Advanced driver assistance systems (ADAS) and automated driving functions are becoming integral to modern vehicles. Ensuring their safety and reliability requires validating their operation within well-defined Operational Design Domains (ODD). Monitoring ODD compliance is crucial to determine when these functions can operate safely. This paper presents a systematic approach to ODD monitoring using a formalized, machine-readable ODD description and fuzzy logic. The method evaluates compliance and provides explanations for non-compliance. The approach introduces a two-level hierarchical ODD representation, a membership score quantifying compliance, and an explanation mechanism for identifying the primary factors contributing to non-compliance. The monitoring results are integrated into a Conditional Activation Control System (CACS), which governs function activation based on ODD compliance. The proposed system was implemented within a production vehicle and validated using real-world data, demonstrating its feasibility for deployment. By enabling clear, real-time assessments of ODD adherence, this approach supports safer and more reliable automated driving, promoting user confidence and regulatory compliance.

Driving autonomously in diverse environments remains a significant challenge, especially when transitioning between regions with distinct traffic cultures and regulations. While human drivers exhibit remarkable adaptability through experiential learning and cognitive modeling, current data-driven autonomous systems often struggle with environmental adaptation, interpretability, and continuous learning capabilities. In this work, we present LoDriver (Local Driver), a novel knowledge-based architecture that enhances the conventional scene understanding-decision-planning paradigm through cognitive-inspired dual-process reasoning for path planning. LoDriver integrates a reactive process and a deliberative mechanism, processing multi-modal scene descriptions through parallel pathways. It maintains a structured memory module that dynamically accumulates driving experiences, traffic regulations, and knowledge, enabling experience-based decision-making and continuous learning through systematic memory updates. Experimental evaluation on the nuScenes dataset demonstrates LoDriver's interpretability and enhanced performance compared to existing knowledge-driven models, highlighting its advantage in operating across different environments.

This study addresses the critical need for refined, reliable, and complete real-world trajectory data in the de-velopment of Advanced Driver Assistance Systems (ADAS), particularly for Adaptive Cruise Control (ACC) functions. We conducted a comprehensive comparison of car-following and deceleration scenarios across ten open-source datasets from multiple countries, encompassing both highway and urban environments. Focusing on key kinematic variables crucial for longitudinal behavior, we employed statistical measures and safety metrics to compare data sets across different driving regulations and road designs. Our findings reveal substantial overlaps in the distributions of logical parameters, despite the varied data sources and cultural contexts. However, we noted significant differences in safety-critical metrics, such as Time Headway and Time To Collision (TTC), highlighting culture-specific driving behaviors. Interestingly, Chinese datasets consistently exhibited the smallest distance head ways across all scenarios, yet maintained high TTC values (around 16s) compared to other datasets, suggesting a unique approach to risk management. To quantify these differences, we calibrated the Intelligent Driver Model using U.S. data and evaluated its transferability, demonstrating remarkable performance degradation when applied to non-U.S. datasets. These results provide crucial insights for developing globally applicable, yet culturally sensitive safety assessment methodologies for next-generation automated vehicles, highlighting the need for adaptive ADAS technologies that can accommodate regional driving norms while maintaining consistent safety standards. The code and extracted Longitudinal Trajectory data used in this study are available: https://github.com/imanetaourarti/Car-Following-analysis.

Autonomous systems use independent decision-making with only limited human intervention to accomplish goals in complex and unpredictable environments. As the autonomy technologies that underpin them continue to advance, these systems will find their way into an increasing number of applications in an ever wider range of settings. If we are to deploy them to perform safety-critical or mission-critical roles, it is imperative that we have justified confidence in their safe and correct operation. Verification is a key process for establishing such confidence. However, autonomous systems pose challenges to existing verification practices. This paper highlights viewpoints of the Roadmap Working Group of the IEEE Robotics and Automation Society Technical Committee for Verification of Autonomous Systems, identifying these grand challenges, and providing a vision for future research efforts that will be needed to address them.

Advanced Driver Assistance Systems (ADAS) are rapidly becoming a standard feature in modern road vehicles, enhancing safety and driver comfort. As ADAS adoption expands across diverse geographical and cultural regions, the performance of camera-based perception systems may vary significantly due to environmental and expected social behaviour of the different actors. This paper explores the referred factors and evaluates the traffic environment complexity for vehicles with different levels of automation. In particular, we propose a novel modeling and quantitative assessment approach for environment complexity. Specifically, we compare a perception model trained on United States dataset with a dataset from India, a nation characterized by unique traffic patterns, signage conventions, and cultural norms to assess its performance variation, and to lay the basis for proposing influencing factors of traffic environment complexity. We establish a scheme of referential and additional static factors and based on an expert evaluation, environment complexity is established. The effectiveness of the proposed approach is testified by naturalistic driving data. These findings pave the way for future research in intelligent driving and emphasize the importance of addressing cultural nuances as vehicle automation levels increase.

For vehicles to navigate autonomously, they need to perceive and understand their immediate surroundings. Currently, cameras are the preferred sensors, due to their high performance and relatively low-cost compared with other sensors like LiDARs and Radars. However, their performance is limited by inherent imaging constraints, a standard RGB camera may perform poorly in extreme conditions, including low illumination, high contrast, bad weather (e.g. fog, rain, snow, etc.), glare, etc. Further, when using monocular cameras, it is more challenging to determine spatial distances than when using active range sensors such as LiDARs or Radars. Over the past years, novel image sensors, namely, infrared cameras, range-gated cameras, polarization cameras, and event cameras, have demonstrated strong potential. Some of them could be game-changers for future autonomous vehicles, they are the result of progress in sensor technology and the development of the accompanying perception algorithms. This paper presents in a systematic manner their principles, comparative advantages, data processing algorithms, and related applications. The purpose is to provide practitioners with an in-depth overview of novel sensing technologies that can contribute to the safe deployment of autonomous vehicles.

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.

By transmitting lasers and processing laser returns, LiDAR (light detection and ranging) perceives the surrounding environment through distance measurements. Because of high ranging accuracy, LiDAR is one of the most critical sensors in autonomous driving systems. Revolving around the 3D point clouds generated from LiDARs, plentiful algorithms have been developed for object detection/tracking, environmental mapping, or localization. However, a LiDAR’s ranging performance suffers under adverse weather (e.g. fog, rain, snow etc.), which impedes full autonomous driving in all weather conditions. This article focuses on analyzing the performance of a typical time-of-flight (ToF) LiDAR under fog environment. By controlling the fog density within CEREMA Adverse Weather Facility, the relations between the ranging performance and fogs are both qualitatively and quantitatively investigated. Furthermore, based on the collected data, a machine learning based model is trained to predict the minimum fog visibility that allows successful ranging for this type of LiDAR. The revealed experimental results and methods are helpful for ToF LiDAR specifications from automotive industry.

Deployment of SAE Level 3+ automated vehicles faces validation and certification challenges due to uncertainty and state space size of the operating domain. We propose a validation and testing methodology that aims to minimize unknown unknowns through minimization of scenarios that have not been accounted for, and scenarios that have not been identified due to modeling deficiencies. The methodology utilizes simulators with different levels of fidelity for residual risk handling, functional hierarchies for simplification of complex navigation tasks, and the Backtracking Process Algorithm to identify scenarios of risk significance. The methodology is demonstrated on a scenario with an intersection preceded by a traffic light. Through use of the testing flowchart, we were able to identify and remedy scenarios leading to undesirable events.

The deployment of autonomous vehicles requires safety assurance and performance guarantees of the developed system. However, this is complex due to the number of scenario variations and uncertainty associated with the operating environment. To alleviate this challenge, we propose a model-based validation methodology that relies on a functional hierarchy for the breakdown and simplification of the system navigation functions, and the Backtracking Process Algorithm to identify, trace, and probabilistically quantify risk significant event sequences (scenarios) that lead to Top Events of interest (such as requirement violations). This methodology is demonstrated on a scenario with an occluded pedestrian crossing the road. We are able to identify risks associated with the actor classification problem and sudden changes in behavior of the pedestrian.

For a vehicle to navigate autonomously, it needs to perceive its surroundings and estimate the future state of the relevant traffic-agents with which it might interact as it navigates across public road networks. Predicting the future state of the perceived entities is a challenge, as these might appear to move in a stochastic manner. However, their motion is constrained to an extent by context, in particular the road network structure. Conventional machine learning methods are mainly trained using data from the perceived entities without considering roads, as a result trajectory prediction is difficult. In this paper, the notion of maps representing the road structure are included into the machine learning process. For this purpose, 3D LiDAR points and maps in the form of binary masks are used. These are used on a recurrent artificial neural network, the LSTM encoder-decoder based architecture to predict the motion of the interacting traffic agents. A comparison between the proposed solution with one that is only sensor driven (LiDAR) is included. For this purpose, NuScenes dataset is utilised, that includes annotated 3D point clouds. The results have demonstrated the importance of context to enhance our prediction performance as well as the capability of our machine learning framework to incorporate map information.

Automotive systems must undergo a strict process of validation before their release on commercial vehicles. With the increased use of probabilistic approaches in autonomous systems, standard validation methods are not applicable to this end. Furthermore, real life validation, when even possible, implies costs which can be obstructive. New methods for validation and testing are thus necessary. In this paper, we propose a generic method to evaluate complex probabilistic frameworks for autonomous driving. The method is based on Statistical Model Checking (SMC), using specifically defined Key Performance Indicators (KPIs), as temporal properties depending on a set of identified metrics. By studying the behavior of these metrics during a large number of simulations via our statistical model checker, we finally evaluate the probability for the system to meet the KPIs. We show how this method can be applied to two different subsystems of an autonomous vehicle: a perception system and a decision-making approach. An overview of these two systems is given to understand related validation challenges. Extensive validation results are then provided for the decision-making case.

As drivers approach a road intersection, they must decide whether to cross it or to come to a stop. For this purpose, drivers make a situation assessment and adapt their behaviour accordingly. When this task is performed by a computer, the available information is partial and uncertain. Any decision requires the system to use this information as well as taking into account the behaviour of other drivers to avoid collisions. Common metrics such as collision rate can remain low in an interactive environment because of other driver's actions. Consequently, evaluation metrics must depend on other driving aspects. In this paper a decision-making mechanism and metrics to evaluate such a system at road intersection crossing are presented. For the former, a Partially Observable Markov Decision Process is used to model the system with respect to uncertainties in the behaviour of other drivers. For the latter, different key performance indicators are defined to evaluate the resulting behaviour of the system with different configurations and scenarios. The approach is demonstrated within an automotive grade simulator. It has showed at times, that whilst the vehicle can cross safely the intersection, it might not satisfy other key performance indicators related to highway code.

When approaching a road intersection, drivers consider several factors and choose amongst different likely manoeuvres. For an autonomous agent, it is fundamental to understand what other drivers are doing before deciding their own manoeuvres. These are seldom be the same as intersections differ and the situations too. Whilst, learning techniques can be used to process features of trajectories and to predict manoeuvres of others cars. The problem with such approaches is the difficult process of recording data for each intersection, not only of the subject vehicle but of the other vehicles. To address this problem, a hybrid data set was constructed. It is built in a simulated environment and completed with real data after has driven multiple times across the intersection. To analyze these data, classification technique is used to find the common range of features for each manoeuvre. Random forest classifiers are used in conjunction with our functional discretization to analyze the trajectories of cars approaching an intersection. The classifiers can determine the longitudinal manoeuvre as well as the direction. We show how our approach performs compared to other classifiers and space discretization. In addition, we demonstrate the impact and the usefulness of the mixture between simulated and real data. An improvement of 30% accuracy is obtained with the hybrid data set, and 5% using our functional discretization with respect to baseline approach.

An Automated Driving System (ADS) is subject to hazardous weather conditions and to failures, both of which can result in a partial or total loss of its ability to monitor the driving environment. Yet until high driving automation and full driving automation is achieved, a human driver is expected to respond appropriately to any malfunction or adverse on-road conditions preventing the ADS from reliably sustaining the dynamic driving task performance. However, automation causes drowsiness and hypo-vigilance, which can compromise a human driver's ability to respond to ADS-issued requests. Hence the necessity of defining dynamic driving task fallback strategies that can be performed by the ADS, if and when necessary. The proposed fallback strategy is aimed at level 4 ADS features designed to operate a vehicle on a road whose characteristics make any attempt at stopping hazardous. It naturally applies to level 5 ADS-operated vehicles and to ADS-dedicated vehicles as well. The transition stage, during which the strategy is triggered, consists in the replacement of missing vehicles and obstacles in the world model with ghost objects. An embedded visibility map is then used to retrieve the maximum distance at which the ADS-operated vehicle can be seen, when driving behind it. The speed profile underlying the fallback strategy meets a time to collision criterion of 4 s, which enables the avoidance and the mitigation of rear-end collisions. The behaviour of drivers in collision imminent situations cannot be observed in test track studies due to safety concerns. As a result, experiments were conducted in the driving simulation software SCANeR studio.

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.

Modern vehicles embed an increasing number of Advanced Driving Assistance Systems (ADAS). Whilst such systems showed their capability to improve comfort and safety, most of them provide assistance only as a last resort, that is, they alert the driver or trigger automatic braking only when collision is imminent. This limitation is mainly due to the difficulty to accurately anticipate risk situations in order to provide the driver with preventive assistance, i.e. assistance allowing for comfortable reaction. This paper presents a Bayesian framework which aims to detect risk situations sufficiently early to trigger conventional curative assistance as well as preventive assistance. By taking into consideration the context, the vehicle state, the driver actuation and the manner how the driver usually negotiates given situations, the framework allows to infer which type of assistance is the most pertinent to be provided to the driver. The principles of this framework are applied to a fundamental case study, the arrival to a stop intersection. Results obtained from data recorded under controlled conditions are presented. They show that the framework allows to coherently detect risk situations and to identify what assistance, including preventive assistance, is the most appropriate for the situation.

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.

Within a vehicle driving space, different entities such as vehicles and vulnerable road users are in constant interaction which governs their behaviour. Whilst smart sensors provide information about the state of the perceived objects, considering the spatio-temporal relationships between them with respect to the subject vehicle remains a challenge. This paper proposes to fill this gap by using contextual information to infer how perceived entities are expected to behave, and thus what are the consequences of these behaviours on the subject vehicle. For this purpose, an ontology is formulated about the vehicle, perceived entities and context (map information) to provide a conceptual description of all road entities with their interaction. It allows for inferences of knowledge about the situation of the subject vehicle with respect to the environment in which it is navigating. The framework is applied to the navigation of a vehicle as it approaches road intersections, to demonstrate its applicability. Results from the real-time implementation on a vehicle operating under controlled conditions are included. They show that the proposed ontology allows for a coherent understanding of the interactions between the perceived entities and contextual data. Further, it can be used to improve the situation awareness of an ADAS (Advanced Driving Assistance System), by determining which entities are the most relevant for the subject vehicle navigation.

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.

Advanced Driving Assistance Systems usually provide assistance to drivers only once a high risk situation has been detected. Indeed, it is difficult for an embedded system to understand driving situations, and to predict early enough that it is to become uncomfortable or dangerous. Most of ADAS work assume that interactions between road entities do not exist (or are limited), and that all drivers react in the same manner in similar conditions. We propose a framework that enables to fill these gaps. On one hand, an ontology which is a conceptual description of entities present in driving spaces is used to understand how all the perceived entities interact together with the subject vehicle, and govern its behavior. On the other hand, a dynamic Bayesian Network enables to estimate the driver situation awareness with regard to the perceived objects, based on the ontology inferences, map information, driver actuation and driving style.

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.

This paper proposes a novel approach to risk assessment at road intersections. Unlike most approaches in the literature, it does not rely on trajectory prediction. Instead, dangerous situations are identified by comparing what drivers intend to do with what they are expected to do. Driver intentions and expectations are estimated from the joint motion of the vehicles, taking into account the layout of the intersection and the traffic rules at the intersection. The proposed approach was evaluated in simulation with two vehicles involved in typical collision scenarios. An analysis of the collision prediction horizon allows to characterize the efficiency of the approach in different situations, as well as the potential of different strategies to avoid an accident after a dangerous situation is detected.

Intersections are the most complex and hazardous areas of the road network, and 89% of accidents at intersection are caused by driver error. We focus on these accidents and propose a novel approach to risk assessment: in this work dangerous situations are identified by detecting conflicts between intention and expectation, i.e. between what drivers intend to do and what is expected of them. Our approach is formulated as a Bayesian inference problem where intention and expectation are estimated jointly for the vehicles converging to the same intersection. This work exploits the sharing of information between vehicles using V2V wireless communication links. The proposed solution was validated by field experiments using passenger vehicles. Results show the importance of taking into account interactions between vehicles when modeling intersection situations.

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.

Safety applications at road intersections require algorithms that can estimate the manoeuvre intention of all the drivers in the scene. In this paper, the use of contextual information extracted from a digital map of the road network is explored. We propose a Bayesian network which combines probabilistically uncertain observations on the vehicle's behaviour and information about the geometrical and topological characteristics of the road intersection in order to infer a driver's manoeuvre intention. The approach is evaluated on trajectories recorded from real traffic, including complex scenarios where the behaviour of the vehicle is inconsistent. We define an evaluation method that accounts for the impossibility to make reliable predictions in some situations, and show that the system is able to reliably combine vehicle state information and map information to infer a driver's intended manoeuvre.

As an increasing number of automatic safety and navigation features are added to modern vehicles, the crucial job of providing real-time localisation is predominantly performed by a single sensor, GPS, despite its well-known failings, particularly in urban environments. Various attempts have been made to supplement GPS to improve localisation performance, but these usually require additional specialised and expensive sensors. Offering increased value to vehicle OEMs, we show that it is possible to use just the video stream from a rear parking camera to produce smooth and locally accurate visual odometry in real-time. We use an efficient whole image alignment approach based on ESM, taking account of both the difficulties and advantages of the fact that a parking camera views only the road surface directly behind a vehicle. Visual odometry is complementary to GPS in offering localisation information at 30 Hz which is smooth and highly accurate locally whilst GPS is course but offers absolute measurements. We demonstrate our system in a large scale experiment covering real urban driving. We also present real-time fusion of our visual estimation with automotive GPS to generate a commodity-cost localisation solution which is smooth, accurate and drift free in global coordinates.

]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.

Conventionally GPS receivers and odometers are used in localization systems for ground vehicles/robots due to cost constraints. When these are deployed in urban conditions, multi-path and wheel slippage often result in large localization estimation errors. In this paper, pattern recognition techniques are employed to improve the localization estimates of a loosely coupled GPS-odometer solution. The presented method filters out from the fusion process false GPS estimates and uses extensively information on the vehicle ego-state. The approach comprises three phases. First, a detection algorithm is used to recognize likely false GPS estimates, which are then excluded from Kalman Filter updates. Second, we model the vehicle motion as a weighted sum of individual maneuvers. These are processed by a multiple model Kalman Filter to improve accuracy. Third, a maneuver recognition algorithm is used to select automatically the type of motion taken by the vehicle. The performance of our localization system has been evaluated in a quantitative manner by comparing it with a reference trajectory. This reference trajectory is estimated by a localization system based on high-grade GPS-IMU-odometer. Extensive trials were performed in different real traffic conditions; results have validated the approach and demonstrated tremendous potential.

Vehicle following can be achieved by minimizing the relative information (Kullback-Leibler or K-L distance), between the estimated poses of leader and follower vehicles by formulating the vehicle following system as an optimization problem. The aim is to search for an optimal control action for the follower vehicle in the admissible control command space. Relative information is used as a metric in the search space and for evaluating the expected performance of vehicle following. With this metric, and based on the assumption that both vehicle pose (position and orientation) distributions are Gaussian functions, the K-L distance of the vehicle following system can be computed. With a series of admissible actions, such as steering and velocity commands, for the follower vehicle at each pose prediction step, and by minimizing the K-L distance, an optimized action for the follower vehicle can be obtained. The proposed vehicle following algorithm has been tested and the performance of the follower vehicle when the leader undergoes various kinds of maneuvers has been analyzed. Results using this new method, as compared to classical methods, have shown the advantages of this method.

A framework for the development of Autonomous Unmanned Systems is presented in this paper. This framework is based on the belief that autonomy is the outcome of an intelligent decision-making process that enables a system to maximize its own survival within its operating constraints. The guiding principles of this approach, as applied to Autonomous Unmanned Ground Vehicles (AUGVs) are included. This interpretation of survivability is based on insights from cognitive science, psychology, and animal behaviour. we adopt a biologically-inspired approach by considering the needs and emotions of an autonomous system, and it is the ability of the system to fulfil these needs that contributes to its survival, as is the case with living creatures. Within this framework, survivability emerges from the process of determining the behaviour, or sequence of behaviours that maximizes the probability of meeting the needs of the system. Such an interpretation is purported to be conducive for the emergence of intelligence and autonomy in unmanned systems. This paper presents a description of the proposed framework and a case study as applied to a personal, man-transportable AUGV where the application of these concepts are formulated and simulated for verification purposes.

Simultaneous localization and mapping problem for mobile robots has received considerable attention over the last decade. The widely used formulation of the SLAM problem has been the augmented state approach in an estimation theoretic framework. Although, many related issues of SLAM such as computational complexity, loop closing and data association have received much attention, the observability issue has largely remained ignored. System observability is an important aspect in any state estimation problem. Observability analysis provides for understanding of the fundamental limits of the solution obtainable, regardless of process and measurement noises. The standard world-centric SLAM formulation is a highly non-linear system. Thus the direct use of linear observability tools and criteria in the analysis of its observability yields incorrect and inconsistent results. In this paper an appropriate method of analysis of the observability of non-linear systems is applied to investigate the properties of the standard SLAM formulation. Contrary to popular belief, it is shown through theoretical analysis that the standard 2D planar world-centric SLAM formulation involving odometry inputs for robot speed and heading, and range/bearing measurements to features in the environment is unobservable. It is also shown that for the system to be observable, it requires at least two absolutely known feature point positions, thus questioning the very meaning implied by SLAM. The analytical results thus established are verified through simulations.

A good localization ability is essential for an autonomous vehicle to perform any functions. For ground vehicles operating in outdoor, uneven and unstructured environments, the localization task becomes much more difficult than in indoor environments. In urban or forest environments where high buildings or tall trees exist, GPS sensors also fail easily. The main contribution of this paper is that a multi-aided inertial based localization system has been developed to solve the outdoor localization problem. The multi-aiding information is from odometry, an accurate gyroscope and vehicle constraints. Contrary to previous work, a kinematic model is developed to estimate the inertial sensor’s lateral velocity. This is particularly important when cornering at speed, and side slip occurs. Experimental results are presented of this system which is able to provide a vehicle’s position, velocity and attitude estimation accurately, even when the testing vehicle runs in outdoor uneven environments.

The ability to construct a consistent map whilst determining its pose is a prerequisite for mobile robot navigation. When operating in circuit-like trajectories (e.g. surveillance), acquiring large cyclic maps and closing these trajectories is very important. This paper presents the use of map-based a-priori knowledge for constraining the solution to the simultaneous localization and mapping problem. This is formulated in a Bayesian framework where a probabilistic model of the traversable environment (e.g. road network map) is used to minimise the accumulated errors in robot localization during cyclic mapping. The implementation uses an adaptive Rao-Blackwellized particle filter to optimise computation. The map-based priors are generated from a road network map that describes the robot traversable areas. The principle is to bind effectively the adaptive sample-based representation of the robot estimation using the probability map whilst detecting and mapping distinct features found at the roadsides. it allows the number of samples to be reduced and the particle depletion problem that compromises the robot closing large loops minimized. Extensive experiments were conducted using a vehicle test-bed travelling at 15Km/h in a University Campus road network. These have shown that our approach enables us to build cyclic maps and thus close the cycles (trajectories) in a much better manner than other existing methods.

Low-cost inertial measurement units (IMUs) are increasingly becoming commercially available and the use of IMUs in autonomous vehicle applications has increased rapidly in the past decade. IMUs are subject to various errors, such as biases, drifts, nonlinearities, scale factors and noise. The noise is produced by various sources, such as thermal and vibrational disturbances. Noise estimation is critical in accurate inertial navigation systems (INS). The main contribution of this paper is that a noise analysis of the raw accelerations measured by IMUs during signal presence (i.e, an acceleration caused by a specific force) or absence (when the IMU undergoes constant velocity) is carried out to reduce these noise components, which corrupt the inertial data. After noise reduction, multi-aiding information from odometry, a single-axis gyroscope and vehicle constraints is utilized to bound the error growth of the inertial data and produce a reliable outdoor localization system. Experimental results are presented to show the effectiveness of the noise reduction method and the improved accuracy of the multi-aided INS.

Through the use of a virtual trailer link model, autonomous vehicle following capabilities have been demonstrated. The principle is based on the modelling of the trailer link, used in the off-hooked trailer system, as a virtual link between the leading and led vehicles. The leader vehicle is modelled as the tractor (towing vehicle) and the follower vehicle as the trailer (towed vehicle). This method enables our autonomous vehicle to follows the estimated trajectory of the virtual trailer, which is predicted from observations of the maneuvers of the lead vehicle. Unlike conventional methods, in our system, neither communication links between two vehicles nor the installation of special road infrastructures are needed for the implementation. Communication system may failed and the installation of road infrastructures are costly. We show that system response of the virtual trailer link model is much smoother. A series of simulations and experimental results have indicated the validity of the proposed method.

In this paper, we proposed a robot vehicle following algorithm which can navigate a 10 ton armored personnel carrier to follow a leading vehicle (MPV) in the jungle. This algorithm comprises two components, the first one is a target tracking module which can detect and track the lead vehicle from the measurements of a SICK laser scanner; the second one is a obstacle avoidance module which takes the tracking results and the local environment description as input, it then generates the set-points for the vehicle to follow. Plenty of trials have been carried out in the jungle of Singapore, our technique's validity and robust is demonstrated and tested, the results will be showed in this paper.

Robot localisation in neighbourhood environments situated in equatorial regions presents many different challenges to those found elsewhere, buildings are sparse and the surrounding areas are covered by dense vegetation. In this paper, a Bayesian formulated framework that uses a road network topology in the form of a map to constrain the simultaneous localization and mapping (SLAM) solution is presented. The implementation uses a Rao-Blackwellized particle filter with adaptive particle sampling sets to optimise computation. The rationale is to bind effectively the adaptive sample-based representation of robot localisation estimation using a road network map whilst detecting and mapping distinct features found at the roadsides. This allows the reduction of the number of samples for ease of computation. In addition the particle depletion problem that compromises the robot closing large loops is minimized. The effectiveness of the approach is demonstrated via experimentation on a vehicle test-bed travelling in a university campus road network.

Laser detection and ranging sensors or LADARs are widely used in mobile robotics as sensing mechanism. When processing LADAR data for the purposes of feature extraction and/or data association, most previous works model such devices as processing range data which follows a normal distribution. In this paper, it will be demonstrated that commonly used LADARs with separated transmitter and receiver configuration suffer from incorrect range readings at range discontinuities due to occlusion, a much more detrimental effect on feature extraction or data association algorithms than random noise. The occurrence of these errors can be reliably predicted by monitoring the received signal strength. A useful design criterion for the optical separation of the transmitter and receiver is derived for non-coaxial LADARs and the exact environmental conditions which can cause range errors is quantified so that such errors can be reliably predicted.

A robust vehicle following system with obstacle avoidance capabilities for operation in natural environments is described in this paper. By combining a novel vehicle-tracking and detection algorithm with our path-planner for autonomous navigation, it was possible for a tracked logistics armoured ambulance carrier to follow a multi purpose vehicle in an equatorial jungle where few non-paved roads and markers exist. With this new approach, vehicle following performance is enhanced and vehicle safety ensured. Field trials performed in tropical jungle conditions have demonstrated the validity of the approach; results from the field works are included and discussed in this paper.

Feature-based simultaneous localization and map building (SLAM) approaches require a robust method to extract position invariant landmarks from the surrounding environment. 2D laser range finders are currently one of the most common sensors used to obtain environmental information for mobile robot navigation due to their reliability, accuracy and low cost. However, the 2D laser scan data only give very limited information, making it difficult to extract meaningful features particularly in unstructured environments. The most important steps to extract features are segmentation and noise reduction. Scale space and adaptive smoothing are two common techniques within the vision community. They are used to remove high frequency noise and represent image data in multi-scale spaces. They allow for an easier segmentation of images and the extraction of features in the appropriate scale. In this paper, a modified adaptive smoothing algorithm is proposed and applied to laser range data within a modified scale space framework. This algorithm smoothes range data and segments it at the same time by translating a line model mask over the range data. Lines can be extracted from the segments by using a standard fitting algorithm.

A large autonomous logistics tracked carrier, which can be deployed in a tropical forest for day and night, has been developed. This paper presents details of the architecture and major system components. Emphasis is made on the conversion of a highly non-linear and mechanically-operated vehicle into a computer-controlled system, the perception mechanism used to identify drivable areas, and algorithms developed for vehicle path planning. A suite of active and passive sensors is employed for visual guidance. The data from different sensors are fused and fed to a path planner that takes into account the vehicle dynamics and generates the heading and speed commands for the vehicle control system. The paper includes results from a series of field trials completed in a tropical forest and conditions that are unique to the region.

A prerequisite for mobile robot navigation is a reliable sensing mechanism. Laser detection and ranging sensors or LADARs are widely used in mobile robotics. When processing LADAR data for the purposes of feature extraction and/or data association, most previous work models such device as processing range data which follows a normal distribution. In this paper, it would be demonstrated that commonly used LADARs suffer from incorrect range readings at range discontinuities, which can have a much more detrimental effect on feature extraction or data association algorithms than random noise. LADARs with separated transmitter and receiver configuration can introduce a significant occlusion effect, as the reflected laser energy from the target can be partially occluded from the receiver. This paper would demonstrate that false range values can result from LADARs and that the occurrence of these values can be reliably predicted by monitoring the received signal strength. A useful design criterion for the optical separation of the transmitter and receiver is also derived for non-coaxial LADARs. The parameters, which are related to range errors, are quantified so that such errors can be reliably predicted.

The effect of changing the input goal coordinates to a real vehicle's position control system is examined here. Such inputs provide motoring speed/torque signals, based upon local sensor information and the position of the global target, with little regard for the vehicle dynamics. In this article mobile robot path planning parameters are related to the application of correct, general control laws. The derivation of desired velocity/torque signals which feed a vehicle's speed/torque controller and conform to the velocity and acceleration limits of the vehicle is presented. A trajectory planner which produces correct displacement, velocity and acceleration profiles as a function of time is derived. These trajectories drive the vehicle to its target, while always keeping within the defined safe operating acceleration-velocity limits.

Many mobile robot path planning algorithms produce changing intermediate goal coordinates for a mobile robot to pursue. These provide motoring speed/torque signals, based upon local sensor information and the position of the global target, with little regard for the vehicle dynamics. In this article mobile robot path planning parameters are related to the application of correct, general control laws. The derivation of desired velocity signals which feed a vehicle's speed controller and conform to the velocity and acceleration limits of the vehicle is presented. A safe operating area, for the individual wheels of a vehicle is derived in acceleration-velocity space. A trajectory planner which produces correct displacement, velocity and acceleration, profiles as a function of time is derived. These trajectories drive the vehicle to its target, while always keeping within the defined safe operating acceleration-velocity limits.