuver of the parallel parking, an approach of using saturated control with two different levels of saturation is proposed. The vehicle can be automatically parked by using one or multiple maneuvers, depending on the size of the parking spot. Simulation results are presented to confirm the effectiveness of the proposed control schemes.

Navigation in the Intelligent Transportation Systems (ITS) domain is still divided between reliable solutions that require heavy and costly set-ups and affordable solutions that still lack performances. By proposing a new method for Simultaneous Localisation and Mapping (SLAM) based on Transferable Belief Model (TBM), the authors aimed at finding a reasonable compromise for urban environment [1]. This article supports this choice and proposes a comparison between different laser set-ups to expose advantages and drawbacks of this solution.

From the early beginning, the Simultaneous Localization And Mapping (SLAM) problem has been approached using a probabilistic background. A new solution based on the Transferable Belief Model (TBM) framework is proposed in this article. It appears that this representation of knowledge affords numerous advantages over the classic probabilistic ones and leads to particularly good performances (an average of 3.2% translation drift and 0.0040deg/m rotation drift), especially when it comes to crowded environment. By introducing the basic concepts of a Credibilist SLAM, this article aims at proving that the use of this new theoretical context opens a lot of perspectives for the SLAM community.

Vehicle and pedestrian collisions often result in fatality to the vulnerable road users, indicating a strong need of technologies to protect such vulnerable road users. Wireless communications have potential to support road safety by enabling road users to exchange information. In contrast to vehicle to vehicle (V2V) and vehicle to infrastructure (V2I) communications for avoidance of inter-vehicle collisions, very limited efforts are made on communication mechanisms for pedestrian safety. This paper addresses the issue in a concrete way. We first formulate the requirement of the minimum information exchange distance for providing road users to have the necessary amount of time to perceive the situation and react. We then report our field tests and measurement based analysis to investigate if a Wi-Fi system can satisfy the application requirement. We also introduce a pedestrian protection application, V2ProVu, which provides the functionalities of the Wi-Fi communications, risk calculation, and hazard alarming. Our study discloses several useful insights including 1) information exchange for a velocity of 80 km/h has to be made before vehicle to pedestrian (V2P) distance is below 72 meters and 2) while this requirement is not too hard for radio communications technologies, the V2P communication range is greatly reduced if the signal is blocked by a human body.

In car-sharing applications and during certain time slots, some parking parks become full whereas others are empty. To redress this imbalance, vehicle redistribution strategies must be elaborated. As automatic relocation cannot be in place, one alternative is to get a leader vehicle, driven by a human, which come to pick up and drop off vehicles over the stations. This paper deals with the vehicle redistribution problem among parking using this strategy and focuses on automatic parking and vehicle's platooning. We present an easy exit parking controller and path planning based only on geometric approach and vehicle's characteristics. Once the vehicle exits the parking, it joins a platoon of vehicles and follows it automatically to go to an empty parking space.

Automated functions for real scenarios have been increasing in last years in the automotive industry. Many research contributions have been done in this field. However, other problems have come to the drivers: When should they (the drivers or the new automated systems) be able to take control of the vehicle? This question has not a simple answer; it depends on different conditions, such as: the environment, driver condition, vehicle capabilities, fault tolerance, among others. For this reason, in this work we will analyze the acceptability to the ADAS functions available in the market, and its relation with the different control actions. In this paper a survey on arbitration and control solutions in ADAS is presented. It will allow to create the basis for future development of a generic ADAS control (the lateral and longitudinal behavior), based on the integration of the application request, the driver behavior and driving conditions in the framework of the DESERVE project (DEvelopment platform for Safe and Efficient dRiVE1, a ARTEMIS project 2012–2105). The main aim of this work is to allow the development of a new generation of ADAS solutions where the control could be effectively shared between the vehicle and the driver. Different solutions of shared control have been analyzed. A first approach is proposed, based on the presented solutions.

In this paper, an algorithm for dynamic path generation in urban environments is presented, taking into account structural and sudden changes in straight and bend segments (e.g. roundabouts and intersections). The results present some improvements in path generation (previously hand plotted) considering parametric equations and continuous-curvature algorithms, which guarantees a comfortable lateral acceleration. This work is focused on smooth and safe path generation using road and obstacle detection information. Finally, some simulation results show a good performance of the algorithm using different ranges of urban curves. The main contribution is an Intelligent Trajectory Generator, which considers infrastructure and vehicle information. This method is recently used in the framework of the project CityMobil21, for urban autonomous guidance of Cybercars.

Local mapping is valuable for many real-time applications of intelligent vehicle systems. Multivehiclecooperative local mappingcan bring considerable benefits to vehicles operating in some challenging scenarios. In this paper, we introduce a method of occupancy grid map merging, dedicated to multivehicle cooperative local mapping purpose in outdoor environments. In a general map merging framework, we propose an objective function based on occupancy likelihood and provide some concrete procedures designed in the spirit of genetic algorithm to optimize the defined objective function. Based on the introduced method, we further describe a strategy of indirect vehicle-to-vehicle (V2V) relative pose (RP) estimation, which can serve as a general solution for multivehicle perception association. We present a variety of experiments that validate the effectiveness of the proposed occupancy grid map merging method. We also demonstrate several useful application examples of the indirect V2V RP estimation strategy.

In this paper, we present a mathematical model and adaptive controller for an autonomous vehicle overtaking maneuver. We consider the problem of an autonomous three-phase overtaking without the use of any roadway marking scheme or intervehicle communication. The developed feedback controller requires information for the current relative intervehicle position and orientation, which are assumed to be available from onboard sensors. We apply standard robotic nomenclature for translational and rotational displacements and velocities and propose a general kinematic model of the vehicles and the relative intervehicle kinematics during the overtaking maneuver. The overtaking maneuver is investigated as a tracking problem with respect to desired polynomial virtual trajectories for every phase, which are generated in real time. An update control law for the automated overtaking vehicle is designed that allows tracking the desired trajectories in the presence of unknown velocity of the overtaken vehicle. Simulation results illustrate the performance of the proposed controller.

In this paper, we present a two-layer nonlinear adaptive steering controller for autonomous lane change maneuver with respect to a stopped vehicle. First, we derive a dynamic model of the vehicle using the Boltzmann-Hamel method in quasi-coordinates for nonholonomic systems. The lane change maneuver is investigated as a tracking problem with respect to desired cycloidal trajectory, which is generated in real time. An adaptive update control law is designed that allows tracking the desired trajectories in the presence of unknown inertial parameters of the vehicle. Simulation results illustrate the performance of the proposed controller.

Personal Mobility Vehicles (PMV) is is an important part of the Intelligent Transportation System (ITS) domain. These new transport systems have been designed for urban traffic areas, pedestrian streets, green zones and private parks. In these areas, steps and curbs make the movement of disable or mobility reduced people with PMV, and with standard chair wheels difficult. In this paper, we present a step and curb detection system based on laser sensors. This system is dedicated to vehicles able to cross over steps, for transportation systems, as well as for mobile robots. The system is based on the study of the first derivative of the altitude and highlights the use of a new algebraic derivative method adapted to laser sensor data. The system has been tested on several real scenarios. It provides the distance, altitude and orientation of the steps in front of the vehicle and offers a high level of precision, even with small steps and challenging scenarios such as stairs.

Traffic Sign Recognition (TSR) is now relatively well-handled by several approaches. However, traffic signs are often completed by one (or several) supplementary sign(s) placed below. They are essential for correct interpretation of main sign, as they specify its applicability scope. The main difficulty of supplementary sub-sign recognition is the potentially infinite number of classes, as nearly any information can be written on them. In this paper, we propose and evaluate a hierarchical approach for recognition of supplementary signs, in which the “meta-class” of the sub-sign (Arrow, Pictogram, Text or Mixed) is first determined. The classification is based on the pyramid-HOG feature, completed by dark area proportion measured on the same pyramid. Evaluation on a large database of images with and without supplementary signs shows that the classification accuracy of our approach reaches 95% precision and recall. When used on output of our sub-sign specific detection algorithm, the global correct detection and recognition rate is 91%.

Data fusion is an important process in a variety of tasks in the intelligent transportation systems field. Most existing data fusion methods rely on the assumption of conditional independence or known statistics of data correlation. In contrast, the split covariance intersection filter (split CIF) was heuristically presented in literature, which aims at providing a mechanism to reasonably handle both known independent information and unknown correlated information in source data. In this paper, we provide a theoretical foundation for the split CIF. First, we clearly specify the consistency definition (coined as split consistency) for estimates in split form. Second, we provide a theoretical proof for the fusion consistency of the split CIF. Finally, we provide a theoretical derivation of the split CIF for the partial observation case. We also present a general architecture of decentralized vehicle localization, which serves as a concrete application example of the split CIF to demonstrate the advantages of the split CIF and how it can potentially benefit vehicle localization (noncooperative and cooperative). In general, this paper aims at providing a baseline for researchers who might intend to incorporate the split CIF (a useful tool for general data fusion) into their prospective research works.

Autonomous mapping, especially in the form of SLAM (Simultaneous Localization And Mapping), has long since been used for many indoor robotic applications and is also useful in outdoor intelligent vehicle applications such as object detection. Most existing research works on environment mapping and object detection in outdoor applications have been dedicated to single vehicle system. On the other hand, multi-vehicle cooperative perception based on inter-vehicle data sharing can bring considerable benefits in many scenarios that are challenging for a single vehicle system. In this paper, a new method for occupancy grid maps merging is proposed: an objective function based on occupancy likelihood is introduced to measure the consistency degree of maps alignment; genetic algorithm implemented in a dynamic scheme is adopted to optimize the objective function. A scheme of multi-vehicle cooperative local mapping and moving object detection using the proposed occupancy grid maps merging method is also introduced. Real-data tests are given to demonstrate the effectiveness of the introduced method.

This article tackles the problem of the autonomous navigation and coordination of multiple driverless vehicles for the transport of persons or goods in outdoor environments. The system composed of fully automated road vehicles, capable of providing an effective transportation service, was recently tested at the city of La Rochelle. This same system was further improved, and a new demonstration was performed at Inria Rocquencourt, in order to demonstrate the validity of the concepts for a coordinated navigation in the presence of ambiguous and conflictual situations in a mixed environment. The originality of the approach relies on the use of new cooperative concepts and their combination with advanced perception tasks operating simultaneously on several robots. This system was developed in the context of the European project CityMobil.

In this paper, we present the architecture of an innovative docking station for electric vehicles recharging and a hybrid control scheme for automatic docking of the vehicles. This work is a part of on-going project concerning the development of a smart charging station for electric vehicles equipped with an automated arm, which connect the vehicle to the charging station, and an infrared beacon system for localizing the automatically maneuvering vehicle in the docking area. The proposed control scheme combines time-optimal (bang-bang) control with continuous time-invariant nonlinear control, which stabilizes the vehicle to a small neighborhood of the docking point. Simulation and experimental results illustrate the effectiveness of the proposed controller.

Vehicle localization (ground vehicles) is an important task for intelligent vehicle systems and vehicle cooperation may bring benefits for this task. A new cooperative multi-vehicle localization method using split covariance intersection filter is proposed in this paper. In the proposed method, each vehicle maintains an estimate of a decomposed group state and this estimate is shared with neighboring vehicles; the estimate of the decomposed group state is updated with both the sensor data of the ego-vehicle and the estimates sent from other vehicles; the covariance intersection filter which yields consistent estimates even facing unknown degree of inter-estimate correlation has been used for data fusion. A comparative study based simulations demonstrate the effectiveness and the advantage of the proposed cooperative localization method.

In this paper, we describe our approach for intersection safety developed in the scope of the European project INTERSAFE-2. A complete solution for the safety problem including the tasks of perception and risk assessment using on-board lidar and stereo-vision sensors will be presented and interesting results are shown.

The objective of the CityMobil project is to achieve a more effective organisation of urban transport, resulting in a more rational use of motorised traffic with less congestion and pollution, safer driving, a higher quality of living and an enhanced integration with spatial development. This objective is brought closer by developing integrated traffic solutions: advanced concepts for innovative autonomous and automated road vehicles for passengers and goods, embedded in an advanced spatial setting. This paper presents the automated road vehicles service demonstration to be held in La Rochelle in 2011.

In a scene, rain produces a complex set of visual effects. Obviously, such effects may infer failures in outdoor vision-based systems which could have important side-effects in terms of security applications. For the sake of these applications, rain detection would be useful to adjust their reliability. In this paper, we introduce the problem (almost unprecedented) of unfocused raindrops. Then, we present a first approach to detect these unfocused raindrops on a transparent screen using a spatio-temporal approach to achieve detection in real-time. We successfully tested our algorithm for Intelligent Transport System (ITS) using an on-board camera and thus, detected the raindrops on the windscreen. Our algorithm differs from the others in that we do not need the focus to be set on the windscreen. Therefore, it means that our algorithm may run on the same camera sensor as the other vision-based algorithms.

Global localization aims to estimate a robot's pose in a learned map without any prior knowledge of its initial pose. Achieving highly accurate global localization remains a challenge for autonomous mobile robots especially in large-scale unstructured outdoor environments. This paper introduces a real-time reliable global localization approach with the capability of addressing the kidnapped robot problem using only laser sensors. Our approach includes four steps: 1) local Simultaneous Localization and Mapping 2) map matching 3) position tracking and 4) localization quality evaluation. For sensor perception, we use occupancy grid method to represent robot environment. A novel pyramid grid-map based coarse-to-fine matching approach is proposed to improve the localization accuracy. Experimental results including an outdoor environment of 25, 000 m2are presented to validate the feasibility and reliability of the proposed approach.

In this paper, we will present the design and the implementation of a new generation of maps specially designed for the ADAS-like applications. We will focus on the design of the map, the data structure and the choice of road attributes. We will present also the design of a software that enables our intelligent vehicle to perform as a mapping system for advanced attributes acquisition.

For most tracking applications the Kalman filter is reliable and efficient, but it is limited to a relatively restricted class of linear Gaussian problems. Particle filters are proving to be dependable methods for stochastic dynamic estimation. We will present in this paper, an accurate localization strategy for vehicles in urban environments based on the particle filters, the communication between vehicles and the vision systems when GPS data is unavailable or has a poor quality of signal due to the multi-tracks or bad satellite visibility. The method relies on the particle filter for the treatment of the GPS data and the vision data that will be collected from the loading system in the vehicles. From the modelling point of view, a particularity of the method is due to the use of vision systems and the communication through a wireless communication devices. The experiments on our fleet of communicating vehicles carried out in real conditions prove the feasibility of this approach.

Human beings do not have well defined shapes neither well defined behaviors. In dense outdoor environments, they are as a consequence hard to detect and algorithms based on a single sensor tend to produce lot of wrong detections. Moreover, many applications require algorithms that work very fast on CPU limited mobile architectures while remaining able to detect, track and classify objects as people with a very high precision. We present an algorithm based on the contribution of a range finder and a vision based algorithm that addresses these three constraints: efficiency, velocity and robustness and that we believe is scalable to a large variety of applications.

In this paper we introduce a real-time traffic light recognition system for intelligent vehicles. The method proposed is fully based on image processing. Detection step is achieved in grayscale with spot light detection, and recognition is done using our generic ¿adaptive templates¿. The whole process was kept modular which make our TLR capable of recognizing different traffic lights from various countries. To compare our image processing algorithm with standard object recognition methods we also developed several traffic light recognition systems based on learning processes such as cascade classifiers with AdaBoost. Our system was validated in real conditions in our prototype vehicle and also using registered video sequence from various countries (France, China, and U.S.A.). We noticed high rate of correctly recognized traffic lights and few false alarms. Processing is performed in real-time on 640x480 images using a 2.9 GHz single core desktop computer.

Because pedestrians have neither well defined shapes nor well defined behaviors, detecting and tracking them from a moving vehicle remains a difficult task. To serve as an onboard driver assistance system, a perception algorithm also needs to be both fast and robust. We present in this paper a system that reaches a good level of reliability by efficiently combining the data of two sensors - a laser scanner and a camera - while remaining tractable on CPU limited mobile architectures.

In this paper we present a system for three-dimensional environment modeling. It consists of an instrumented vehicle equipped with a 2D laser range scanner for data mapping, and GPS, INS and odometers for vehicle positioning and attitude information. The advantage of this system is its ability to perform data acquisition during the vehicle navigation; the sensor needed being a basic 2D scanner with opposition to traditional expensive 3D sensors. This system integrates the laser raw range data with the vehicle's internal state estimator and is capable of reconstructing the 3D geometry of the environment by real-time geo-referencing. We propose a high level representation of the urban scene while identifying automatically and in real time some types of existing objects in this environment. Thus, our modeling is articulated around three principal axes: the segmentation, decimation, the 3D reconstruction and visualization. The road is the most important object for us; some road features like the curvature and the width are extracted.

This paper presents a 3D navigation subsystem providing specific treatments needed for the perception and the navigation of an all-terrain mobile robot. This subsystem was developed and integrated in the global framework of the EDEN experimentation. After a brief description of this outdoor navigation experimentation, we describe the natural environment representations we use. Two important perception functions based on 3D data are involved here: fast construction of elevation maps and robot localization. We then describe the 3D motion planner dedicated to the navigation on rugged terrains. The current state of integration of the experiment is finally presented by the mean of experimental results obtained from the natural environment of the mobile robot ADAM.>

As an autonomous robot navigates in an unknown environment, the perception subsystem must be able to perform the incremental modeling of this environment as well as robot self-location. In this paper, the authors have chosen to combine a polyhedral representation of the world with its digital elevation model, in order to deal with autonomous navigation in semi-structured environments. The authors describe algorithms needed to build snapshot models from noisy and sparse range data, to perform 3D data fusion between these snapshot models, in order to incrementally build a reliable 3D model from which a path planner could generate safe trajectories. The authors present a fully implemented modeling strategy based on range data processing, and describe the different modeling services required in order to perform the indoor scene navigation of the robot HILARE-2.

The authors consider the perception subsystem of an autonomous mobile robot which must be able to navigate in 3D terrain. They describe their approach to building a rough geometric model of a 3D terrain accounting for the locomotion capabilities of the vehicle, using a laser range finder. This model may be used as direct input for the robot's path planner. The terrain model relies on two grid-based representations: the local elevation map and the local navigation map. Both are incrementally built at arbitrary resolution using new interpolation and localization methods and other 3D vision techniques. The authors validate the proposed approach by presenting some comprehensive results using real range images of an indoor structured environment.>