The goal of extrinsic calibration is the alignment of sensor data to ensure an accurate representation of the surroundings and enable sensor fusion applications. From a safety perspective, sensor calibration is a key enabler of autonomous driving. In the current state of the art, a trend from target-based offline calibration towards targetless online calibration can be observed. However, online calibration is subject to strict real-time and resource constraints which are not met by state-of-the-art methods. This is mainly due to the high number of parameters to estimate, the reliance on geometric features, or the dependence on specific vehicle maneuvers. To meet these requirements and ensure the vehicle's safety at any time, we propose a miscalibration detection framework that shifts the focus from the direct regression of calibration parameters to a binary classification of the calibration state, i.e., calibrated or miscalibrated. Therefore, we propose a contrastive learning approach that compares embedded features in a latent space to classify the calibration state of two different sensor modalities. Moreover, we provide a comprehensive analysis of the feature embeddings and challenging calibration errors that highlight the performance of our approach. As a result, our method outperforms the current state-of-the-art in terms of detection performance, inference time, and resource demand. The code is open source and available on https://github.com/TUMFTM/MiscalibrationDetection.

This work presents a methodology to estimate tire parameters and their uncertainty using a Bayesian optimization approach. The literature mainly considers the estimation of tire parameters but lacks an evaluation of the parameter identification quality and the required slip ratios for an adequate model fit. Therefore, we examine the use of Stochastical Variational Inference as a methodology to estimate both - the parameters and their uncertainties. We evaluate the method compared to a state-of-the-art Neider-Mead algorithm for theoretical and real-world application. The theoretical study considers parameter fitting at different slip ratios to evaluate the required excitation for an adequate fitting of each parameter. The results are compared to a sensitivity analysis for a Pacejka Magic Formula tire model. We show the application of the algorithm on real-world data acquired during the Abu Dhabi Autonomous Racing League and highlight the uncertainties in identifying the curvature and shape parameters due to insufficient excitation. The gathered insights can help assess the acquired data's limitations and instead utilize standardized parameters until higher slip ratios are captured. We show that our proposed method can be used to assess the mean values and the uncertainties of tire model parameters in real-world conditions and derive actions for the tire modeling based on our simulative study.

Usually, a controller for path- or trajectory tracking is employed in autonomous driving. Typically, these controllers generate high-level commands like longitudinal acceleration or force. However, vehicles with combustion engines expect different actuation inputs. This paper proposes a longitudinal control concept that translates high-level trajectory-tracking commands to the required low-level vehicle commands such as throttle, brake pressure and a desired gear. We chose a modular structure to easily integrate different trajectory-tracking control algorithms and vehicles. The proposed control concept enables a close tracking of the high-level control command. An anti-lock braking system, traction control, and brake warmup control also ensure a safe operation during real-world tests. We provide experimental validation of our concept using real world data with longitudinal accelerations reaching up to$25\frac{m}{s^{2}}$. The experiments were conducted using the EAV24 racecar during the first event of the Abu Dhabi Autonomous Racing League on the Yas Marina Formula 1 Circuit.

Deep learning models for object detection in autonomous driving have recently achieved impressive performance gains and are already being deployed in vehicles worldwide. However, current models require increasingly large datasets for training. Acquiring and labeling such data is costly, necessitating the development of new strategies to optimize this process. Active learning is a promising approach that has been extensively researched in the image domain. In our work, we extend this concept to the LiDAR domain by developing several inconsistency-based sample selection strategies and evaluate their effectiveness in various settings. Our results show that using a naive inconsistency approach based on the number of detected boxes, we achieve the same mAP as the random sampling strategy with 50% of the labeled data.

Autonomous driving is a complex undertaking. A common approach is to break down the driving task into individual sub tasks through modularization. These sub-modules are usually developed and published separately. However, if these individually developed algorithms have to be combined again to form a full-stack autonomous driving software, this poses particular challenges. Drawing upon our practical experience in developing the software of TUM Autonomous Motorsport, we have identified and derived these challenges in developing an autonomous driving software stack within a scientific environment. We do not focus on the specific challenges of individual algorithms but on the general difficulties that arise when deploying research algorithms on real-world test vehicles. To overcome these challenges, we introduce strategies that have been effective in our development approach. We additionally provide open-source implementations that enable these concepts on GitHub. As a result, this paper's contributions will simplify future full-stack autonomous driving projects, which are essential for a thorough evaluation of the individual algorithms.

In autonomous systems, precise object detection and uncertainty estimation are critical for self-aware and safe operation. This work addresses confidence calibration for the classification task of 3D object detectors. We argue that it is necessary to regard the calibration of the full predictive confidence distribution over all classes and deduce a metric which captures the calibration of dominant and secondary class predictions. We propose two auxiliary regularizing loss terms which introduce either calibration of the dominant prediction or the full prediction vector as a training goal. We evaluate a range of post-hoc and train-time methods for CenterPoint, PillarNet and DSVT-Pillar and find that combining our loss term, which regularizes for calibration of the full class prediction, and isotonic regression lead to the best calibration of CenterPoint and PillarNet with respect to both dominant and secondary class predictions. We further find that DSVT-Pillar can not be jointly calibrated for dominant and secondary predictions using the same method.

Conventional trajectory planning approaches for autonomous vehicles often assume a fixed vehicle model that remains constant regardless of the vehicle's location. This overlooks the critical fact that the tires and the surface are the two force-transmitting partners in vehicle dynamics; while the tires stay with the vehicle, surface conditions vary with location. Recognizing these challenges, this paper presents a novel framework for spatially resolving dynamic constraints in both offline and online planning algorithms applied to autonomous racing. We introduce the GripMap concept, which provides a spatial resolution of vehicle dynamic constraints in the Frenet frame, allowing adaptation to locally varying grip conditions. This enables compensation for location-specific effects, more efficient vehicle behavior, and increased safety, unattainable with spatially invariant vehicle models. The focus is on low storage demand and quick access through perfect hashing. This framework proved advantageous in real-world applications in the presented form. Experiments inspired by autonomous racing demonstrate its effectiveness. In future work, this framework can serve as a foundational layer for developing future interpretable learning algorithms that adjust to varying grip conditions in real-time.

State-of-the-art LiDAR calibration frameworks mainly use non-probabilistic registration methods such as Iterative Closest Point (ICP) and its variants. These methods suffer from biased results due to their pair-wise registration procedure as well as their sensitivity to initialization and parameterization. This often leads to misalignments in the calibration process. Probabilistic registration methods compensate for these drawbacks by specifically modeling the probabilistic nature of the observations. This paper presents GMMCalib, an automatic target-based extrinsic calibration approach for multi-LiDAR systems. Using an implementation of a Gaussian Mixture Model (GMM)-based registration method that allows joint registration of multiple point clouds, this data-driven approach is compared to ICP algorithms. We perform simulation experiments using the digital twin of the EDGAR research vehicle and validate the results in a real-world environment. We also address the local minima problem of local registration methods for extrinsic sensor calibration and use a distance-based metric to evaluate the calibration results. Our results show that an increase in robustness against sensor miscalibrations can be achieved by using GMM-based registration algorithms. The code is open source and available on GitHub3.

Today, deep learning detectors for autonomous driving are delivering impressive results on public datasets and in real-world applications. However, these detectors require large amounts of data, especially labeled data, to achieve the performance needed to ensure safe driving. The process of collecting and tagging data is expensive and cumbersome. Therefore, the recent focus of the industry has been on how to achieve similar performance while limiting the amount of labeled data required to train such models. Within the cross-modal active learning paradigm, we propose and analyze new strategies to exploit the inconsistencies between camera and LiDAR detectors to improve sampling efficiency and label only the samples that promise improvements for model training. For this, we leverage the 2D projection of the bounding boxes to equalize the output quality of camera and LiDAR detections. Finally, we achieve up to 0.6% AP improvement for camera and 2% improvement for LiDAR over random sampling on the KITTI dataset using a sampling strategy based on the number of detected objects.

Simulation is crucial in the development of autonomous driving software. In particular, assessing control algorithms requires an accurate vehicle dynamics simulation. However, recent publications use models with varying levels of detail. This disparity makes it difficult to compare individual control algorithms. Therefore, this paper aims to investigate the influence of the fidelity of vehicle dynamics modeling on the closed-loop behavior of trajectory-following controllers. For this purpose, we introduce a comprehensive Autoware-compatible vehicle model. By simplifying this, we derive models with varying fidelity. Evaluating over 550 simulation runs allows us to quantify each model’s approximation quality compared to real-world data. Furthermore, we investigate whether the influence of model simplifications changes with varying margins to the acceleration limit of the vehicle. From this, we deduce to which degree a vehicle model can be simplified to evaluate control algorithms depending on the specific application. The real-world data used to validate the simulation environment originate from the Indy Autonomous Challenge race at the Autodromo Nazionale di Monza in June 2023. They show the fastest fully autonomous lap of TUM Autonomous Motorsport, with vehicle speeds reaching $267\frac{{{\text{km}}}}{{\text{h}}}$ and lateral accelerations of up to $15\frac{{{\text{mm}}}}{{{{\text{s}}^2}}}$.

Autonomous trucking is a promising technology that can greatly impact modern logistics and the environment. Ensuring its safety on public roads is one of the main duties that requires an accurate perception of the environment. To achieve this, machine learning methods rely on large datasets, but to this day, no such datasets are available for autonomous trucks. In this work, we present MAN TruckScenes, the first multimodal dataset for autonomous trucking. MAN TruckScenes allows the research community to come into contact with truck-specific challenges, such as trailer occlusions, novel sensor perspectives, and terminal environments for the first time. It comprises more than 740 scenes of 20 s each within a multitude of different environmental conditions. The sensor set includes 4 cameras, 6 lidar, 6 radar sensors, 2 IMUs, and a high-precision GNSS. The dataset's 3D bounding boxes were manually annotated and carefully reviewed to achieve a high quality standard. Bounding boxes are available for 27 object classes, 15 attributes, and a range of more than 230 m. The scenes are tagged according to 34 distinct scene tags, and all objects are tracked throughout the scene to promote a wide range of applications. Additionally, MAN TruckScenes is the first dataset to provide 4D radar data with 360° coverage and is thereby the largest radar dataset with annotated 3D bounding boxes. Finally, we provide extensive dataset analysis and baseline results. The dataset, development kit, and more will be available online.

In this paper, we assess the state of the art in pedestrian trajectory prediction within the context of generating single trajectories, a critical aspect aligning with the requirements in autonomous systems. The evaluation is conducted on the widely-used ETH/UCY dataset where the Average Displacement Error (ADE) and the Final Displacement Error (FDE) are reported. Alongside this, we perform an ablation study to investigate the impact of the observed motion history on prediction performance. To evaluate the scalability of each approach when confronted with varying amounts of agents, the inference time of each model is measured. Following a quantitative analysis, the resulting predictions are compared in a qualitative manner, giving insight into the strengths and weaknesses of current approaches. The results demonstrate that although a constant velocity model (CVM) provides a good approximation of the overall dynamics in the majority of cases, additional features need to be incorporated to reflect common pedestrian behavior observed. Therefore, this study presents a data-driven analysis with the intent to guide the future development of pedestrian trajectory prediction algorithms.

Dampers are crucial components of the vehicle’s suspension to enable safe and comfortable driving. Therefore, defects like an oil leakage or a gas loss need to be detected expeditiously and with high accuracy. In this paper, we present a novel approach that relies solely on wheel speed signals to detect continuous levels of damper degradation. A dedicated 100000km real-world driving data set with multiple relevant damper defects and diverse environmental conditions is used for development and validation. Different vehicle types, routes, vehicle loads, tires, and driving styles are taken into account. Our approach comprises a frequency analysis of the wheel speed signals using the Fast Fourier Transform (FFT). A physical connection between defective dampers and oscillations in the wheel speeds enables a regression model to detect defective dampers. By using the residual sum of a polynomial fit of the FFT data points as a regressor variable, the current level of oil loss is determined. Subsequently, the remaining useful life (RUL) of the damper can be extrapolated. The resulting method is a threefold cascaded regression. In our results, we show a high sensitivity of the damper defect detection to vehicle loads as well as low sensitivity to ambient temperatures and rim sizes. The proposed method achieves a mean absolute error (MAE) of 5.4% oil loss. Future research will focus on efficiently implementing the algorithms onboard the vehicle and sending aggregated data to a remote back end for further analysis.

Scenario understanding and motion prediction are essential components for completely replacing human drivers and for enabling highly and fully automated driving (SAE-Level 4/5). In deeply stochastic and uncertain traffic scenarios, autonomous driving software must act beyond existing traffic rules and must predict critical situations in advance to provide safe and comfortable rides. In addition, comprehensive prediction models intend not just to reproduce, but rather to encode the human driver behavior, which requires profound scenario understanding. Hence, research in the field of scenario understanding and motion prediction also contributes to enable intelligent driver behavior models in general. This paper aims to review the state of research and outline common methods. A classification of these models is proposed according to their underlying investigation methodology. Based on this classification, a comparison is drawn between three specific prediction methods, which considers specific functional aspects and general requirements of applicability. The results of the comparison reveal a trade-off between holism and explainability in the state of the art. In conclusion, suggestions for future research objectives to solve this conflict are proposed.

The prediction of other road users is an essential task in autonomous driving for preventing collisions and enabling dynamic trajectory planning. This task becomes even more complex because different road users have different driving behaviors. There are underlying intentions that cannot be predicted with certainty without direct communication. In the current state of the art, most promising pattern-based models are trained on a dataset and then applied in the real world. In this paper we present an algorithm for vehicle trajectory prediction that is using online learning. The algorithm uses observations during the inference to optimize the underlying neural network at runtime. We show that our model can adapt to an observed behavior and thus improve the predicted uncertainty of trajectory predictions. Furthermore, we emphasize that our online learning approach can be transferred to many problems in self-supervised learning. The code used in this research is available as open-source software: https://github.com/TUMFTM/Wale-Net

We propose a prediction model to forecast the coverage of road networks in vehicle-to-vehicle or vehicle-to-infrastructure (V2X) networks for cloud-based automotive applications. The model is derived from fleet tests in the City of Munich (Germany). It considers the fleet and the road network characteristics by splitting the network into sub-networks and using the fleet's relative mileage on the sub-networks. The correlation of the spatial coverage and the fleet's mileage is analyzed for each sub-network showing that the expected degressive correlation exists. The derived regression model also shows a comparable fit for a data series taking the driving direction into account. Finally, we validated the model's ability to predict the temporal coverage by reducing the considered time intervals and taking the number of observations into account. The results show that the model can be used to predict the availability, the up-to-dateness and the accuracy of extended floating car data (XFCD).

Automation of the driving task continues to progress rapidly. In addition to improving the algorithms, proof of their safety is still an unsolved problem. For an automated driving function that does not require permanent monitoring by the driver, a theoretically infinite number of possible traffic situations must be tested. One promising method to overcome this problem is the scenario-based approach. This approach shall enable an economic certification of automated driving functions with sufficient test space coverage. However, even with this approach, the selection of the scenarios to be tested is still problematic. The first step is to consider a driver assistance system in order to reduce complexity. For the Lane Keeping Assist System under consideration, this paper defines a methodology as well as the scenarios for a comprehensive yet economically-feasible certification. Economical-feasibility of the presented methodology is shown in the results by an approximation of the resulting simulation costs for executing the defined test cases.

This paper presents a detailed description of the software architecture that is used in the autonomous Roborace vehicles by the TUM-Team. The development of the software architecture was driven by both hardware components and usage of open source languages for making the software architecture reusable and easy to understand. The architecture combines the autonomous software functions perception, planning and control which are modularized for the usage on different hardware and for the purpose of using the car on high speed racetracks. The goal of the paper is to show which software functions are necessary for letting the car drive autonomously and fast around a racetrack.

Vehicle automation is linked to various benefits such as an increase in fuel and transport efficiency, as well as an increase in driving comfort. Automation also comes with a variety of downsides e.g. loss of situation awareness, loss of skills as well as inappropriate trust levels regarding system functionality. Drawbacks differ between automation levels. As highly-automated driving (level 3) requires the driver to take over the driving task in critical situations within a limited period of time, the need for an appropriate human-machine interface (HMI) arises. To foster adequate and efficient humanmachine interaction, this contribution presents a user-centered, iterative approach for HMI design for highly-automated truck driving.An expert workshop was conducted to develop first ideas and HMI ketches. Workshop results were combined with scientific findings regarding HMI design for highly-automated car driving. Based on those findings, a paper prototype was created and evaluated with experts, using an approach of mixed qualitative methods (heuristic evaluation, thinking aloud). The outcome was implemented to the HMI concept. In a third step, the HMI was conceptualized as video prototype enabling a more detailed evaluation. Again, experts were asked to assess the HMI using qualitative (thinking aloud) and quantitative methods (questionnaires).The result represents a video prototype showing a HMI strategy for highly-automated driving, aiming at fostering a successful human-machine interaction. Relevant issues such as drivers' informational needs, situation awareness and trust were explicitly considered during HMI design. Next steps comprise HMI implementation and user evaluation in a driving simulator to let users experience the HMI in a semi-real driving context.

Due to the limited range of todays electric vehicles, it is important to lower the energy consumption for these vehicles. This can for example be achieved by employing an energy management system. Most research in this field focuses on strategies for individual components and only some literature exists on holistic energy management concepts. This paper presents an optimization-based holistic energy management system. The strategy is currently developed within a simulation environment and will, in the future, be adapted to a usage in existing vehicles. To demonstrate the feasibility of the concept, a hybrid genetic algorithm is implemented. By adjusting the velocity for each spatial discretization step and the air conditioning unit's power for each time step of a driving cycle, the total energy consumption, traveling time, and cabin temperature are optimized. The results show that the energy consumption can be considerably reduced, while keeping the driver comfort well within acceptable limits and the driving time constant.

The usage of battery electric vehicles in the commercial sector provides a lot of advantages. However many commercial company owners are reluctant to switch to battery electric vehicles. Important reasons for this are the insufficient range of battery electric vehicles and the lack of charging infrastructure. This paper presents an analysis of the charging infrastructure for battery electric vehicles in the commercial sector. The analysis is based on fleet test data, which was collected by 16 different commercial companies and 32 individual vehicles in the area of Munich. The approach in this paper is to use a simulation model, in which a backward-facing longitudinal dynamic model can simulate different types of electric vehicles. In addition, a charging simulation is integrated which includes the charging behavior of the user and different types of charging stations in the fleet test area of Munich. With the electric vehicle and charging simulation, it is possible to evaluate the current and future charging infrastructure of Munich. A comparison between public, company, employee and customer charging station locations is displayed in the results.

In order to guarantee a precise range estimation over the lifetime of battery electric vehicles (BEV), various circumstances have to be taken into account. Since the traction battery is, and will continue to be in future, the most costly component in BEVs, high effort has been invested in detecting its aging status. In this paper, a theoretical approach for detecting the battery's state of health is devised. The algorithm uses information from repeating reference cycles completed under comparable thermal situations to derive the health status. This theory is validated by an experimental setup using a battery simulator as the power source and a prototype vehicle in combination with a roller bench as the power sink. Furthermore, the influence of the state of health on the actual driving range is investigated for a class of ultra-compact vehicles. The results show that, in an environment with a dynamometer, the parameters can be estimated with a normalized error of less than one percent. Implementing this in a realistic environment in order to evaluate the exactness of the algorithm is the subject of further research.

This paper presents an evaluation of the potential of integrating electric vehicles into commercial companies. The evaluation is based on fleet test data which was collected for 16 different commercial companies. The basic idea is to use a simulation, in which a backward-facing longitudinal dynamic model can simulate different types of electric vehicles. With this model and the real life velocity profiles from the fleet test data, the requested energy demand by the traction battery can be calculated. In addition, a charging simulation is integrated which includes the charging behavior of the user and the different types of charging stations in the fleet test area. With the electric vehicle and charging simulation it is possible to evaluate two questions: firstly, is it possible to substitute the companies' conventional cars with electric vehicles? Secondly, what influence does the current charging infrastructure has on the mobility of electric vehicles in the commercial sector?

This paper presents the results of research into the application of an active battery switching system in an electric vehicle's drivetrain. The system's purpose is to increase the drivetrain's electrical efficiency, especially in the partial-load range. Efficiency is increased using a switching system that allows the vehicle's traction-battery circuitry to be changed during operation, thereby adjusting the intermediate circuit voltage to that actually required. The system consists of three electronic switches, which allow two different voltages in the intermediate circuit. This paper presents possible operating strategies of the new system developed from roller dynamometer test runs.

Teleoperated driving is known as a transient technology toward full autonomous driving in urban areas. However, this mobility concept suffers mainly from the communication time delay, which may result in safety hazards as well as stop-and-go driving behavior in crowded inner-city areas. This paper presents a novel active safety concept to assist the human operator of the teleoperated vehicle considering the communication time delay. The proposed system reacts not only to the actual driving hazards, but also to the upcoming hazards the human operator is not aware of because of time delay. For this purpose, it predicts the future trajectories of dynamic objects in the vehicle surroundings using a stereo vision based track-before-detect approach and reacts autonomously to the predicted hazards through speed control. After each intervention, the human operator is informed about the autonomous intervention of the vehicle by a Human-Machine-Interface (HMI), having the ability to override this intervention. Results of the test drives show an overall increase of the safety by reduction of Time-To-Collision as well as an improvement of the acceptance of teleoperated driving through the reduction of the overall triggered deceleration during driving in urban areas.

A lack of telepresence is one of the main challenges of vehicle teleoperation, which degrades the task performance of the human operator. This paper introduces a novel human-machine interface (HMI) using a head-mounted display (HMD) to improve the situation awareness and, consequently, the telepresence of the human operator. The proposed HMI concept uses the transmitted data of the camera as well as LiDAR sensors of the remote vehicle to illustrate the 360° vehicle surroundings as a mixture of the real and virtual environments to the human operator. The resulting system provides the possibility to precisely control the remote vehicle with a low additional load to the transmitted data. The developed concept is evaluated by experienced operators within different test scenarios. The results of the test drives show a significant improvement of the task performance as well as a reduction of the workload of the human operators using the proposed HMI concept during control of the teleoperated vehicle.

Despite impressive developments in automated driving technology, several technical, economic and social challenges hinder the large-scale deployment of highly or full automated vehicles. We present teleoperated driving - where in-car drivers are replaced by tele-drivers located at a control center- as a transient technology to enable a driverless, door-to-door taxi service. In this novel service, the transmission of video and audio streams of the vehicle surroundings via wireless networks to the taxi dispatch center allows a human operator to remotely sense the environment through a virtual windshield and to remotely operate the vehicle controls through an emulated cockpit. This safe and cost-effective transport service merges together aspects of taxi transport with car sharing services if the passenger drives part of the route. A large-scale empirical evaluation study proves the feasibility of this novel taxi operation mode and shows that the implementation of the system can reduce, on average, the number of drivers to between 15% and 27% when considering teleoperation during pickup/dropoff and service, respectively. A premium service where passengers are remotely also driven from their origin to the destination also presents considerable gains for taxi operators. Teleoperation of taxi fleets could revolutionize urban mobility by offering a cost-effective and safe door-to-door transportation service.

Lateral control of teleoperated vehicles is a significant challenge for human operators while driving within dense urban scenarios. This paper presents the general system design of a novel haptic assistance system for safe lateral control of these vehicles. The proposed system is based on a direct control structure to keep the human operator as the main decision maker in human- machine cooperating steering tasks. The haptic system uses a two-stage prediction on a LiDAR occupancy grid. The first prediction stage compensates the communication time delay with which the actual states of the teleoperated vehicle as well as other dynamic objects in the environment are predicted. For the second prediction stage, an extension of the look-ahead approach is proposed, which predicts side collisions and generates a smooth haptic feedback at the steering wheel of the operator workstation. The resulted haptic assistance system supports the human operator in a generic way at all challenging scenarios without the need for road information. The results of the test drives conducted by experienced operators show the capability of the developed system to assist the human operator at preventing side collisions as well as stabilizing the lateral control of teleoperated vehicles.

Tracking the mobility behavior of participants with smartphones to determine the CO2 emissions is an overcharging task for researchers. In a fleet test with 52 participants, 9968 datasets were generated, making the manual analysis a long-lasting endeavor. With our work, we are attempting to reduce the analysis time of the generated data and provide in the same way immediate feedback to the participants. We propose an automated mobility tracking system that makes use of a track analyzer that identifies the mode of mobility to calculate CO2 emissions. We will describe the system functions, how the datasets are collected, processed and led back to the users. Based on the setup, calculation accuracy and the feedback from the participants, benefits for user studies in the automotive context are identified. This system will influence the setup of future large data user studies with smartphones.

A lidar-based approach of an emergency braking system for teleoperated vehicles is presented. Despite the time delay for the communication link of a teleoperated system, the vehicle has to be able to react to emerging objects in time. Starting with intelligent sensor data processing, reliable information is computed. An adapted particle filter algorithm tracks moving points to calculate their mean velocity, used for the prediction of surrounding moving objects. Further, in order to interpret this information, a situation assessment based on an intervention concept derived from Kamm’s circle is implemented. A motion prediction of possible trajectories of the ego-vehicle results in a clear decision-making process. All calculations are made at the raw data level and can be done online. Through artificial objects being included in real sensor data, the methodology was validated.

This paper presents a new approach to improve lidar data evaluation on the basis of using a priori knowledge. In addition to the common I- and L-shapes, the directional IS-shape, the C-shape for pedestrians and the E-shape for bicycles are introduced. Considering the expected object shape and predicted position enables effective interpretation even of poor measurement values. Therefore a classification routine is utilized to distinguish between three classes (cars, bicycles, pedestrians). The tracking operation with Kalman filters is based on class specific dynamic models. The fusion of radar objects with the used a priori knowledge improves the quality of the lidar evaluation. Experiments with real measurement data showed good results even with a single layer lidar scanner.

This paper presents a system for the prediction of the necessary energy for selected trips of electric vehicles (EVs), which can be used for various EV assistants like range estimation. We use statistical features extracted from crowd-sourced speed profiles for the energy prediction, since they consider the varying impact factors of the individual driving style and the prevailing traffic condition. A statistical prediction model uses these features in order to predict the deviation from the mean energy consumption of the EV. Hence, the model predicts the variance of energy consumption caused for example by individual driving behavior. The results show an improvement of the energy prediction by 5.4 percentage points if the statistical features are considered. The prediction of the propulsion energy for EVs before the start of a given route has a relative mean error of 6.8%.

The use of Head-Up Displays (HUD) in automobiles to visualize various types of driving information on the windshield has rapidly increased in recent years. However, these HUDs display the graphics on only a specific area of the windshield. This paper introduces a new generation of automotive augmented reality systems for driver assistance at night which detects the 3D positions of potential collision partners as well as the driver's eyes to display the warning information at the exact position according to driver's viewing direction on the full-windshield (FWD). Furthermore, a generic method for unified calibration of various components of this system is proposed. The introduced concepts are validated on a prototype with an external stereo night vision system for obstacle detection, an interior mono night vision system for eye tracking as well as different projection units.

New mobility concepts for urban traffic will benefit from driverless driving. However, fully autonomous driving is not currently feasible in mixed urban traffic. Teleoperation with distinct human-machine interaction is required to manage such highly complex automation tasks. This work discusses the possibility of a safe and reliable approach to the teleoperated driving of road vehicles in urban environments. Based on the current state of the art, this study derives a new trajectory-based approach using the methodology of shared autonomy control. Here, control is based on automated driving along predefined paths. The study shows that trajectory-based driving is fast enough for inner-city traffic and guarantees safety in case of operator connection loss.