Autonomous driving has the potential to significantly enhance productivity and provide numerous societal benefits. Ensuring robustness in these safety-critical systems is essential, particularly when vehicles must navigate adverse weather conditions and sensor corruptions that may not have been encountered during training. Current methods often overlook uncertainties arising from adversarial conditions or distributional shifts, limiting their real-world applicability. We propose an efficient adaptation of an uncertainty estimation technique for 3D occupancy prediction. Our method dynamically calibrates model confidence using epistemic uncertainty estimates. Our evaluation under various camera corruption scenarios, such as fog or missing cameras, demonstrates that our approach effectively quantifies epistemic uncertainty by assigning higher uncertainty values to unseen data. We introduce region-specific corruptions to simulate defects affecting only a single camera and validate our findings through both scene-level and region-level assessments. Our results show superior performance in Out-of-Distribution (OoD) detection and confidence calibration compared to common baselines such as Deep Ensembles and MC-Dropout. Our approach consistently demonstrates reliable uncertainty measures, indicating its potential for enhancing the robustness of autonomous driving systems in real-world scenarios. Code and dataset are available at https://github.com/ika-rwth-aachen/OCCUQ.

In an increasingly automated world – from ware-house robots to self-driving cars – streamlining the development and deployment process and operations of robotic applications becomes ever more important. Automated DevOps processes and microservice architectures have already proven successful in other domains such as large-scale customer-oriented web services (e.g., Netflix). We recommend to employ similar microservice architectures for the deployment of small- to large-scale robotic applications in order to accelerate development cycles, loosen functional dependence, and improve resiliency and elasticity. In order to facilitate involved DevOps processes, we present and release a tooling suite for automating the development of microservices for robotic applications based on the Robot Operating System (ROS). Our tooling suite covers the automated minimal containerization of ROS applications, a collection of useful machine learning-enabled base container images, as well as a CLI tool for simplified interaction with container images during the development phase. Within the scope of this paper, we embed our tooling suite into the overall context of streamlined robotics deployment and compare it to alternative solutions. We release our tools as open-source software at github.com/ika-rwth-aachen/dorotos.

Multi-modal 3D object detection models for automated driving have demonstrated exceptional performance on computer vision benchmarks like nuScenes. However, their reliance on densely sampled LiDAR point clouds and meticulously calibrated sensor arrays poses challenges for real-world applications. Issues such as sensor misalignment, miscalibration, and disparate sampling frequencies lead to spatial and temporal misalignment in data from LiDAR and cameras. Additionally, the integrity of LiDAR and camera data is often compromised by adverse environmental conditions such as inclement weather, leading to occlusions and noise interference. To address this challenge, we introduce MultiCorrupt, a comprehensive benchmark designed to evaluate the robustness of multi-modal 3D object detectors against ten distinct types of corruptions. We evaluate five state-of-the-art multi-modal detectors on MultiCorrupt and analyze their performance in terms of their resistance ability. Our results show that existing methods exhibit varying degrees of robustness depending on the type of corruption and their fusion strategy. We provide insights into which multi-modal design choices make such models robust against certain perturbations. The dataset generation code and benchmark are open-sourced at https://github.com/ika-rwth-aachen/MultiCorrupt.

Future mobility systems and their components are increasingly defined by their software. The complexity of these cooperative intelligent transport systems (C-ITS) and the ever-changing requirements posed at the software require continual software updates. The dynamic nature of the system and the practically innumerable scenarios in which different software components work together necessitate efficient and automated development and testing procedures that use simulations as one core methodology. The availability of such simulation architectures is a common interest among many stakeholders, especially in the field of automated driving. That is why we propose CARLOS - an open, modular, and scalable simulation framework for the development and testing of software in C-ITS that leverages the rich CARLA and ROS ecosystems. We provide core building blocks for this framework and explain how it can be used and extended by the community. Its architecture builds upon modern microservice and DevOps principles such as containerization and continuous integration. In our paper, we motivate the architecture by describing important design principles and showcasing three major use cases - software prototyping, data-driven development, and automated testing. We make CARLOS and example implementations of the three use cases publicly available at github.com/ika-rwth-aachen/carlos.

Scenario-based testing of automated driving functions has become a promising method to reduce time and cost compared to real-world testing. In scenario-based testing automated functions are evaluated in a set of pre-defined scenarios. These scenarios provide information about vehicle behaviors, environmental conditions, or road characteristics using parameters. To create realistic scenarios, parameters and parameter dependencies have to be fitted utilizing real-world data. However, due to the large variety of intersections and movement constellations found in reality, data may not be available for certain scenarios. This paper proposes a methodology to systematically analyze relations between parameters of scenarios. Bayesian networks are utilized to analyze causal dependencies in order to decrease the amount of required data and to transfer causal patterns creating unseen scenarios. Thereby, infrastructural influences on movement patterns are investigated to generate realistic scenarios on unobserved intersections. For evaluation, scenarios and underlying parameters are extracted from the inD dataset. Movement patterns are estimated, transferred and checked against recorded data from those initially unseen intersections.

Scenario-based testing has become a promising approach to overcome the complexity of real-world traffic for safety assurance of automated vehicles. Within scenario-based testing, a system under test is confronted with a set of predefined scenarios. This set shall ensure more efficient testing of an automated vehicle operating in an open context compared to real-world testing. However, the question arises if a scenario catalog can cover the open context sufficiently to allow an argumentation for sufficiently safe driving functions and how this can be proven. Within this paper, a methodology is proposed to argue a sufficient completeness of a scenario concept using a goal structured notation. Thereby, the distinction between completeness and coverage is discussed. For both, methods are proposed for a streamlined argumentation and regarding evidence. These methods are applied to a scenario concept and the inD dataset to prove the usability.

Scenario-based testing is a promising method to develop, verify and validate automated driving systems (ADS) since pure on-road testing seems inefficient for complex traffic environments. A major challenge for this approach is the provision and management of a sufficient number of scenarios to test a system. The provision, generation, and management of scenario at scale is investigated in current research. This paper presents the scenario database scenario.center to process and manage scenario data covering the needs of scenario-based testing approaches comprehensively and automatically. Thereby, requirements for such databases are described. Based on those, a four-step approach is proposed. Firstly, a common input format with defined quality requirements is defined. This is utilized for detecting events and base scenarios automatically. Furthermore, methods for searchability, evaluation of data quality and different scenario generation methods are proposed to allow a broad applicability serving different needs. For evaluation, the methodology is compared to state-of-the-art scenario databases. Finally, the application and capabilities of the database are shown by applying the methodology to the inD dataset. A public demonstration of the database interface is provided at https://scenario.center.

The selection of relevant test scenarios for the scenario-based testing and safety validation of automated driving systems (ADSs) remains challenging. An important aspect of the relevance of a scenario is the challenge it poses for an ADS. Existing methods for calculating the challenge of a scenario aim to express the challenge in terms of a metric value. Metric values are useful to select the least or most challenging scenario. However, they fail to provide human-interpretable information on the cause of the challenge which is critical information for the efficient selection of relevant test scenarios. Therefore, this paper presents the Challenge Description Method that mitigates this issue by analyzing scenarios and providing a description of their challenge in terms of the minimum required lane changes and their difficulty. Applying the method to different highway scenarios showed that it is capable of analyzing complex scenarios and providing easy-to-understand descriptions that can be used to select relevant test scenarios.

Cooperation of automated vehicles (AVs) can improve safety, efficiency and comfort in traffic. Digital twins of Cooperative Intelligent Transport Systems (C-ITS) play an important role in monitoring, managing and improving traffic. Computing a live digital twin of traffic requires as input live perception data of preferably multiple connected entities such as automated vehicles (AVs). One such type of perception data are evidential occupancy grid maps (OGMs). The computation of a digital twin involves their spatiotemporal alignment and fusion. In this work, we focus on the spatial alignment, also known as registration, and fusion of evidential occupancy grid maps of multiple automated vehicles. While there exists extensive research on the synchronization and fusion of object-based environment representations, the registration and fusion of OGMs originating from multiple connected vehicles has not been investigated much. We propose a methodology that involves training a deep neural network (DNN) to predict a fused evidential OGM from two OGMs computed by different AVs. The output includes an estimate of the first- and second-order uncertainty. We demonstrate that the DNN trained with synthetic data only outperforms a baseline approach based on coordinate transformation and combination rules also on real-world data. Experimental results on synthetic data show that our approach is able to compensate for spatial misalignments of up to 5 meters and 20 degrees.

The use of smart roadside infrastructure sensors is highly relevant for future applications of connected and automated vehicles. External sensor technology in the form of intelligent transportation system stations (ITS-Ss) can provide safety-critical real-time information about road users in the form of a digital twin. The choice of sensor setups has a major influence on the downstream function as well as the data quality. To date, there is insufficient research on which sensor setups result in which levels of ITS-S data quality. We present a novel approach to perform detailed quality assessment for smart roadside infrastructure sensors. Our framework is multimodal across different sensor types and is evaluated on the DAIR-V2X dataset. We analyze the composition of different lidar and camera sensors and assess them in terms of accuracy, latency, and reliability. The evaluations show that the framework can be used reliably for several future ITS-S applications.

Edge nodes such as Intelligent Transportation System Stations are becoming increasingly relevant in the context of automated driving as they provide connected vehicles with additional information to support their automated driving functions. However, the power budget for these edge nodes is limited and data has to be processed in real-time to be of use to automated driving functions. In this work, we present a system for processing raw lidar data in real-time on an FPGA, resulting in a significant reduction in power consumption compared to conventional hardware. Our approach leads to a 42.4% reduction in power consumption while maintaining the quality of the results. Processing two 128-layer surround-view lidar point clouds takes 522 ms per frame and an average power consumption of 39.3 W for the CPU and 34.5W for the FPGA. Our optimizations surpass the state-of-the-art by up to 193 times.

Scenario-based approaches are important for verifying and validating automated driving systems due to the complexity of traffic, which cannot be covered by on-road tests. A challenge is the definition of a scenario catalog that is not too abstract to address this complexity, but still keeps a manageable number of driving scenarios. This paper presents a semi-formalized approach to derive a scenario catalog, resulting in less than 300 base-scenarios, for use in a driving scenario database for safety validation of automated driving. The approach defines abstract concepts as collections of characteristics to distinguish different driving scenarios. Within high-level categories, certain concepts are combined, either as full factorial of characteristics, or by considering, that the combination of characteristics implies other characteristics. Superclasses are also defined to group scenarios with common characteristics. The approach efficiently represents real-world interactions and can cover many existing catalogs within predefined constraints.

Storing and transmitting LiDAR point cloud data is essential for many AV applications, such as training data collection, remote control, cloud services or SLAM. However, due to the sparsity and unordered structure of the data, it is difficult to compress point cloud data to a low volume. Transforming the raw point cloud data into a dense 2D matrix structure is a promising way for applying compression algorithms. We propose a new lossless and calibrated 3D-to-2D transformation which allows compression algorithms to efficiently exploit spatial correlations within the 2D representation. To compress the structured representation, we use common image compression methods and also a self-supervised deep compression approach using a recurrent neural network. We also rearrange the LiDAR’s intensity measurements to a dense 2D representation and propose a new metric to evaluate the compression performance of the intensity. Compared to approaches that are based on generic octree point cloud compression or based on raw point cloud data compression, our approach achieves the best quantitative and visual performance. Source code and dataset are available at https://github.com/ika-rwth-aachen/Point-Cloud-Compression.

Development and safety validation of highly automated vehicles increasingly relies on data and data-driven methods. In processing sensor datasets for environment perception, it is common to use public and commercial datasets for training and evaluating machine learning based systems. For system-level evaluation and safety validation of an automated driving system, real-world trajectory datasets are of great value for several tasks in the process, i.a. for testing in simulation, scenario extraction or training of road user agent models. Ground-based recording methods such as sensor-equipped vehicles or infrastructure sensors are sometimes limited, for instance, due to their field of view. Camera-equipped drones, however, offer the ability to record road users without vehicle-to-vehicle occlusion and without influencing traffic. The highway drone dataset (highD) has shown that the recording method is efficient in terms of cumulative kilometers and has become a benchmark dataset for many research questions. It contains many vehicle interactions due to dense traffic, but lacks merging scenarios, which are challenging for highly automated vehicles. Therefore, we propose this highway drone dataset called exiD, recorded using camera-equipped drones at entries and exits on the German Autobahn. The dataset contains 69 172 road users classified as car, truck and vans and a total amount of more than 16 hours of measurement data. For non-commercial public research, the exiD dataset is available free of charge at https://www.exid-dataset.com.

The RGB complementary metal-oxide-semiconductor (CMOS) sensor works within the visible light spectrum. Therefore it is very sensitive to environmental light conditions. On the contrary, a long-wave infrared (LWIR) sensor operating in 8-14 μm spectral band, functions independent of visible light.In this paper, we exploit both visual and thermal perception units for robust object detection purposes. After delicate synchronization and (cross-) labeling of the FLIR [1] dataset, this multi-modal perception data passes through a convolutional neural network (CNN) to detect three critical objects on the road, namely pedestrians, bicycles, and cars. After evaluation of RGB and infrared (thermal and infrared are often used interchangeably) sensors separately, various network structures are compared to fuse the data at the feature level effectively. Our RGB-thermal (RGBT) fusion network, which takes advantage of a novel entropy-block attention module (EBAM), outperforms the state-of-the-art network [2] by 10% with 82.9% mAP.

Automated driving functions have received a lot of attention from the scientific community and the general public in the recent years. However, safety assurance, verification and validation of automated driving systems remain as a huge challenge, among others, towards making automated vehicles available to a broader public. For tackling these challenges, scenario-based validation, as one building block, can be used to show the effect and the impact of automated vehicles in (safety-) relevant scenarios. As of now, this is mainly done without considering external factors that can have a major impact on the performance of humans and systems such as road characteristics and adverse weather conditions. In this paper we focus on the aspect of road characteristics. We present a method to extract road characteristics from online map data and compare that data to the coverage of road characteristics in various datasets. This can be used for the comparison with recorded datasets and thereby give an overview of covered road characteristics as well as the gaps in those characteristics which still need to be covered by further recordings or datasets.

Evidential occupancy grid maps (OGMs) are a popular representation of the environment of automated vehicles. Inverse sensor models (ISMs) are used to compute OGMs from sensor data such as lidar point clouds. Geometric ISMs show a limited performance when estimating states in unobserved but inferable areas and have difficulties dealing with ambiguous input. Deep learning-based ISMs face the challenge of limited training data and they often cannot handle uncertainty quantification yet. We propose a deep learning-based framework for learning an OGM algorithm which is both capable of quantifying first- and second-order uncertainty and which does not rely on manually labeled data. Results on synthetic and on real-world data show superiority over other approaches. Source code and datasets are available at https://github.com/ika-rwth-aachen/EviLOG.

With the recent boost in autonomous driving, increased attention has been paid on radars as an input for occupancy mapping. Besides their many benefits, the inference of occupied space based on radar detections is notoriously difficult because of the data sparsity and the environment dependent noise (e.g. multipath reflections). Recently, deep learning-based inverse sensor models, from here on called deep ISMs, have been shown to improve over their geometric counterparts in retrieving occupancy information [1], [2], [3]. Nevertheless, these methods perform a data-driven interpolation which has to be verified later on in the presence of measurements. In this work, we describe a novel approach to integrate deep ISMs together with geometric ISMs into the evidential occupancy mapping framework. Our method leverages both the capabilities of the data-driven approach to initialize cells not yet observable for the geometric model effectively enhancing the perception field and convergence speed, while at the same time use the precision of the geometric ISM to converge to sharp boundaries. We further define a lower limit on the deep ISM estimate's certainty together with analytical proofs of convergence which we use to distinguish cells that are solely allocated by the deep ISM from cells already verified using the geometric approach.

Automated vehicles rely heavily on data-driven methods, especially for complex urban environments. Large datasets of real world measurement data in the form of road user trajectories are crucial for several tasks like road user prediction models or scenario-based safety validation. So far, though, this demand is unmet as no public dataset of urban road user trajectories is available in an appropriate size, quality and variety. By contrast, the highway drone dataset (highD) has recently shown that drones are an efficient method for acquiring naturalistic road user trajectories. Compared to driving studies or ground-level infrastructure sensors, one major advantage of using a drone is the possibility to record naturalistic behavior, as road users do not notice measurements taking place. Due to the ideal viewing angle, an entire intersection scenario can be measured with significantly less occlusion than with sensors at ground level. Therefore, we created a comprehensive, large-scale urban intersection dataset with naturalistic road user behavior using camera-equipped drones as successor of the highD dataset. The resulting dataset contains more than 13 500 road users including vehicles, bicyclists and pedestrians at intersections in Germany and is called inD. The dataset consists of 10 hours of measurement data from four intersections and is available online for non-commercial research at: https://www.inD-dataset.com.

Modeling perception errors of automated vehicles requires reference data, but common reference measurement methods either cannot capture uninstructed road users or suffer from vehicle-vehicle-occlusions. Therefore, we propose a method based on a camera-equipped drone hovering over the field of view of the perception system that is to be modeled. From recordings of this advantageous perspective, computer vision algorithms extract object tracks suited as reference. As a proof of concept of our approach, we create and analyze a phenomenological error model of a lidar-based sensor system. From eight hours of simultaneous traffic recordings at an intersection, we extract synchronized state vectors of associated true-positive vehicle tracks. We model the deviations of the full lidar state vectors from the reference as multivariate Gaussians. The dependency of their covariance matrices and mean vectors on the reference state vector is modeled by a fully-connected neural network. By customizing the network training procedure and losses, we are able to achieve consistent results even in sparsely populated areas of the state space. Finally, we show that time dependencies of errors can be considered separately during sampling by an autoregressive model.

Accurate environment perception is essential for automated vehicles. Since occlusions and inaccuracies regularly occur, the exchange and combination of perception data of multiple vehicles seems promising. This paper describes a method to combine perception data of automated and connected vehicles in the form of evidential Dynamic Occupany Grid Maps (DOGMas) in a cloud-based system. This system is called the Collective Environment Model and is part of the cloud system developed in the project UNICARagil. The presented concept extends existing approaches that fuse evidential grid maps representing static environments of a single vehicle to evidential grid maps computed by multiple vehicles in dynamic environments. The developed fusion process additionally incorporates self-reported data provided by connected vehicles instead of only relying on perception data. We show that the uncertainty in a DOGMa described by Shannon entropy as well as the uncertainty described by a non-specificity measure can be reduced. This enables automated and connected vehicles to behave in ways not before possible due to unknown but relevant information about the environment.

To perform high speed tasks, sensors of autonomous cars have to provide as much information in as few time steps as possible. However, radars, one of the sensor modalities autonomous cars heavily rely on, often only provide sparse, noisy detections. These have to be accumulated over time to reach a high enough confidence about the static parts of the environment. For radars, the state is typically estimated by accumulating inverse detection models (IDMs). We employ the recently proposed evidential convolutional neural networks which, in contrast to IDMs, compute dense, spatially coherent inference of the environment state. Moreover, these networks are able to incorporate sensor noise in a principled way which we further extend to also incorporate model uncertainty. We present experimental results which show that this approach leads to a denser environment perception in only one time step while at the same time reducing the false positive and negative rates.

Intersections with connected infrastructure and vehicle sensors allow observing vulnerable road users (VRU) longer and with less occlusion than from a moving vehicle. Furthermore, the connected sensors are providing continuous measurements of VRUs at the intersection. Thus, we propose a data-driven prediction model, which benefits of the continuous, local measurements. While most approaches in literature use the most probable path to predict road users, it does not represent the uncertainty in prediction and multiple maneuver options. We propose the use of Recurrent Neural Networks fed with measured trajectories and a variety of contextual information to output the prediction in a local occupancy grid map in polar coordinates. By using polar coordinates, a reliable movement model is learned as base model being insensitive against blind spots in the data. The model is further improved by considering input features containing information about the static and dynamic environment as well as local movement statistics. The model successfully predicts multiple movement options represented in a polar grid map. Besides, the model can continuously improve the prediction accuracy without re-training by updating local movement statistics. Finally, the trained model is providing reliable predictions if applied on a different intersection without data from this intersection.

Generative Adversarial Networks (GANs) are a new network architecture capable of delivering state-of-the-art performance in generating synthetic images in various domains. We train a network called VeGAN (Vehicle Generative Adversarial Network) to generate realistic images of vehicles that look like images taken from a top-down view of an unmanned aerial vehicle (UAV). The generated images are used as additional training data for a semantic segmentation network, which precisely detects vehicles in recordings of traffic on highways. While images are commonly generated randomly for a content-based augmentation, we leverage ideas from the domain of active learning. Using a network which is based on the InfoGAN architecture allows mapping existing vehicle images to a latent space representation. After mapping the complete training dataset, we perform the augmentation in the latent space. The applied techniques include creating variations of given hard negative samples and generating samples in sparsely occupied areas of the latent space. We improve the IoU of the semantic segmentation network from 93.4% to 94.9% and reduce the mean positional error of the detected vehicles' centers from 0.51 to 0.37 pixels in longitudinal and from 0.21 to 0.17 pixels in lateral direction.

In this paper we propose a local trajectory planner for front steered car-like vehicles based on a combined direct optimization of the lateral and longitudinal vehicle guidance. The planner is designed for continuously optimizing a local trajectory based on a provided reference path in a structured or semi-structured driving environment. The planner respects constraints of the driving dynamics as well as actuator lim- itations and avoids static and dynamic obstacles. It is not restricted to a limited set of maneuvers. The implementation of the planner allows an online adaptation of the resulting driving behavior to satisfy different comfort or driving style demands. After Software-in-the-Loop simulations the algorithm was tested in two different real-world driving scenarios in ika’s automated vehicle which provides interfaces for full lateral and longitudinal control.

This paper presents the results of an online questionnaire (N=130) focusing on the impact of initial information for novel systems in two different automation levels. Willingness to share data and privacy concerns were compared between partial and conditional automation. With initial information on system limits manipulated between participants, differences in a priori attitudes and information relevance were analyzed. General attitude towards automation was positive. Willingness to share data when using automation was independent of ADAS experience and automation level. All driver-related data were not considered as sharable. Information relevance was highest for information on the anticipation of take-over situations, with information on certainty of successful situation management being significantly more important if system limits were unspecific. Results provide input for studies analyzing the influence of initial information and online information on take-over performance as well as on willingness to share data when receiving higher levels of automation in return.

Automated valet parking can help manage space in parking garages more efficiently and increase the comfort for the driver by delegating the parking task to the system. To successfully navigate the vehicle in a parking garage, the valet parking system requires a-priori information about the environment. This paper shows an approach to derive a-priori information from available blueprints of a parking lot. Based on the derived map data, paths for Ackermann-steered vehicles are planned to navigate vehicles through the parking area and park them into desired parking spots.

The increasing market penetration of connected vehicles supports the development of highly automated vehicles for various traffic situations. Especially intersections form a bottleneck for the traffic flow and thus offer a high potential not only to increase the efficiency, but also to ensure safety. This paper presents a decoupled and decentralized approach using graph-based methods to optimize longitudinal trajectories for multiple vehicles at urban intersections. The approach enables the vehicles to cooperate, while avoiding collisions, considering dynamic influences like traffic lights, and minimizing a cost function. Furthermore, several heuristics are introduced, reducing the computational effort to solve these complex tasks. Simulations of an intersection scenario using the Monte Carlo method show a reduction of summarized costs, which represent travel time, efficiency and driving comfort, by ~28% compared to a driver model and by ~2.6% compared to a non-cooperative system.

This work describes a methodology to assess the impact of positioning and prediction accuracy on the potential benefit of collision avoidance systems. The predicted position of vulnerable road users (VRU) ahead of the vehicle is affected by measurement and prediction uncertainty. In advanced cooperative collision avoidance systems the position of VRUs is provided by vehicle-to-vehicle or vehicle-to-infrastructure (V2X) communication. This work describes a method to optimize the vehicle's longitudinal and lateral trajectories in critical situations in order to minimize the risk of the situation considering the influence of positioning and prediction inaccuracies of VRU. The findings discussed here define requirements on the prediction accuracy and for vehicle velocities of 50 km/h the predicted VRU position should provide a standard deviation of less than 55 cm.

The increasing electrification of electric drive trains leads to new challenges concerning automotive system design. Since no or only a little amount of useable waste heat is available on a sufficiently high temperature level the passenger cabin heating directly influences the electric driving range for battery electric vehicles (BEVs). The scope of the paper is to analyze the integration of micro-combined heat and power (CHP) units into BEVs providing heating energy in an efficient way. Both the influence on the electric driving range as well as the overall energy efficiency in terms of primary energy and CO2emissions is investigated and compared to other heating systems for BEVs.

Short term motion planners for automated vehicles typically require a reference path as input to optimize the ride quality between distinct vehicle states. This paper presents a novel approach to simplify the generation of such reference paths. It is based on the idea of converting the driving route and all relevant objects from the current vehicle's environment into a road-aligned coordinate system eliminating road's curvature. Based on this, a suitable path using geometric primitives can be constructed, which is then converted back into the original coordinate system. When considered during generation, the resulting reference path guarantees to respect vehicle kinodynamics and is checked against collisions.

Predictive and energy efficient driving styles considerably reduce fuel consumption and emissions of vehicles. Vehicle-to-vehicle and vehicle-to-infrastructure (V2X) communication provide information useful to further optimize fuel economy especially in urban conditions. This work summarizes an optimization approach integrating V2X information in the optimization of longitudinal dynamics. Besides the dimensions distance and velocity also the dimension time is reflected in discrete dynamic programming, which is based on a three-dimensional state space. Upcoming signal states of traffic signals are reflected in the optimization to implement an efficient pass through at intersections. Furthermore, simulated average driving behavior defines a reference for optimized velocity trajectories. This excludes optimization results strongly deviating from average behavior. The approach is implemented in a vehicle in a real-time capable way. In a field test the vehicle approaches a V2X traffic light and the optimization reduces fuel consumption by up to 15 % without increasing travel time.

Current advanced driver assistance systems (ADAS) for lateral support are based on optical sensors for environmental detection. Due to different influences e.g. bad sight conditions or missing lane markings, theses systems might not be able determine the necessary information. In order to improve the availability and reliability of camera based ADAS systems in these situations, the potential of a fusion with navigation information is analyzed at the Institut für Kraftfahrzeuge (ika) RWTH Aachen University. Therefore, a fusion model is developed, which continuously fuses data between a camera system with vehicle inertial data and navigation information. In order to gain optimal results out of the fusion model, different sources of potential errors, which have a negative influence on precision, are identified and analyzed within a sensitivity analysis.

The deployment of predictive driving styles reduces fuel consumption of vehicles significantly, while assistance systems can support drivers in this task. This paper describes a modular approach to consider various sources of information as well as different driver and vehicle types in the prediction and the optimization of the vehicle's longitudinal dynamics to reduce fuel consumption. Energy efficient driving strategies such as roll out or fuel cut-off are compared to the average driving behavior of the driver. The utility of the efficient strategies is assessed relative to the average driver behavior, which is similar to human information processing. Resulting optimal driving strategies are provided to the driver as recommendations or applied to vehicles by intervening assistance systems such as adaptive cruise control. This paper aims to summarize the basic methodology of the approach.

Intelligent Transportation Systems (ITS) are widely expected to deliver a major contribution to the improvement of driving comfort as well as road safety. An insight into the benefits of ITS is an important ingredient in the deployment of ITS. Assessing these benefits is one of the research goals within the 7th Framework Program of the European Commission. Field Operational Tests (FOT) have emerged as an important research methodology for assessing the impact of ITS on driver behavior and performance, traffic safety, traffic efficiency as well as the environment. Within the euroFOT project, a large scale field test that involves approximately 1000 instrumented vehicles on the road all over Europe the impact of eight selected ITS function is tested. Most of these vehicles have one or more ITS applications on board, including continuously operating ones like Adaptive Cruise Control (ACC) and Forward Collision Warning (FCW). This paper describes the method applied for the FOT to assess the impact of the ACC and FCW. The euroFOT approach has some similarities to existing FOTs but includes novel aspects to handle specific limitations and conditions of the FOT and the available data. The paper further describes the final results of the data analysis based on the predefined hypotheses to answer the research questions of the project.